phdbib.bib

@article{Nettiksimmons2010,
abstract = {Cerebrospinal fluid (CSF) and structural magnetic resonance imaging (MRI) show patterns of change in Alzheimer's disease (AD) that precede dementia. The Alzheimer's Disease Neuroimaging Initiative (ADNI) studied normal controls (NC), subjects with mild cognitive impairment (MCI), and subjects with AD to identify patterns of biomarkers to aid in early diagnosis and effective treatment of AD. Two hundred twenty-two NC underwent baseline MRI and clinical examination at baseline and at least one follow-up. One hundred twelve also provided CSF at baseline. Unsupervised clustering based on initial CSF and MRI measures was used to identify clusters of participants with similar profiles. Repeated measures regression modeling assessed the relationship of individual measures, and of cluster membership, to cognitive change over 3 years. Most individuals showed little cognitive change. Individual biomarkers had limited predictive value for cognitive decline, but membership in the cluster with the most extreme profile was associated with more rapid decline in ADAS-cog. Subtypes among NC based on multiple biomarkers may represent the earliest stages of subclinical cognitive decline and AD. {\textcopyright} 2010 Elsevier Inc.},
author = {Nettiksimmons, Jasmine and Harvey, Danielle and Brewer, James and Carmichael, Owen and DeCarli, Charles and Jack, C. R. and Petersen, Ronald and Shaw, Leslie M and Trojanowski, John Q and Weiner, Michael W and Beckett, Laurel},
doi = {10.1016/j.neurobiolaging.2010.04.025},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Nettiksimmons et al. - 2010 - Subtypes based on cerebrospinal fluid and magnetic resonance imaging markers in normal elderly predict cog.pdf:pdf},
isbn = {0197-4580},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Amyloid beta-protein,Cerebrospinal fluid,Clustering,Cognition,Dementia,Early diagnosis,Hippocampal volume,Normal controls,Structural magnetic resonance imaging,Tau protein},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {8},
pages = {1419--1428},
pmid = {20542598},
title = {{Subtypes based on cerebrospinal fluid and magnetic resonance imaging markers in normal elderly predict cognitive decline}},
volume = {31},
year = {2010}
}

@inproceedings{Gregor2015a,
abstract = {This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.},
archivePrefix = {arXiv},
arxivId = {1502.04623},
author = {Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo Jimenez and Wierstra, Daan},
booktitle = {32nd Int. Conf. Mach. Learn. ICML 2015},
eprint = {1502.04623},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Gregor et al. - 2015 - DRAW A Recurrent Neural Network For Image Generation(2).pdf:pdf},
isbn = {9781510810587},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates,PhDThesis/VAE},
month = {feb},
pages = {1462--1471},
publisher = {International Machine Learning Society (IMLS)},
title = {{DRAW: A recurrent neural network for image generation}},
volume = {2},
year = {2015}
}


@article{Antelmi2019,
abstract = {Interpretablc modeling of heterogeneous data channels is essential in medical applications, for example when jointly analyzing clinical scores and medical images. Variational Autoencoders (VAE) are powerful generative models that learn representations of complex data. The flexibility of VAE may come at the expense of lack of interpretability in describing the joint relationship between heterogeneous data. To tackle this problem, in this work we extend the variational framework of VAE to bring parsimony and interpretability when jointly account for latent relationships across multiple channels. In the latent space, this is achieved by constraining the variational distribution of each channel to a common target prior. Parsimonious latent representations are enforced by variational dropout. Experiments on synthetic data show that our model correctly identifies the prescribed latent dimensions and data relationships across multiple testing scenarios. When applied to imaging and clinical data, our method allows to identify the joint effect of age and pathology in describing clinical condition in a large scale clinical cohort.},
annote = {Base paper.},
author = {Antelmi, Luigi and Ayache, Nicholas and Robert, Philippe and Lorenzi, Marco},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Antelmi et al. - 2019 - Sparse multi-channel variational autoencoder for the joint analysis of heterogeneous data(2).pdf:pdf},
isbn = {9781510886988},
journal = {36th Int. Conf. Mach. Learn. ICML 2019},
mendeley-groups = {Papers bib/mcvae{\_}paper,PhDThesis/VAE},
pages = {453--464},
title = {{Sparse multi-channel variational autoencoder for the joint analysis of heterogeneous data}},
volume = {2019-June},
year = {2019}
}
@inproceedings{Fabius2015,
abstract = {In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that data can be generated from samples of the latent space. An important contribution of this work is that the model can make use of unlabeled data in order to facilitate supervised training of RNNs by initialising the weights and network state.},
archivePrefix = {arXiv},
arxivId = {1412.6581},
author = {Fabius, Otto and van Amersfoort, Joost R.},
booktitle = {3rd Int. Conf. Learn. Represent. ICLR 2015 - Work. Track Proc.},
eprint = {1412.6581},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Fabius, van Amersfoort - 2014 - Variational Recurrent Auto-Encoders.pdf:pdf},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates,PhDThesis/VAE},
pages = {1--5},
month = {dec},
publisher = {International Conference on Learning Representations, ICLR},
title = {{Variational recurrent auto-encoders}},
year = {2015}
}
@article{Hyun2016,
abstract = {Longitudinal neuroimaging data plays an important role in mapping the neural developmental profile of major neuropsychiatric and neurodegenerative disorders and normal brain. The development of such developmental maps is critical for the prevention, diagnosis, and treatment of many brain-related diseases. The aim of this paper is to develop a spatio-temporal Gaussian process (STGP) framework to accurately delineate the developmental trajectories of brain structure and function, while achieving better prediction by explicitly incorporating the spatial and temporal features of longitudinal neuroimaging data. Our STGP integrates a functional principal component model (FPCA) and a partition parametric space-time covariance model to capture the medium-to-large and small-to-medium spatio-temporal dependence structures, respectively. We develop a three-stage efficient estimation procedure as well as a predictive method based on a kriging technique. Two key novelties of STGP are that it can efficiently use a small number of parameters to capture complex non-stationary and non-separable spatio-temporal dependence structures and that it can accurately predict spatio-temporal changes. We illustrate STGP using simulated data sets and two real data analyses including longitudinal positron emission tomography data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and longitudinal lateral ventricle surface data from a longitudinal study of early brain development.},
annote = {From Duplicate 2 (STGP: Spatio-temporal Gaussian process models for longitudinal neuroimaging data - Hyun, Jung Won; Li, Yimei; Huang, Chao; Styner, Martin; Lin, Weili; Zhu, Hongtu)

Aquest paper hauria d'anar amb els del lorenzi pero no s{\'{e}} molt b{\'{e}} on posar-lo... el deixarem aqu{\'{i}} de moment.},
author = {Hyun, Jung Won and Li, Yimei and Huang, Chao and Styner, Martin and Lin, Weili and Zhu, Hongtu},
doi = {10.1016/j.neuroimage.2016.04.023},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Hyun et al. - 2016 - STGP Spatio-temporal Gaussian process models for longitudinal neuroimaging data(3).pdf:pdf;:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Hyun et al. - 2016 - STGP Spatio-temporal Gaussian process models for longitudinal neuroimaging data(4).pdf:pdf},
issn = {10959572},
journal = {Neuroimage},
keywords = {Functional principal component analysis,Kriging,Neuroimaging,Prediction,Spatio-temporal modeling},
mendeley-groups = {PHD/Machine Learning/Longitudinal related,PHD/Machine Learning/Gaussian Processes,Review2,PHD,PHD/Machine Learning,PhDThesis/VAE},
pages = {550--562},
pmid = {27103140},
publisher = {Elsevier Inc.},
title = {{STGP: Spatio-temporal Gaussian process models for longitudinal neuroimaging data}},
volume = {134},
year = {2016}
}
@article{Hochreiter1997,
abstract = {Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient-based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O(1). Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.},
author = {Hochreiter, Sepp and Schmidhuber, J{\"{u}}rgen},
doi = {10.1162/neco.1997.9.8.1735},
issn = {08997667},
journal = {Neural Comput.},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates,PhDThesis/VAE},
month = {nov},
number = {8},
pages = {1735--1780},
pmid = {9377276},
publisher = {MIT Press Journals},
title = {{Long Short-Term Memory}},
volume = {9},
year = {1997}
}
@article{Goldberg2017,
abstract = {Neural networks are a family of powerful machine learning models. This book focuses on the application of neural network models to natural language data. The first half of the book (Parts I and II) covers the basics of supervised machine learning and feed-forward neural networks, the basics of working with machine learning over language data, and the use of vector-based rather than symbolic representations for words. It also covers the computation-graph abstraction, which allows to easily define and train arbitrary neural networks, and is the basis behind the design of contemporary neural network software libraries. The second part of the book (Parts III and IV) introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural networks, conditioned-generation models, and attention-based models. These architectures and techniques are the driving force behind state-of-the-art algorithms for machine translation, syntactic parsing, and many other applications. Finally, we also discuss tree-shaped networks, structured prediction, and the prospects of multi-task learning.},
author = {Goldberg, Yoav},
doi = {10.2200/S00762ED1V01Y201703HLT037},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Goldberg - 2017 - Neural Network Methods for Natural Language Processing.pdf:pdf},
issn = {19474040},
journal = {Synth. Lect. Hum. Lang. Technol.},
keywords = {deep learning,machine learning,natural language processing,neural networks,recurrent neural networks,sequence to sequence models,supervised learning,word embeddings},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates,PhDThesis/VAE},
month = {apr},
number = {1},
pages = {1--311},
publisher = {Morgan and Claypool Publishers},
title = {{Neural Network Methods for Natural Language Processing}},
volume = {10},
year = {2017}
}



@article{Chung2015,
abstract = {In this paper, we explore the inclusion of latent random variables into the hidden state of a recurrent neural network (RNN) by combining the elements of the variational autoencoder. We argue that through the use of high-level latent random variables, the variational RNN (VRNN)1 can model the kind of variability observed in highly structured sequential data such as natural speech. We empirically evaluate the proposed model against other related sequential models on four speech datasets and one handwriting dataset. Our results show the important roles that latent random variables can play in the RNN dynamics.},
author = {Chung, Junyoung and Kastner, Kyle and Dinh, Laurent and Goel, Kratarth and Courville, Aaron and Bengio, Yoshua},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Chung et al. - 2015 - A recurrent latent variable model for sequential data.pdf:pdf},
issn = {10495258},
journal = {Adv. Neural Inf. Process. Syst.},
mendeley-groups = {Papers bib/mcvae{\_}paper/rnn},
pages = {2980--2988},
title = {{A recurrent latent variable model for sequential data}},
volume = {2015-Janua},
year = {2015}
}

@article{Marti-Juan2020,
abstract = {Background and Objectives: Recently, longitudinal studies of Alzheimer's disease have gathered a substantial amount of neuroimaging data. New methods are needed to successfully leverage and distill meaningful information on the progression of the disease from the deluge of available data. Machine learning has been used successfully for many different tasks, including neuroimaging related problems. In this paper, we review recent statistical and machine learning applications in Alzheimer's disease using longitudinal neuroimaging. Methods: We search for papers using longitudinal imaging data, focused on Alzheimer's Disease and published between 2007 and 2019 on four different search engines. Results: After the search, we obtain 104 relevant papers. We analyze their approach to typical challenges in longitudinal data analysis, such as missing data and variability in the number and extent of acquisitions. Conclusions: Reviewed works show that machine learning methods using longitudinal data have potential for disease progression modelling and computer-aided diagnosis. We compare results and models, and propose future research directions in the field.},
author = {Mart{\'{i}}-Juan, Gerard and Sanroma-Guell, Gerard and Piella, Gemma},
journal = {Comput. Methods Programs Biomed.},
doi = {10.1016/j.cmpb.2020.105348},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Mart{\'{i}}-Juan, Sanroma-Guell, Piella - 2020 - A survey on machine and statistical learning for longitudinal analysis of neuroimaging data i.pdf:pdf},
issn = {18727565},
keywords = {Alzheimer's disease,Disease progression,Longitudinal,Machine learning},
mendeley-groups = {Pensem/Article1,Conferences/PhDThesis/VAE},
month = {jun},
pages = {105348},
publisher = {Elsevier Ireland Ltd},
title = {{A survey on machine and statistical learning for longitudinal analysis of neuroimaging data in Alzheimer's disease}},
volume = {189},
year = {2020}
}


@article{Susanto2015,
abstract = {BACKGROUND: Knowledge of Alzheimer's disease (AD) manifestation in the pre-dementia stage facilitates the selection of appropriate measures for early detection and disease progression. OBJECTIVE: To examine the trajectories of cognitive performance, gray matter volume (GMV), and cerebrospinal fluid (CSF) biomarkers, together with the influence of apolipoprotein E (APOE) in subjects with amyloid-beta (Abeta) deposits across the pre-clinical to dementia stages of AD. METHODS: 356 subjects were dichotomized into Abeta+ and Abeta- groups based on their CSF Abeta1-42 level. We derived AD-related atrophic regions (AD-ROIs) using the voxel-based morphometry approach. We characterized the trajectories of cognitive scores, GMV at AD-ROIs, and CSF biomarkers from preclinical to disease stages in Abeta+ subjects. The effect of APOE epsilon4 genotype on these trajectories was examined. RESULTS: Impairments in executive functioning/processing speed (EF/PS) and atrophy at the right supramarginal/inferior parietal gyrus were detected in cognitively normal Abeta+ subjects. Together with the APOE epsilon4 carrier status, these measures showed potential to identify cognitively normal elderly with abnormal CSF Abeta1-42 level in another independent cohort. Subsequently, impairment in memory, visuospatial, language, and attention as well as atrophy in the temporal lobe, thalamus, and mid-cingulate cortex were detectable in Abeta+ mild cognitive impairment (MCI) subjects. In MCI and dementia Abeta+ subjects, epsilon4 carriers had more severe atrophy of the medial temporal lobe and memory impairment but higher EF/PS compared to non-carriers. CONCLUSIONS: EF/PS decline and right parietal atrophy might act as non-invasive screening tests for abnormal amyloid deposition in cognitively normal elderly. APOE modulation on subsequent trajectories in cognition and atrophy should be taken into account when analyzing disease progression.},
author = {Susanto, Thomas Adi Kurnia and Pua, Emmanuel Peng Kiat and Zhou, Juan},
doi = {10.3233/JAD-142451},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = {Aged,Aged, 80 and over,Alzheimer Disease,Amyloid beta-Peptides,Analysis of Variance,Apolipoproteins E,Atrophy,Biomarkers,Brain,Cognition Disorders,Cohort Studies,Dementia,Female,Humans,Image Processing, Computer-Assisted,Magnetic Resonance Imaging,Male,Neuropsychological Tests,Peptide Fragments,Psychiatric Status Rating Scales,cerebrospinal fluid,complications,diagnosis,etiology,genetics,pathology},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {1},
pages = {253--268},
pmid = {25524955},
title = {{Cognition, brain atrophy, and cerebrospinal fluid biomarkers changes from preclinical to dementia stage of Alzheimer's disease and the influence of apolipoprotein e.}},
volume = {45},
year = {2015}
}
@book{Good2000,
abstract = {This book provides a step-by-step manual on the application of permutation tests in biology, business, medicine, science, and engineering. Its intuitive and informal style will ideally suit it as a text for students and researchers whether experienced or coming to these resampling methods for the first time. The real-world problems of missing and censored data, multiple comparisons, nonresponders, after-the-fact covariates, and outliers are dealt with at length. The book's main features include: * detailed consideration of one-, two-, and k-sample tests, contingency tables, experimental design, clinical trials, cluster analysis, multiple comparisons, multivariate data, regression, and sample size reduction; * numerous practical applications in archeology, biology, climatology, economics, education, medicine, and the social sciences; * valuable techniques for reducing computation time; * practical advice on experimental design; * comparisons with bootstrap, parametric, and nonparametric techniques; * an extensive three-part bibliography featuring more than 1,000 articles. This new edition has more than 100 additional pages, and includes streamlined statistics for the k-sample comparison and analysis of variance plus expanded sections on computational techniques, multiple comparisons, multiple regression, comparing variances, and testing interactions in balanced designs. Comprehensive author and subject indexes, plus an expert-system guide to methods, provide for further ease of use. The invaluable exercises at the end of every chapter have been supplemented with drills and a number of graduate-level thesis problems.},
author = {Good, Phillip.},
doi = {10.1007/978-1-4757-3235-1},
isbn = {038798898X},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
pages = {xvi + 270},
publisher = {Springer New York},
title = {{Permutation tests: a practical guide to resampling methods for testing hypotheses}},
year = {2000}
}
@article{Hu2012,
abstract = {OBJECTIVES: While plasma biomarkers have been proposed to aid in the clinical diagnosis of Alzheimer disease (AD), few biomarkers have been validated in independent patient cohorts. Here we aim to determine plasma biomarkers associated with AD in 2 independent cohorts and validate the findings in the multicenter Alzheimer's Disease Neuroimaging Initiative (ADNI).$\backslash$n$\backslash$nMETHODS: Using a targeted proteomic approach, we measured levels of 190 plasma proteins and peptides in 600 participants from 2 independent centers (University of Pennsylvania, Philadelphia; Washington University, St. Louis, MO), and identified 17 analytes associated with the diagnosis of very mild dementia/mild cognitive impairment (MCI) or AD. Four analytes (apoE, B-type natriuretic peptide, C-reactive protein, pancreatic polypeptide) were also found to be altered in clinical MCI/AD in the ADNI cohort (n = 566). Regression analysis showed CSF A$\beta$42 levels and t-tau/A$\beta$42 ratios to correlate with the number of APOE4 alleles and plasma levels of B-type natriuretic peptide and pancreatic polypeptide.$\backslash$n$\backslash$nCONCLUSION: Four plasma analytes were consistently associated with the diagnosis of very mild dementia/MCI/AD in 3 independent clinical cohorts. These plasma biomarkers may predict underlying AD through their association with CSF AD biomarkers, and the association between plasma and CSF amyloid biomarkers needs to be confirmed in a prospective study.},
author = {Hu, William T and Holtzman, David M and Fagan, Anne M and Shaw, Leslie M and Perrin, Richard and Arnold, Steven E and Grossman, Murray and Xiong, Chengjie and Craig-Schapiro, Rebecca and Clark, Christopher M and Pickering, Eve and Kuhn, Max and Chen, Yu and {Van Deerlin}, Vivianna M and McCluskey, Leo and Elman, Lauren and Karlawish, Jason and Chen-Plotkin, Alice and Hurtig, Howard I and Siderowf, Andrew and Swenson, Frank and Lee, Virginia M.-Y and Morris, John C and Trojanowski, John Q and Soares, Holly},
doi = {10.1212/WNL.0b013e318266fa70},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Hu et al. - 2012 - Plasma multianalyte profiling in mild cognitive impairment and Alzheimer Disease.pdf:pdf},
isbn = {1526-632X},
issn = {1526632X},
journal = {Neurology},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {9},
pages = {897--905},
pmid = {22855860},
title = {{Plasma multianalyte profiling in mild cognitive impairment and Alzheimer Disease}},
volume = {79},
year = {2012}
}
@article{Mattsson2017,
abstract = {Importance Existing cerebrospinal fluid (CSF) or imaging (tau positron emission tomography) biomarkers for Alzheimer disease (AD) are invasive or expensive. Biomarkers based on standard blood test results would be useful in research, drug development, and clinical practice. Plasma neurofilament light (NFL) has recently been proposed as a blood-based biomarker for neurodegeneration in dementias. Objective To test whether plasma NFL concentrations are increased in AD and associated with cognitive decline, other AD biomarkers, and imaging evidence of neurodegeneration. Design, Setting, and Participants In this prospective case-control study, an ultrasensitive assay was used to measure plasma NFL concentration in 193 cognitively healthy controls, 197 patients with mild cognitive impairment (MCI), and 180 patients with AD dementia from the Alzheimer's Disease Neuroimaging Initiative. The study dates were September 7, 2005, to February 13, 2012. The plasma NFL analysis was performed in September 2016. Main Outcomes and Measures Associations were tested between plasma NFL and diagnosis, A$\beta$ pathologic features, CSF biomarkers of neuronal injury, cognition, brain structure, and metabolism. Results Among 193 cognitively healthy controls, 197 patients with mild cognitive impairment, and 180 patients with AD with dementia, plasma NFL correlated with CSF NFL (Spearman $\rho$ = 0.59, P {\textless} .001). Plasma NFL was increased in patients with MCI (mean, 42.8 ng/L) and patients with AD dementia (mean, 51.0 ng/L) compared with controls (mean, 34.7 ng/L) (P {\textless} .001) and had high diagnostic accuracy for patients with AD with dementia vs controls (area under the receiver operating characteristic curve, 0.87, which is comparable to established CSF biomarkers). Plasma NFL was particularly high in patients with MCI and patients with AD dementia with A$\beta$ pathologic features. High plasma NFL correlated with poor cognition and AD-related atrophy (at baseline and longitudinally) and with brain hypometabolism (longitudinally). Conclusions and Relevance Plasma NFL is associated with AD diagnosis and with cognitive, biochemical, and imaging hallmarks of the disease. This finding implies a potential usefulness for plasma NFL as a noninvasive biomarker in AD.},
author = {Mattsson, Niklas and Andreasson, Ulf and Zetterberg, Henrik and Blennow, Kaj and Weiner, Michael W. and Aisen, Paul and Toga, Arthur W. and Petersen, Ronald and Jack, Clifford R. and Jagust, William and Trojanowki, John Q. and Shaw, Leslie M. and Beckett, Laurel and Green, Robert C. and Saykin, Andrew J. and Morris, John C. and Khachaturian, Zaven and Sorensen, Greg and Carrillo, Maria and Kuller, Lew and Raichle, Marc and Holtzman, David and Paul, Steven and Davies, Peter and Fillit, Howard and Hefti, Franz and Mesulam, M. Marcel and Potter, William and Snyder, Peter and Lilly, Eli and Schwartz, Adam and Montine, Tom and Thomas, Ronald G. and Donohue, Michael and Walter, Sarah and Gessert, Devon and Sather, Tamie and Jiminez, Gus and Balasubramanian, Archana B. and Mason, Jennifer and Sim, Iris and Harvey, Danielle and Bernstein, Matthew and Borowski, Bret and Gunter, Jeff and Senjem, Matt and Vemuri, Prashanthi and Jones, David and Kantarci, Kejal and Ward, Chad and Fox, Nick and Thompson, Paul and Schuff, Norbert and DeCarli, Charles and Landau, Susan and Koeppe, Robert A. and Foster, Norm and Reiman, Eric M. and Chen, Kewei and Mathis, Chet and Cairns, Nigel J. and Franklin, Erin and Taylor-Reinwald, Lisa and Lee, Virginia and Korecka, Magdalena and Figurski, Michal and Crawford, Karen and Neu, Scott and Foroud, Tatiana M. and Shen, Li and Faber, Kelley and Kim, Sungeun and Nho, Kwangsik and Potkin, Steven and Thal, Lean and Albert, Marilyn and Frank, Richard and Hsiao, John and Kaye, Jeffrey and Quinn, Joseph and Silbert, Lisa and Lind, Betty and Carter, Raina and Dolen, Sara and Schneider, Lon S. and Pawluczyk, Sonia and Becerra, Mauricio and Teodoro, Liberty and Spann, Bryan M. and Brewer, James and Vanderswag, Helen and Fleisher, Adam and Heidebrink, Judith L. and Lord, Joanne L. and Mason, Sara S. and Albers, Colleen S. and Knopman, David and Johnson, Keith A. Kathleen Kris and Doody, Rachelle S. and Villanueva-Meyer, Javier and Pavlik, Valory and Shibley, Victoria and Chowdhury, Munir and Rountree, Susan and Dang, Mimi and Stern, Yaakov and Honig, Lawrence S. and Bell, Karen L. and Ances, Beau and Morris, John C. and Carroll, Maria and Creech, Mary L. and Mintun, Mark A. and Schneider, Stacy and Oliver, Angela and Marson, Daniel and Geldmacher, David and Love, Marissa Natelson and Griffith, Randall and Clark, David and Brockington, John and Roberson, Erik and Grossman, Hillel and Mitsis, Effie and Shah, Raj C. and {De Toledo-Morrell}, Leyla and Duara, Ranjan and Greig-Custo, Maria T. and Barker, Warren and Onyike, Chiadi and D'Agostino, Daniel and Kielb, Stephanie and Sadowski, Martin and Sheikh, Mohammed O. and Ulysse, Anaztasia and Gaikwad, Mrunalini and Doraiswamy, P. Murali and Petrella, Jeffrey R. and Borges-Neto, Salvador and Wong, Terence Z. and Coleman, Edward and Arnold, Steven E. and Karlawish, Jason H. and Wolk, David A. and Clark, Christopher M. and Smith, Charles D. and Jicha, Greg and Hardy, Peter and Sinha, Partha and Oates, Elizabeth and Conrad, Gary and Lopez, Oscar L. and Oakley, Mary Ann and Simpson, Donna M. and Porsteinsson, Anton P. and Goldstein, Bonnie S. and Martin, Kim and Makino, Kelly M. and Ismail, M. Saleem and Brand, Connie and Preda, Adrian and Nguyen, Dana and Womack, Kyle and Mathews, Dana and Quiceno, Mary and Levey, Allan I. and Lah, James J. and Cellar, Janet S. and Burns, Jeffrey M. and Swerdlow, Russell H. and Brooks, William M. and Apostolova, Liana and Tingus, Kathleen and Woo, Ellen and Silverman, Daniel H.S. and Lu, Po H. and Bartzokis, George and Graff-Radford, Neill R. and Parfitt, Francine and Poki-Walker, Kim and Farlow, Martin R. and Hake, Ann Marie and Matthews, Brandy R. and Brosch, Jared R. and Herring, Scott and {Van Dyck}, Christopher H. and Carson, Richard E. and MacAvoy, Martha G. and Varma, Pradeep and Chertkow, Howard and Bergman, Howard and Hosein, Chris and Black, Sandra and Stefanovic, Bojana and Caldwell, Curtis and Hsiung, Ging Yuek Robin and Mudge, Benita and Sossi, Vesna and Feldman, Howard and Assaly, Michele and Finger, Elizabeth and Pasternack, Stephen and Rachisky, Irina and Trost, Dick and Kertesz, Andrew and Bernick, Charles and Munic, Donna and Rogalski, Emily and Lipowski, Kristine and Weintraub, Sandra and Bonakdarpour, Borna and Kerwin, Diana and Wu, Chuang Kuo and Johnson, Nancy and Sadowsky, Carl and Villena, Teresa and Turner, Raymond Scott and Johnson, Keith A. Kathleen Kris and Reynolds, Brigid and Sperling, Reisa A. and Johnson, Keith A. Kathleen Kris and Marshall, Gad and Yesavage, Jerome and Taylor, Joy L. and Lane, Barton and Rosen, Allyson and Tinklenberg, Jared and Sabbagh, Marwan N. and Belden, Christine M. and Jacobson, Sandra A. and Sirrel, Sherye A. and Kowall, Neil and Killiany, Ronald and Budson, Andrew E. and Norbash, Alexander and Johnson, Patricia Lynn and Obisesan, Thomas O. and Wolday, Saba and Allard, Joanne and Lerner, Alan and Ogrocki, Paula and Tatsuoka, Curtis and Fatica, Parianne and Fletcher, Evan and Maillard, Pauline and Olichney, John and Carmichael, Owen and Kittur, Smita and Borrie, Michael and Lee, T. Y. and Bartha, Rob and Johnson, Sterling and Asthana, Sanjay and Carlsson, Cynthia M. and Tariot, Pierre and Burke, Anna and Milliken, Ann Marie and Trncic, Nadira and Reeder, Stephanie and Bates, Vernice and Capote, Horacio and Rainka, Michelle and Scharre, Douglas W. and Kataki, Maria and Kelley, Brendan and Zimmerman, Earl A. and Celmins, Dzintra and Brown, Alice D. and Pearlson, Godfrey D. and Blank, Karen and Anderson, Karen and Flashman, Laura A. and Seltzer, Marc and Hynes, Mary L. and Santulli, Robert B. and Sink, Kaycee M. and Gordineer, Leslie and Williamson, Jeff D. and Garg, Pradeep and Watkins, Franklin and Ott, Brian R. and Tremont, Geoffrey and Daiello, Lori A. and Salloway, Stephen and Malloy, Paul and Correia, Stephen and Rosen, Howard J. and Miller, Bruce L. and Perry, David and Mintzer, Jacobo and Spicer, Kenneth and Bachman, David and Pasternak, Stephen and Rachinsky, Irina and Rogers, John and Drost, Dick and Pomara, Nunzio and Hernando, Raymundo and Sarrael, Antero and Schultz, Susan K. and Smith, Karen Ekstam and Koleva, Hristina and Nam, Ki Won and Shim, Hyungsub and Relkin, Norman and Chiang, Gloria and Lin, Michael and Ravdin, Lisa and Smith, Amanda and Raj, Balebail Ashok and Fargher, Kristin},
doi = {10.1001/jamaneurol.2016.6117},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Mattsson et al. - 2017 - Association of plasma neurofilament light with neurodegeneration in patients with Alzheimer disease(2).pdf:pdf},
institution = {Alzheimer's Disease Neuroimaging Initiative},
isbn = {2168-6157$\backslash$r2168-6149},
issn = {21686149},
journal = {JAMA Neurol.},
keywords = {80 and over,Aged,Alzheimer Disease,Atrophy,Biomarkers,Case-Control Studies,Cognitive Dysfunction,Disease Progression,Female,Humans,Longitudinal Studies,Male,Middle Aged,Neurofilament Proteins,Registries,blood,diagnostic imaging,physiopathology},
language = {eng},
mendeley-groups = {PHD/Cardiovascular related,Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {may},
number = {5},
pages = {557--566},
pmid = {28346578},
title = {{Association of plasma neurofilament light with neurodegeneration in patients with Alzheimer disease}},
volume = {74},
year = {2017}
}
@article{Schneider2009,
abstract = {At the earliest clinical stages of Alzheimer's disease (AD), when first symptoms are mild, making a reliable and accurate diagnosis is difficult. AD related brain pathology and underlying molecular mechanisms precede symptoms. Biological markers can serve as supportive early screening and diagnostic tools as well as indicators of presymptomatic biochemical change. Moreover, biomarkers cover a variety of roles and functions such as disease prediction, indicating disease acuity and progression, and may ensure biological mapping of treatment outcome. Early screening, detection, and diagnosis of AD would permit earlier disease modifying intervention at potentially reversible stages. To date, most established biological markers from both cerebrospinal fluid neurochemistry and structural and functional neuroimaging have not reached widespread clinical application. Crucial remaining problems, such as easy acceptance and application of a test, cost-effectiveness, and noninvasiveness, need to be resolved. The development and validation of precise, reliable, and robust tests and biomarkers in blood, plasma, or serum has therefore been for a long time the ultimate focus of many research groups worldwide. Blood-based testing will most likely be the prerequisite to future sensitive screening of large populations at risk of AD and the baseline in a diagnostic flow approach to AD. The status and emerging perspectives on hypothesis and exploratory-based candidate biomarkers derived from blood, plasma, and serum are reviewed and discussed.},
annote = {From Duplicate 2 (Biological Marker Candidates of Alzheimer's Disease in Blood, Plasma, and Serum - Schneider, Philine; Hampel, Harald; Buerger, Katharina)

Could use some of the explanations here},
author = {Schneider, Philine and Hampel, Harald and Buerger, Katharina},
doi = {10.1111/j.1755-5949.2009.00104.x},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Schneider, Hampel, Buerger - 2009 - Biological Marker Candidates of Alzheimer's Disease in Blood, Plasma, and Serum(2).pdf:pdf},
isbn = {1755-5949 (Electronic)$\backslash$r1755-5930 (Linking)},
issn = {17555930},
journal = {CNS Neurosci. Ther.},
keywords = {APP isoforms,Alzheimers's disease,Amyloid beta,Antioxidants,Apolipoprotein E,A$\beta$ autoantibodies,A$\beta$40,A$\beta$42,BACE1,Biological marker,Blood,CT‐proET‐1,Cholesterol,Diagnosis,Early detection,Interleukin‐6,Isoprostanes,MR‐proADM,MR‐proANP,Oxysterols,Plasma,Prediction,Proteomics,Screening,Serum,a $\beta$ 40,a $\beta$ 42,a $\beta$ autoantibodies,alzheimers,amyloid beta,antioxidants,apolipoprotein e,app isoforms,bace1,disease,p‐tau,s,$\alpha$1‐Antichymotrypsin},
mendeley-groups = {PHD/Cardiovascular related,Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {dec},
number = {4},
pages = {358--374},
pmid = {19840034},
publisher = {Blackwell Publishing Ltd},
title = {{Biological Marker Candidates of Alzheimer's Disease in Blood, Plasma, and Serum}},
volume = {15},
year = {2009}
}
@article{Mapstone2014,
abstract = {Alzheimer's disease causes a progressive dementia that currently affects over 35  million individuals worldwide and is expected to affect 115 million by 2050 (ref. 1). There are no cures or disease-modifying therapies, and this may be due to our inability to detect the disease before it has progressed to produce evident memory loss and functional decline. Biomarkers of preclinical disease will be critical to the development of disease-modifying or even preventative therapies. Unfortunately, current biomarkers for early disease, including cerebrospinal fluid tau and amyloid-beta levels, structural and functional magnetic resonance imaging and the recent use of brain amyloid imaging or inflammaging, are limited because they are either invasive, time-consuming or expensive. Blood-based biomarkers may be a more attractive option, but none can currently detect preclinical Alzheimer's disease with the required sensitivity and specificity. Herein, we describe our lipidomic approach to detecting preclinical Alzheimer's disease in a group of cognitively normal older adults. We discovered and validated a set of ten lipids from peripheral blood that predicted phenoconversion to either amnestic mild cognitive impairment or Alzheimer's disease within a 2-3 year timeframe with over 90{\%} accuracy. This biomarker panel, reflecting cell membrane integrity, may be sensitive to early neurodegeneration of preclinical Alzheimer's disease.},
author = {Mapstone, Mark and Cheema, Amrita K and Fiandaca, Massimo S and Zhong, Xiaogang and Mhyre, Timothy R and MacArthur, Linda H and Hall, William J and Fisher, Susan G and Peterson, Derick R and Haley, James M and Nazar, Michael D and Rich, Steven A and Berlau, Dan J and Peltz, Carrie B and Tan, Ming T and Kawas, Claudia H and Federoff, Howard J},
doi = {10.1038/nm.3466},
issn = {1546-170X (Electronic)},
journal = {Nat. Med.},
keywords = {Aged,Alzheimer Disease,Asparagine,Biomarkers,Carnitine,Cognitive Dysfunction,Cohort Studies,Dipeptides,Female,Humans,Longitudinal Studies,Lysophosphatidylcholines,Malates,Male,Memory Disorders,Metabolome,Neuropsychological Tests,Phosphatidylcholines,Phosphatidylinositols,Phospholipids,Proline,Prospective Studies,Sensitivity and Specificity,Sphingomyelins,Ursodeoxycholic Acid,analogs {\&} derivatives,blood,complications,diagnosis,etiology},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {apr},
number = {4},
pages = {415--418},
pmid = {24608097},
title = {{Plasma phospholipids identify antecedent memory impairment in older adults.}},
volume = {20},
year = {2014}
}
@article{Ota2016,
abstract = {BACKGROUND: Prediction of progression to Alzheimer's disease (AD) in amnestic mild cognitive impairment (MCI) is challenging because of its heterogeneity. OBJECTIVE: To evaluate a stratification method on different cohorts and to investigate whether stratification in amnestic MCI could improve prediction accuracy. METHODS: We identified 80 and 79 patients with amnestic MCI from different cohorts, respectively. They underwent baseline magnetic resonance imaging (MRI) and 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) scans. We performed hierarchical clustering with three imaging biomarkers: Brain volume on MRI, left hippocampus grey matter loss on MRI, and left inferior temporal gyrus glucose hypometabolism on FDG-PET. Regions-of-interest for biomarkers were defined by the Automated Anatomical Labeling atlas. We performed voxel-wise statistical parametric mapping to explore differences between clusters in patterns of grey matter loss and glucose hypometabolism. We compared time to progression using an interval-censored parametric model. We evaluated predictive performance using logistic regression. RESULTS: Similar clusters were found in different cohorts. MCI1 had the healthiest biomarker profile of cognitive performance and imaging biomarkers. MCI2 had cognitive performance and MRI measures intermediate between those of nonconverters and converters. MCI3 showed the severest reduction in brain volume and left hippocampal atrophy. MCI4 showed remarkable glucose hypometabolism in the left inferior temporal gyrus, and also demonstrated significant decreases in most cognitive scores, including non-memory functions. MCI4 showed the highest risk for progression. The prediction of progression of MCI2 especially benefited from the stratification. CONCLUSION: Stratification with imaging biomarkers in amnestic MCI can be a good approach for improving predictive performance.},
author = {Ota, Kenichi and Oishi, Naoya and Ito, Kengo and Fukuyama, Hidenao},
doi = {10.3233/JAD-160145},
institution = {SEAD-J Study Group},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = {Aged,Alzheimer Disease,Biomarkers,Brain,Cognitive Dysfunction,Disease Progression,Female,Fluorodeoxyglucose F18,Glucose,Gray Matter,Hippocampus,Humans,Magnetic Resonance Imaging,Male,Neuroimaging,Positron-Emission Tomography,Temporal Lobe,classification,diagnosis,diagnostic imaging,metabolism},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {apr},
number = {4},
pages = {1385--1401},
pmid = {27079727},
title = {{Prediction of Alzheimer's Disease in Amnestic Mild Cognitive Impairment Subtypes: Stratification Based on Imaging Biomarkers.}},
volume = {52},
year = {2016}
}
@article{Clark2011,
abstract = {The ability to identify and quantify brain $\beta$-amyloid could increase the accuracy of a clinical diagnosis of Alzheimer disease.},
author = {Clark, Christopher M. and Schneider, Julie A. and Bedell, Barry J. and Beach, Thomas G. and Bilker, Warren B. and Mintun, Mark A. and Pontecorvo, Michael J. and Hefti, Franz and Carpenter, Alan P. and Flitter, Matthew L. and Krautkramer, Michael J. and Kung, Hank F. and Coleman, R. Edward and Doraiswamy, P. Murali and Fleisher, Adam S. and Sabbagh, Marwan N. and Sadowsky, Carl H. and Reiman, P. Eric M and Zehntner, Simone P. and Skovronsky, Daniel M.},
doi = {10.1001/jama.2010.2008},
isbn = {1538-3598 (Electronic)$\backslash$r0098-7484 (Linking)},
issn = {00987484},
journal = {JAMA - J. Am. Med. Assoc.},
keywords = {amyloid,autopsy,diagnostic imaging,florbetapir,pathology,positron-emission tomography},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/Review,PhDThesis/CIMLR},
month = {jan},
number = {3},
pages = {275--283},
pmid = {21245183},
publisher = {American Medical Association},
title = {{Use of florbetapir-PET for imaging $\beta$-amyloid pathology}},
volume = {305},
year = {2011}
}
@article{Yarchoan2013,
abstract = {C-reactive protein (CRP) participates in the systemic response to inflammation. Previous studies report inconsistent findings regarding the relationship between plasma CRP and Alzheimer's disease (AD). We measured plasma CRP in 203 subjects with AD, 58 subjects with mild cognitive impairment (MCI) and 117 normal aging subjects and administered annual Mini-Mental State Examinations (MMSE) during a 3-year follow-up period to investigate CRP's relationship with diagnosis and progression of cognitive decline. Adjusted for age, sex, and education, subjects with AD had significantly lower levels of plasma CRP than subjects with MCI and normal aging. However, there was no significant association between plasma CRP at baseline and subsequent cognitive decline as assessed by longitudinal changes in MMSE score. Our results support previous reports of reduced levels of plasma CRP in AD and indicate its potential utility as a biomarker for the diagnosis of AD.},
author = {Yarchoan, Mark and Louneva, Natalia and Xie, Sharon X and Swenson, Frank J and Hu, William and Soares, Holly and Trojanowski, John Q and Lee, Virginia M-Y and Kling, Mitchel A and Shaw, Leslie M and Chen-Plotkin, Alice and Wolk, David A and Arnold, Steven E},
doi = {10.1016/j.jns.2013.05.028},
issn = {1878-5883 (Electronic)},
journal = {J. Neurol. Sci.},
keywords = {Aged,Alzheimer Disease,Biomarkers,C-Reactive Protein,Case-Control Studies,Cognitive Dysfunction,Disease Progression,Female,Humans,Male,Neuropsychological Tests,Plasma,blood,diagnosis,metabolism,psychology},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {oct},
number = {1-2},
pages = {9--12},
pmid = {23978419},
title = {{Association of plasma C-reactive protein levels with the diagnosis of Alzheimer's disease.}},
volume = {333},
year = {2013}
}
@article{Thambisetty2012,
abstract = {Recent genetic and proteomic studies demonstrate that clusterin/apolipoprotein-J is associated with risk, pathology, and progression of Alzheimer's disease (AD). Our main aim was to examine associations between plasma clusterin concentration and longitudinal changes in brain volume in normal aging and mild cognitive impairment (MCI). A secondary objective was to examine associations between peripheral concentration of clusterin and its concentration in the brain within regions that undergo neuropathological changes in AD. Non-demented individuals (N = 139; mean baseline age 70.5 years) received annual volumetric MRI (912 MRI scans in total) over a mean six-year interval. Sixteen participants (92 MRI scans in total) were diagnosed during the course of the study with amnestic MCI. Clusterin concentration was assayed by ELISA in plasma samples collected within a year of the baseline MRI. Mixed effects regression models investigated whether plasma clusterin concentration was associated with rates of brain atrophy for control and MCI groups and whether these associations differed between groups. In a separate autopsy sample of individuals with AD (N = 17) and healthy controls (N = 4), we examined the association between antemortem clusterin concentration in plasma and postmortem levels in the superior temporal gyrus, hippocampus and cerebellum. The associations of plasma clusterin concentration with rates of change in brain volume were significantly different between MCI and control groups in several volumes including whole brain, ventricular CSF, temporal gray matter as well as parahippocampal, superior temporal and cingulate gyri. Within the MCI but not control group, higher baseline concentration of plasma clusterin was associated with slower rates of brain atrophy in these regions. In the combined autopsy sample of AD and control cases, representing a range of severity in AD pathology, we observed a significant association between clusterin concentration in the plasma and that in the superior temporal gyrus. Our findings suggest that clusterin, a plasma protein with roles in amyloid clearance, complement inhibition and apoptosis, is associated with rate of brain atrophy in MCI. Furthermore, peripheral concentration of clusterin also appears to reflect its concentration within brain regions vulnerable to AD pathology. These findings in combination suggest an influence of this multi-functional protein on early stages of progression in AD pathology. {\textcopyright} 2011.},
archivePrefix = {arXiv},
arxivId = {arXiv:1011.1669v3},
author = {Thambisetty, Madhav and An, Yang and Kinsey, Anna and Koka, Deepthi and Saleem, Muzamil and Guntert, Andreas and Kraut, Michael and Ferrucci, Luigi and Davatzikos, Christos and Lovestone, Simon and Resnick, Susan M.},
doi = {10.1016/j.neuroimage.2011.07.056},
eprint = {arXiv:1011.1669v3},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease (26),Atrophy,Biomarker,Clusterin,Mild cognitive impairment (MCI),Plasma},
mendeley-groups = {PhDThesis/CIMLR},
month = {jan},
number = {1},
pages = {212--217},
pmid = {21824521},
title = {{Plasma clusterin concentration is associated with longitudinal brain atrophy in mild cognitive impairment}},
volume = {59},
year = {2012}
}

@article{Obryant,
abstract = {The last decade has seen a substantial increase in research focused on the identification of blood-based biomarkers that have utility in Alzheimer's disease (AD). Blood-based biomarkers have significant advantages of being time- and cost-efficient as well as reduced invasiveness and increased patient acceptance. Despite these advantages and increased research efforts, the field has been hampered by lack of reproducibility and an unclear path for moving basic discovery toward clinical utilization. Here we reviewed the recent literature on blood-based biomarkers in AD to provide a current state of the art. In addition, a collaborative model is proposed that leverages academic and industry strengths to facilitate the field in moving past discovery only work and toward clinical use. Key resources are provided. This new public-private partnership model is intended to circumvent the traditional handoff model and provide a clear and useful paradigm for the advancement of biomarker science in AD and other neurodegenerative diseases.},
author = {O'Bryant, Sid E. and Mielke, Michelle M. and Rissman, Robert A. and Lista, Simone and Vanderstichele, Hugo and Zetterberg, Henrik and Lewczuk, Piotr and Posner, Holly and Hall, James and Johnson, Leigh and Fong, Yiu Lian and Luthman, Johan and Jeromin, Andreas and Batrla-Utermann, Richard and Villarreal, Alcibiades and Britton, Gabrielle and Snyder, Peter J. and Henriksen, Kim and Grammas, Paula and Gupta, Veer and Martins, Ralph and Hampel, Harald},
doi = {10.1016/j.jalz.2016.09.014},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/O'Bryant et al. - 2017 - Blood-based biomarkers in Alzheimer disease Current state of the science and a novel collaborative paradigm for.pdf:pdf},
isbn = {1552-5260},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {Alzheimer's disease,Biomarker,Blood,Cerebrospinal fluid,Context of use,Diagnosis,Imaging},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {1},
pages = {45--58},
pmid = {27870940},
title = {{Blood-based biomarkers in Alzheimer disease: Current state of the science and a novel collaborative paradigm for advancing from discovery to clinic}},
volume = {13},
year = {2017}
}
@article{Andreasen1999,
abstract = {We studied CSF-tau and CSF-A$\beta$42 in 16 patients with mild cognitive impairment (MCI) who at follow-up investigations 6-27 months later had progressed to Alzheimer's disease (AD) with dementia. For comparison, we studied 15 age-matched healthy individuals. At baseline, 14/16 (88$\%$) of MCI patients had high CSF-tau and/or low CSF-A$\beta$42 levels. These findings show that these CSF-markers are abnormal before the onset of clinical dementia and that they may help to identify MCI patients that will develop AD. This is especially important when drugs with potential effects on the progression of AD will reach the clinical phase. Copyright (C) 1999 Elsevier Science Ireland Ltd.},
author = {Andreasen, N. and Minthon, L. and Vanmechelen, E. and Vanderstichele, H. and Davidsson, P. and Winblad, B. and Blennow, K.},
doi = {10.1016/S0304-3940(99)00617-5},
issn = {03043940},
journal = {Neurosci. Lett.},
month = {sep},
number = {1},
pages = {5--8},
pmid = {10505638},
publisher = {Elsevier},
title = {{Cerebrospinal fluid tau and A$\beta$42 as predictors of development of Alzheimer's disease in patients with mild cognitive impairment}},
volume = {273},
year = {1999}
}
@article{Bradley-Whitman2015,
abstract = {Specific biomarkers in a readily accessible biological fluid, such as blood, could aid in the identification, characterization, validation, and routine monitoring of Alzheimer's disease (AD) progression. In the current study, levels of the previously described novel cerebrospinal fluid aberrant protein complex composed of prostaglandin-D-synthase (PDS) and transthyretin (TTR) were quantified in plasma by a custom two-probe sandwich ELISA and compared to amyloid-beta (Abeta)(1-42) as a standard plasma biomarker of AD. Plasma was analyzed from 140 probable AD subjects, 135 subjects with mild cognitive impairment (MCI), 74 normal control subjects (NC) prior to MCI transition, 23 diseased control (DC) subjects with either frontotemporal dementia or dementia with Lewy bodies, and 182 normal control (NC) subjects who did not progress to MCI or dementia. Levels of Abeta(1-42) were significantly elevated in NC subjects prior to MCI conversion but significantly reduced in probable AD subjects compared to NC subjects. Similarly, levels of the PDS-TTR complex were significantly reduced in both MCI and probable AD subjects compared to NC subjects. Furthermore, levels of Abeta(1-42) and the PDS-TTR complex were not significantly different in DC subjects compared to NC subjects. MMSE scores were weakly but significantly correlated with plasma levels of the PDS-TTR complex and Abeta(1-42). Trail B scores were weakly but significantly correlated with plasma levels of Abeta(1-42). Comparison of receiver operating curves shows the PDS-TTR complex is comparable to Abeta(1-42) in both MCI and probable AD subjects.},
author = {Bradley-Whitman, Melissa A and Abner, Erin and Lynn, Bert C and Lovell, Mark A},
doi = {10.3233/JAD-150183},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = {Aged,Aged, 80 and over,Alzheimer Disease,Amyloid beta-Peptides,Biomarkers,Blood Chemical Analysis,Cognitive Dysfunction,Disease Progression,Enzyme-Linked Immunosorbent Assay,Female,Humans,Intramolecular Oxidoreductases,Lipocalins,Longitudinal Studies,Male,Neuropsychological Tests,Peptide Fragments,Prealbumin,ROC Curve,blood,metabolism},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {3},
pages = {761--771},
pmid = {26401710},
title = {{A Novel Plasma Based Biomarker of Alzheimer's Disease.}},
volume = {47},
year = {2015}
}
@article{Samtani2013,
abstract = {AIM: The objective is to develop a semi-mechanistic disease progression model for mild cognitive impairment (MCI) subjects. The model aims to describe the longitudinal progression of ADAS-cog scores from the Alzheimer's disease neuroimaging initiative trial that had data from 198 MCI subjects with cerebrospinal fluid (CSF) information who were followed for 3 years. METHOD: Various covariates were tested on disease progression parameters and these variables fell into six categories: imaging volumetrics, biochemical, genetic, demographic, cognitive tests and CSF biomarkers. RESULTS: CSF biomarkers were associated with both baseline disease score and disease progression rate in subjects with MCI. Baseline disease score was also correlated with atrophy measured using hippocampal volume. Progression rate was also predicted by executive functioning as measured by the Trail B-test. CONCLUSION: CSF biomarkers have the ability to discriminate MCI subjects into sub-populations that exhibit markedly different rates of disease progression on the ADAS-cog scale. These biomarkers can therefore be utilized for designing clinical trials enriched with subjects that carry the underlying disease pathology.},
author = {Samtani, Mahesh N and Raghavan, Nandini and Shi, Yingqi and Novak, Gerald and Farnum, Michael and Lobanov, Victor and Schultz, Tim and Yang, Eric and DiBernardo, Allitia and Narayan, Vaibhav A},
doi = {10.1111/j.1365-2125.2012.04308.x},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1365-2125 (Electronic)},
journal = {Br. J. Clin. Pharmacol.},
keywords = {Aged,Aged, 80 and over,Alzheimer Disease,Apolipoproteins E,Biomarkers,Cholesterol,Cognitive Dysfunction,Disease Progression,Female,Humans,Male,Middle Aged,Neuroimaging,blood,cerebrospinal fluid,genetics},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
month = {jan},
number = {1},
pages = {146--161},
pmid = {22534009},
title = {{Disease progression model in subjects with mild cognitive impairment from the Alzheimer's disease neuroimaging initiative: CSF biomarkers predict population subtypes.}},
volume = {75},
year = {2013}
}
@article{Seshadri2002,
abstract = {Alzheimer's disease accounts for more than 70 percent of all cases of dementia, so it is important to identify modifiable risk factors for the disease.1 During the past decade, there has been growing interest in vascular factors that may underlie Alzheimer's disease. It is now recognized that subjects with cardiovascular risk factors and a history of stroke have an increased risk of both vascular dementia and Alzheimer's disease.2–4 Plasma total homocysteine has recently emerged as a major vascular risk factor. Elevated total homocysteine levels have been associated with an increased risk of atherosclerotic sequelae, including death from cardiovascular causes, . . .},
author = {Seshadri, Sudha and Beiser, Alexa and Selhub, Jacob and Jacques, Paul F. and Rosenberg, Irwin H. and D'Agostino, Ralph B. and Wilson, Peter W.F. and Wolf, Philip A.},
doi = {10.1056/NEJMoa011613},
isbn = {0028-4793},
issn = {0028-4793},
journal = {N. Engl. J. Med.},
mendeley-groups = {PHD/Cardiovascular related,PhDThesis/CIMLR},
month = {feb},
number = {7},
pages = {476--483},
pmid = {11844848},
publisher = {Massachusetts Medical Society},
title = {{Plasma Homocysteine as a Risk Factor for Dementia and Alzheimer's Disease}},
volume = {346},
year = {2002}
}
@article{Damian2013,
abstract = {BACKGROUND/AIMS: To identify prodromal Alzheimer's disease (AD) subjects using a  data-driven approach to determine cognitive profiles in mild cognitive impairment (MCI). METHODS: A total of 881 MCI subjects were recruited from 20 memory clinics and followed for up to 5 years. Outcome measures included cognitive variables, conversion to AD, and biomarkers (e.g. CSF, and MRI markers). Two hierarchical cluster analyses (HCA) were performed to identify clusters of subjects with distinct cognitive profiles. The first HCA included all subjects with complete cognitive data, whereas the second one selected subjects with very mild MCI (MMSE {\textgreater}/=28). ANOVAs and ANCOVAs were computed to examine whether the clusters differed with regard to conversion to AD, and to AD-specific biomarkers. RESULTS: The HCAs identified 4-cluster solutions that best reflected the sample structure. One cluster (aMCIsingle) had a significantly higher conversion rate (19{\%}), compared to subjective cognitive impairment (SCI, p {\textless} 0.0001), and non-amnestic MCI (naMCI, p = 0.012). This cluster was the only one showing a significantly different biomarker profile (Abeta42, t-tau, APOE epsilon4, and medial temporal atrophy), compared to SCI or naMCI. CONCLUSION: In subjects with mild MCI, the single-domain amnestic MCI profile was associated with the highest risk of conversion, even if memory impairment did not necessarily cross specific cut-off points. A cognitive profile characterized by isolated memory deficits may be sufficient to warrant applying prevention strategies in MCI, whether or not memory performance lies below specific z-scores. This is supported by our preliminary biomarker analyses. However, further analyses with bigger samples are needed to corroborate these findings.},
author = {Damian, Marinella and Hausner, Lucrezia and Jekel, Katrin and Richter, Melany and Froelich, Lutz and Almkvist, Ove and Boada, Merce and Bullock, Roger and {De Deyn}, Peter Paul and Frisoni, Giovanni B and Hampel, Harald and Jones, Roy W and Kehoe, Patrick and Lenoir, Hermine and Minthon, Lennart and {Olde Rikkert}, Marcel G M and Rodriguez, Guido and Scheltens, Philip and Soininen, Hilkka and Spiru, Luiza and Touchon, Jacques and Tsolaki, Magda and Vellas, Bruno and Verhey, Frans R J and Winblad, Bengt and Wahlund, Lars-Olof and Wilcock, Gordon and Visser, Pieter Jelle},
doi = {10.1159/000348354},
issn = {1421-9824 (Electronic)},
journal = {Dement. Geriatr. Cogn. Disord.},
keywords = {Aged,Aged, 80 and over,Alzheimer Disease,Apolipoproteins E,Biomarkers,Cluster Analysis,Cognitive Dysfunction,Cohort Studies,Disease Progression,Europe,Female,Genotype,Humans,Logistic Models,Magnetic Resonance Imaging,Male,Mental Recall,Middle Aged,Neuropsychological Tests,Reproducibility of Results,Tomography, X-Ray Computed,complications,epidemiology,genetics,physiology,psychology},
language = {eng},
mendeley-groups = {Papers bib/ad-simlr paper,PhDThesis/CIMLR},
number = {1-2},
pages = {1--19},
pmid = {23651945},
title = {{Single-domain amnestic mild cognitive impairment identified by cluster analysis predicts Alzheimer's disease in the european prospective DESCRIPA study.}},
volume = {36},
year = {2013}
}
@article{Jack2018,
abstract = {Abstract In 2011, the National Institute on Aging and Alzheimer's Association created separate diagnostic recommendations for the preclinical, mild cognitive impairment, and dementia stages of Alzheimer's disease. Scientific progress in the interim led to an initiative by the National Institute on Aging and Alzheimer's Association to update and unify the 2011 guidelines. This unifying update is labeled a "research framework" because its intended use is for observational and interventional research, not routine clinical care. In the National Institute on Aging and Alzheimer's Association Research Framework, Alzheimer's disease (AD) is defined by its underlying pathologic processes that can be documented by postmortem examination or in vivo by biomarkers. The diagnosis is not based on the clinical consequences of the disease (i.e., symptoms/signs) in this research framework, which shifts the definition of AD in living people from a syndromal to a biological construct. The research framework focuses on the diagnosis of AD with biomarkers in living persons. Biomarkers are grouped into those of $\beta$ amyloid deposition, pathologic tau, and neurodegeneration [AT(N)]. This ATN classification system groups different biomarkers (imaging and biofluids) by the pathologic process each measures. The AT(N) system is flexible in that new biomarkers can be added to the three existing AT(N) groups, and new biomarker groups beyond AT(N) can be added when they become available. We focus on AD as a continuum, and cognitive staging may be accomplished using continuous measures. However, we also outline two different categorical cognitive schemes for staging the severity of cognitive impairment: a scheme using three traditional syndromal categories and a six-stage numeric scheme. It is important to stress that this framework seeks to create a common language with which investigators can generate and test hypotheses about the interactions among different pathologic processes (denoted by biomarkers) and cognitive symptoms. We appreciate the concern that this biomarker-based research framework has the potential to be misused. Therefore, we emphasize, first, it is premature and inappropriate to use this research framework in general medical practice. Second, this research framework should not be used to restrict alternative approaches to hypothesis testing that do not use biomarkers. There will be situations where biomarkers are not available or requiring them would be counterproductive to the specific research goals (discussed in more detail later in the document). Thus, biomarker-based research should not be considered a template for all research into age-related cognitive impairment and dementia; rather, it should be applied when it is fit for the purpose of the specific research goals of a study. Importantly, this framework should be examined in diverse populations. Although it is possible that $\beta$-amyloid plaques and neurofibrillary tau deposits are not causal in AD pathogenesis, it is these abnormal protein deposits that define AD as a unique neurodegenerative disease among different disorders that can lead to dementia. We envision that defining AD as a biological construct will enable a more accurate characterization and understanding of the sequence of events that lead to cognitive impairment that is associated with AD, as well as the multifactorial etiology of dementia. This approach also will enable a more precise approach to interventional trials where specific pathways can be targeted in the disease process and in the appropriate people.},
annote = {The AT(N) classification can be used with different sets of biomarkers, as each A, T or N can be represented by several different markers.},
author = {Jack, Clifford R and Bennett, David A and Blennow, Kaj and Carrillo, Maria C and Dunn, Billy and Haeberlein, Samantha Budd and Holtzman, David M and Jagust, William and Jessen, Frank and Karlawish, Jason and Liu, Enchi and Molinuevo, Jose Luis and Montine, Thomas and Phelps, Creighton and Rankin, Katherine P and Rowe, Christopher C and Scheltens, Philip and Siemers, Eric and Snyder, Heather M and Sperling, Reisa and Elliott, Cerise and Masliah, Eliezer and Ryan, Laurie and Silverberg, Nina},
doi = {10.1016/j.jalz.2018.02.018},
issn = {15525260},
journal = {Alzheimer's Dement.},
keywords = {Alzheimer's disease diagnosis,Alzheimer's disease imaging,Amyloid PET,Biomarkers Alzheimer's disease,CSF biomarkers Alzheimer's disease,Preclinical Alzheimer's disease,Tau PET},
mendeley-groups = {PhDThesis/Review,PhDThesis/Hippo,PhDThesis/CIMLR},
number = {4},
pages = {535--562},
title = {{NIA-AA Research Framework: Toward a biological definition of Alzheimer's disease}},
volume = {14},
year = {2018}
}
@article{Jack2013,
abstract = {In 2010, we put forward a hypothetical model of the major biomarkers of Alzheimer's disease (AD). The model was received with interest because we described the temporal evolution of AD biomarkers in relation to each other and to the onset and progression of clinical symptoms. Since then, evidence has accumulated that supports the major assumptions of this model. Evidence has also appeared that challenges some of our assumptions, which has allowed us to modify our original model. Refinements to our model include indexing of individuals by time rather than clinical symptom severity; incorporation of interindividual variability in cognitive impairment associated with progression of AD pathophysiology; modifications of the specific temporal ordering of some biomarkers; and recognition that the two major proteinopathies underlying AD biomarker changes, amyloid $\beta$ (A$\beta$) and tau, might be initiated independently in sporadic AD, in which we hypothesise that an incident A$\beta$ pathophysiology can accelerate antecedent limbic and brainstem tauopathy.{\textcopyright}2013 Elsevier Ltd.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Jack, Clifford R and Knopman, David S and Jagust, William J and Petersen, Ronald C and Weiner, Michael W and Aisen, Paul S and Shaw, Leslie M and Vemuri, Prashanthi and Wiste, Heather J and Weigand, Stephen D and Lesnick, Timothy G and Pankratz, Vernon S and Donohue, Michael C and Trojanowski, John Q},
doi = {10.1016/S1474-4422(12)70291-0},
eprint = {NIHMS150003},
isbn = {1474-4422},
issn = {14744422},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis/Review,PhDThesis/CIMLR},
month = {feb},
number = {2},
pages = {207--216},
pmid = {23332364},
publisher = {Elsevier},
title = {{Tracking pathophysiological processes in Alzheimer's disease: An updated hypothetical model of dynamic biomarkers}},
volume = {12},
year = {2013}
}
@article{Rissman2012,
abstract = {Alzheimer's disease (AD) affects more than twenty-five million people worldwide and is the most common form of dementia. Symptomatic treatments have been developed, but effective intervention to alter disease progression is needed. Targets have been identified for disease-modifying drugs, but the results of clinical trials have been disappointing. Peripheral biomarkers of disease state may improve clinical trial design and analysis, increasing the likelihood of successful drug development. Amyloid-related measures, presumably reflecting principal pathology of AD, are among the leading cerebrospinal fluid and neuroimaging biomarkers, and measurement of plasma levels of amyloid peptides has been the focus of much investigation. In this review, we discuss recent data on plasma beta-amyloid (Abeta) and examine the issues that have arisen in establishing it as a reliable biomarker of AD.},
author = {Rissman, Robert A and Trojanowski, John Q and Shaw, Leslie M and Aisen, Paul S},
doi = {10.1007/s00702-012-0772-4},
issn = {1435-1463 (Electronic)},
journal = {J. Neural Transm.},
keywords = {Age Factors,Alzheimer Disease,Amyloid beta-Peptides,Biomarkers,Disease Progression,Humans,blood},
mendeley-groups = {PhDThesis/Review,PhDThesis/CIMLR},
month = {jul},
number = {7},
pages = {843--850},
pmid = {22354745},
title = {{Longitudinal plasma amyloid beta as a biomarker of Alzheimer's disease.}},
volume = {119},
year = {2012}
}
@article{Weiner2005,
author = {Albert, Marilyn and DeCarli, C and DeKosky, S and {De Leon}, M and Foster, Norman L and Fox, Nick and Frank, Richard and Frackowiak, Richard and Jack, Clifford and Jagust, William J},
journal = {Alzheimer's Assoc. Chicago},
mendeley-groups = {PhDThesis/Review,PhDThesis/CIMLR},
pages = {1--15},
title = {{The Use of MRI and PET for Clinical Diagnosis of Dementia and Investigation of Cognitive Impairment: A Consensus Report}},
year = {2004}
}
@article{Murray2011,
abstract = {Background: Neurofibrillary pathology has a stereotypical progression in Alzheimer's disease (AD) that is encapsulated in the Braak staging scheme; however, some AD cases are atypical and do not fit into this scheme. We aimed to compare clinical and neuropathological features between typical and atypical AD cases. Methods: AD cases with a Braak neurofibrillary tangle stage of more than IV were identified from a brain bank database. By use of thioflavin-S fluorescence microscopy, we assessed the density and the distribution of neurofibrillary tangles in three cortical regions and two hippocampal sectors. These data were used to construct an algorithm to classify AD cases into typical, hippocampal sparing, or limbic predominant. Classified cases were then compared for clinical, demographic, pathological, and genetic characteristics. An independent cohort of AD cases was assessed to validate findings from the initial cohort. Findings: 889 cases of AD, 398 men and 491 women with age at death of 37-103 years, were classified with the algorithm as hippocampal sparing (97 cases [11{\%}]), typical (665 [75{\%}]), or limbic predominant (127 [14{\%}]). By comparison with typical AD, neurofibrillary tangle counts per 0.125 mm2in hippocampal sparing cases were higher in cortical areas (median 13, IQR 11-16) and lower in the hippocampus (7.5, 5.2-9.5), whereas counts in limbic-predominant cases were lower in cortical areas (4.3, 3.0-5.7) and higher in the hippocampus (27, 22-35). Hippocampal sparing cases had less hippocampal atrophy than did typical and limbic-predominant cases. Patients with hippocampal sparing AD were younger at death (mean 72 years [SD 10]) and a higher proportion of them were men (61 [63{\%}]), whereas those with limbic-predominant AD were older (mean 86 years [SD 6]) and a higher proportion of them were women (87 [69{\%}]). Microtubule-associated protein tau (MAPT) H1H1 genotype was more common in limbic-predominant AD (54 [70{\%}]) than in hippocampal sparing AD (24 [46{\%}]; p=0.011), but did not differ significantly between limbic-predominant and typical AD (204 [59{\%}]; p=0.11). Apolipoprotein E (APOE) e{\{}open{\}}4 allele status differed between AD subtypes only when data were stratified by age at onset. Clinical presentation, age at onset, disease duration, and rate of cognitive decline differed between the AD subtypes. These findings were confirmed in a validation cohort of 113 patients with AD. Interpretation: These data support the hypothesis that AD has distinct clinicopathological subtypes. Hippocampal sparing and limbic-predominant AD subtypes might account for about 25{\%} of cases, and hence should be considered when designing clinical, genetic, biomarker, and treatment studies in patients with AD. Funding: US National Institutes of Health via Mayo Alzheimer's Disease Research Center, Mayo Clinic Study on Aging, Florida Alzheimer's Disease Research Center, and Einstein Aging Study; and State of Florida Alzheimer's Disease Initiative. {\textcopyright}2011 Elsevier Ltd.},
author = {Murray, Melissa E and Graff-Radford, Neill R and Ross, Owen A and Petersen, Ronald C and Duara, Ranjan and Dickson, Dennis W},
doi = {10.1016/S1474-4422(11)70156-9},
isbn = {1474-4465 (Electronic)$\backslash$r1474-4422 (Linking)},
issn = {14744422},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis/CIMLR},
number = {9},
pages = {785--796},
pmid = {21802369},
title = {{Neuropathologically defined subtypes of Alzheimer's disease with distinct clinical characteristics: A retrospective study}},
volume = {10},
year = {2011}
}
@article{Gupta2016,
abstract = {INTRODUCTION$\backslash$nFor early detection of Alzheimer's disease (AD), the field needs biomarkers that can be used to detect disease status with high sensitivity and specificity. Apolipoprotein J (ApoJ, also known as clusterin) has long been associated with AD pathogenesis through various pathways. The aim of this study was to investigate the potential of plasma apoJ as a blood biomarker for AD. $\backslash$n$\backslash$nMETHODS$\backslash$nUsing the Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging, the present study assayed plasma apoJ levels over baseline and 18 months in 833 individuals. Plasma ApoJ levels were analyzed with respect to clinical classification, age, gender, apolipoprotein E (APOE) $\epsilon$4 allele status, mini-mental state examination score, plasma amyloid beta (A$\beta$), neocortical A$\beta$ burden (as measured by Pittsburgh compound B-positron emission tomography), and total adjusted hippocampus volume. $\backslash$n$\backslash$nRESULTS$\backslash$nApoJ was significantly higher in both mild cognitive impairment (MCI) and AD groups as compared with healthy controls (HC; P {\textless}.0001). ApoJ significantly correlated with both “standardized uptake value ratio” (SUVR) and hippocampus volume and weakly correlated with the plasma A$\beta$1–42/A$\beta$1–40 ratio. Plasma apoJ predicted both MCI and AD from HC with greater than 80{\%} accuracy for AD and greater than 75{\%} accuracy for MCI at both baseline and 18-month time points. $\backslash$n$\backslash$nDISCUSSION$\backslash$nMean apoJ levels were significantly higher in both MCI and AD groups. ApoJ was able to differentiate between HC with high SUVR and HC with low SUVR via APOE $\epsilon$4 allele status, indicating that it may be included in a biomarker panel to identify AD before the onset of clinical symptoms.},
author = {Gupta, Veer Bala and Doecke, James D and Hone, Eugene and Pedrini, Steve and Laws, Simon M and Thambisetty, Madhav and Bush, Ashley I and Rowe, Christopher C and Villemagne, Victor L and Ames, David and Masters, Colin L and Macaulay, Stuart Lance and Rembach, Alan and Rainey-Smith, Stephanie R and Martins, Ralph N},
doi = {10.1016/j.dadm.2015.12.001},
isbn = {2352-8729 (Electronic)},
issn = {23528729},
journal = {Alzheimer's Dement. Diagnosis, Assess. Dis. Monit.},
keywords = {Apolipoprotein J,Biomarkers,Brain amyloid beta,Hippocampus volume,Plasma},
mendeley-groups = {PhDThesis/CIMLR},
pages = {18--26},
pmid = {27239546},
title = {{Plasma apolipoprotein J as a potential biomarker for Alzheimer's disease: Australian Imaging, Biomarkers and Lifestyle study of aging}},
volume = {3},
year = {2016}
}
@article{Ramazzotti2018,
abstract = {Outcomes for cancer patients vary greatly even within the same tumor type, and characterization of molecular subtypes of cancer holds important promise for improving prognosis and personalized treatment. This promise has motivated recent efforts to produce large amounts of multidimensional genomic ('multi-omic') data, but current algorithms still face challenges in the integrated analysis of such data. Here we present Cancer Integration via Multikernel Learning (CIMLR; based on an algorithm originally developed for analysis of single-cell RNA-Seq data), a new cancer subtyping method that integrates multi-omic data to reveal molecular subtypes of cancer. We apply CIMLR to multi-omic data from 32 cancer types and show significant improvements in both computational efficiency and ability to extract biologically meaningful cancer subtypes. The discovered subtypes exhibit significant differences in patient survival for 21 of the 32 studied cancer types. Our analysis reveals integrated patterns of gene expression, methylation, point mutations and copy number changes in multiple cancers and highlights patterns specifically associated with poor patient outcomes.},
author = {Ramazzotti, Daniele and Lal, Avantika and Wang, Bo and Batzoglou, Serafim and Sidow, Arend},
doi = {10.1101/267245},
journal = {bioRxiv},
mendeley-groups = {PhDThesis/CIMLR},
pages = {267245},
title = {{Multi-omic tumor data reveal diversity of molecular mechanisms underlying survival}},
year = {2018}
}
@article{Soares2012,
abstract = {BACKGROUND: A blood-based test that could be used as a screen for Alzheimer disease (AD) may enable early intervention and better access to treatment.$\backslash$n$\backslash$nOBJECTIVE: To apply a multiplex immunoassay panel to identify plasma biomarkers of AD using plasma samples from the Alzheimer's Disease Neuroimaging Initiative cohort.$\backslash$n$\backslash$nDESIGN: Cohort study.$\backslash$n$\backslash$nSETTING: The Biomarkers Consortium Alzheimer's Disease Plasma Proteomics Project.$\backslash$n$\backslash$nPARTICIPANTS: Plasma samples at baseline and at 1 year were analyzed from 396 (345 at 1 year) patients with mild cognitive impairment, 112 (97 at 1 year) patients with AD, and 58 (54 at 1 year) healthy control subjects.$\backslash$n$\backslash$nMAIN OUTCOME MEASURES: Multivariate and univariate statistical analyses were used to examine differences across diagnostic groups and relative to the apolipoprotein E (ApoE) genotype.$\backslash$n$\backslash$nRESULTS: Increased levels of eotaxin 3, pancreatic polypeptide, and N-terminal protein B-type brain natriuretic peptide were observed in patients, confirming similar changes reported in cerebrospinal fluid samples of patients with AD and MCI. Increases in tenascin C levels and decreases in IgM and ApoE levels were also observed. All participants with Apo $\epsilon$3/$\epsilon$4 or $\epsilon$4/$\epsilon$4 alleles showed a distinct biochemical profile characterized by low C-reactive protein and ApoE levels and by high cortisol, interleukin 13, apolipoprotein B, and gamma interferon levels. The use of plasma biomarkers improved specificity in differentiating patients with AD from controls, and ApoE plasma levels were lowest in patients whose mild cognitive impairment had progressed to dementia.$\backslash$n$\backslash$nCONCLUSIONS: Plasma biomarker results confirm cerebrospinal fluid studies reporting increased levels of pancreatic polypeptide and N-terminal protein B-type brain natriuretic peptide in patients with AD and mild cognitive impairment. Incorporation of plasma biomarkers yielded high sensitivity with improved specificity, supporting their usefulness as a screening tool. The ApoE genotype was associated with a unique biochemical profile irrespective of diagnosis, highlighting the importance of genotype on blood protein profiles.},
author = {Soares, Holly D and Potter, William Z and Pickering, Eve and Kuhn, Max and Immermann, Frederick W and Shera, David M and Ferm, Mats and Dean, Robert A and Simon, Adam J and Swenson, Frank and Siuciak, Judith A and Kaplow, June and Thambisetty, Madhav and Zagouras, Panayiotis and Koroshetz, Walter J and Wan, Hong I and Trojanowski, John Q and Shaw, Leslie M},
doi = {10.1001/archneurol.2012.1070},
isbn = {0003-9942},
issn = {00039942},
journal = {Arch. Neurol.},
mendeley-groups = {PhDThesis/CIMLR},
number = {10},
pages = {1310--1317},
pmid = {22801723},
publisher = {Eli Lilly},
title = {{Plasma biomarkers associated with the apolipoprotein E genotype and alzheimer disease}},
volume = {69},
year = {2012}
}
@misc{Henriksen2014,
abstract = {Treatment of Alzheimer's disease (AD) is significantly hampered by the lack of easily accessible biomarkers that can detect disease presence and predict disease risk reliably. Fluid biomarkers of AD currently provide indications of disease stage; however, they are not robust predictors of disease progression or treatment response, and most are measured in cerebrospinal fluid, which limits their applicability. With these aspects in mind, the aim of this article is to underscore the concerted efforts of the Blood-Based Biomarker Interest Group, an international working group of experts in the field. The points addressed include: (1) the major challenges in the development of blood-based biomarkers of AD, including patient heterogeneity, inclusion of the "right" control population, and the blood-brain barrier; (2) the need for a clear definition of the purpose of the individual markers (e.g., prognostic, diagnostic, or monitoring therapeutic efficacy); (3) a critical evaluation of the ongoing biomarker approaches; and (4) highlighting the need for standardization of preanalytical variables and analytical methodologies used by the field. {\textcopyright}2014 The Alzheimer's Association. All rights reserved.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Henriksen, Kim and O'Bryant, Sid E and Hampel, Harald and Trojanowski, John Q and Montine, Thomas J and Jeromin, Andreas and Blennow, Kaj and L{\"{o}}nneborg, Anders and Wyss-Coray, Tony and Soares, Holly and Bazenet, Chantal and Sj{\"{o}}gren, Magnus and Hu, William and Lovestone, Simon and Karsdal, Morten A and Weiner, Michael W},
booktitle = {Alzheimer's Dement.},
doi = {10.1016/j.jalz.2013.01.013},
eprint = {NIHMS150003},
isbn = {1552-5260 DO - http://dx.doi.org/10.1016/j.jalz.2013.01.013},
issn = {15525260},
keywords = {Alzheimer's disease,Biomarkers,Blood,Plasma,Serum},
mendeley-groups = {PhDThesis/CIMLR},
number = {1},
pages = {115--131},
pmid = {23850333},
title = {{The future of blood-based biomarkers for Alzheimer's disease}},
volume = {10},
year = {2014}
}
@article{Shaw2009,
abstract = {OBJECTIVE Develop a cerebrospinal fluid biomarker signature for mild Alzheimer's disease (AD) in Alzheimer's Disease Neuroimaging Initiative (ADNI) subjects. METHODS Amyloid-beta 1 to 42 peptide (A beta(1-42)), total tau (t-tau), and tau phosphorylated at the threonine 181 were measured in (1) cerebrospinal fluid (CSF) samples obtained during baseline evaluation of 100 mild AD, 196 mild cognitive impairment, and 114 elderly cognitively normal (NC) subjects in ADNI; and (2) independent 56 autopsy-confirmed AD cases and 52 age-matched elderly NCs using a multiplex immunoassay. Detection of an AD CSF profile for t-tau and A beta(1-42) in ADNI subjects was achieved using receiver operating characteristic cut points and logistic regression models derived from the autopsy-confirmed CSF data. RESULTS CSF A beta(1-42) was the most sensitive biomarker for AD in the autopsy cohort of CSF samples: receiver operating characteristic area under the curve of 0.913 and sensitivity for AD detection of 96.4{\%}. In the ADNI cohort, a logistic regression model for A beta(1-42), t-tau, and APO epsilon 4 allele count provided the best assessment delineation of mild AD. An AD-like baseline CSF profile for t-tau/A beta(1-42) was detected in 33 of 37 ADNI mild cognitive impairment subjects who converted to probable AD during the first year of the study. INTERPRETATION The CSF biomarker signature of AD defined by A beta(1-42) and t-tau in the autopsy-confirmed AD cohort and confirmed in the cohort followed in ADNI for 12 months detects mild AD in a large, multisite, prospective clinical investigation, and this signature appears to predict conversion from mild cognitive impairment to AD.},
archivePrefix = {arXiv},
arxivId = {PMCID: PMC2696350},
author = {Shaw, Leslie M and Vanderstichele, Hugo and Knapik-Czajka, Malgorzata and Clark, Christopher M and Aisen, Paul S and Petersen, Ronald C and Blennow, Kaj and Soares, Holly and Simon, Adam and Lewczuk, Piotr and Dean, Robert and Siemers, Eric and Potter, William and Lee, Virginia M Y and Trojanowski, John Q},
doi = {10.1002/ana.21610},
eprint = {PMCID: PMC2696350},
isbn = {1531-8249 (Electronic)},
issn = {03645134},
journal = {Ann. Neurol.},
mendeley-groups = {PhDThesis/CIMLR},
number = {4},
pages = {403--413},
pmid = {19296504},
title = {{Cerebrospinal fluid biomarker signature in alzheimer's disease neuroimaging initiative subjects}},
volume = {65},
year = {2009}
}
@article{Whitwell2012,
abstract = {Background: Three subtypes of Alzheimer's disease (AD) have been pathologically defined on the basis of the distribution of neurofibrillary tangles: typical AD, hippocampal-sparing AD, and limbic-predominant AD. Compared with typical AD, hippocampal-sparing AD has more neurofibrillary tangles in the cortex and fewer in the hippocampus, whereas the opposite pattern is seen in limbic-predominant AD. We aimed to determine whether MRI patterns of atrophy differ between these subtypes and whether structural neuroimaging could be a useful predictor of pathological subtype at autopsy. Methods: We identified patients who had been followed up in the Mayo Clinic Alzheimer's Disease Research Center (Rochester, MN, USA) or in the Alzheimer's Disease Patient Registry (Rochester, MN, USA) between 1992 and 2005. To be eligible for inclusion, participants had to have had dementia, AD pathology at autopsy (Braak stage ≥IV and intermediate to high probability of AD), and an ante-mortem MRI. Cases were assigned to one of three pathological subtypes-hippocampal-sparing, limbic-predominant, and typical AD-on the basis of neurofibrillary tangle counts in hippocampus and cortex and ratio of hippocampal to cortical burden, without reference to neuronal loss. Voxel-based morphometry and atlas-based parcellation were used to compare patterns of grey matter loss between groups and with age-matched control individuals. Neuroimaging was obtained at the time of first presentation. To summarise pair-wise group differences, we report the area under the receiver operator characteristic curve (AUROC). Findings: Of 177 eligible patients, 125 (71{\%}) were classified as having typical AD, 33 (19{\%}) as having limbic-predominant AD, and 19 (11{\%}) as having hippocampal-sparing AD. Most patients with typical (98 [78{\%}]) and limbic-predominant AD (31 [94{\%}]) initially presented with an amnestic syndrome, but fewer patients with hippocampal-sparing AD (eight [42{\%}]) did. The most severe medial temporal atrophy was recorded in patients with limbic-predominant AD, followed by those with typical disease, and then those with hippocampal-sparing AD. Conversely, the most severe cortical atrophy was noted in patients with hippocampal-sparing AD, followed by those with typical disease, and then limbic-predominant AD. The ratio of hippocampal to cortical volumes allowed the best discrimination between subtypes (p{\textless}0{\textperiodcentered}0001; three-way AUROC 0{\textperiodcentered}52 [95{\%} CI 0{\textperiodcentered}47-0{\textperiodcentered}52]; ratio of AUROC to chance classification 3{\textperiodcentered}1 [2{\textperiodcentered}8-3{\textperiodcentered}1]). Patients with typical AD and non-amnesic initial presentation had a significantly higher ratio of hippocampal to cortical volumes (median 0{\textperiodcentered}045 [IQR 0{\textperiodcentered}035-0{\textperiodcentered}056]) than did those with an amnesic presentation (0{\textperiodcentered}041 [0{\textperiodcentered}031-0{\textperiodcentered}057]; p=0{\textperiodcentered}001). Interpretation: Patterns of atrophy on MRI differ across the pathological subtypes of AD. MRI regional volumetric analysis can reliably track the distribution of neurofibrillary tangle pathology and can predict pathological subtype of AD at autopsy. Funding: US National Institutes of Health (National Institute on Aging). {\textcopyright}2012 Elsevier Ltd.},
author = {Whitwell, Jennifer L and Dickson, Dennis W and Murray, Melissa E and Weigand, Stephen D and Tosakulwong, Nirubol and Senjem, Matthew L and Knopman, David S and Boeve, Bradley F and Parisi, Joseph E and Petersen, Ronald C and Jack, Clifford R and Josephs, Keith A},
doi = {10.1016/S1474-4422(12)70200-4},
isbn = {1474-4465 (Electronic)$\backslash$r1474-4422 (Linking)},
issn = {14744422},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis/CIMLR},
number = {10},
pages = {868--877},
pmid = {22951070},
title = {{Neuroimaging correlates of pathologically defined subtypes of Alzheimer's disease: A case-control study}},
volume = {11},
year = {2012}
}
@article{Noh2014,
abstract = {OBJECTIVE: Because the signs associated with dementia due to Alzheimer disease (AD) can be heterogeneous, the goal of this study was to use 3-dimensional MRI to examine the various patterns of cortical atrophy that can be associated with dementia of AD type, and to investigate whether AD dementia can be categorized into anatomical subtypes.$\backslash$n$\backslash$nMETHODS: High-resolution T1-weighted volumetric MRIs were taken of 152 patients in their earlier stages of AD dementia. The images were processed to measure cortical thickness, and hierarchical agglomerative cluster analysis was performed using Ward's clustering linkage. The identified clusters of patients were compared with an age- and sex-matched control group using a general linear model.$\backslash$n$\backslash$nRESULTS: There were several distinct patterns of cortical atrophy and the number of patterns varied according to the level of cluster analyses. At the 3-cluster level, patients were divided into (1) bilateral medial temporal-dominant atrophy subtype (n = 52, ∼ 34.2{\%}), (2) parietal-dominant subtype (n = 28, ∼ 18.4{\%}) in which the bilateral parietal lobes, the precuneus, along with bilateral dorsolateral frontal lobes, were atrophic, and (3) diffuse atrophy subtype (n = 72, ∼ 47.4{\%}) in which nearly all association cortices revealed atrophy. These 3 subtypes also differed in their demographic and clinical features.$\backslash$n$\backslash$nCONCLUSIONS: This cluster analysis of cortical thickness of the entire brain showed that AD dementia in the earlier stages can be categorized into various anatomical subtypes, with distinct clinical features.},
author = {Noh, Young and Jeon, Seun and Lee, Jong Min and Seo, Sang Won and Kim, Geon Ha and Cho, Hanna and Ye, Byoung Seok and Yoon, Cindy W and Kim, Hee Jin and Chin, Juhee and Park, Kee Hyung and Heilman, Kenneth M and Na, Duk L},
doi = {10.1212/WNL.0000000000001003},
isbn = {0000000000},
issn = {1526632X},
journal = {Neurology},
mendeley-groups = {PhDThesis/CIMLR},
number = {21},
pages = {1936--1944},
pmid = {25344382},
title = {{Anatomical heterogeneity of Alzheimer disease Based on cortical thickness on MRIs}},
volume = {83},
year = {2014}
}
@article{Nettiksimmons2013,
abstract = {Previous work examining Alzheimer's Disease Neuroimaging Initiative (ADNI) normal controls using cluster analysis identified a subgroup characterized by substantial brain atrophy and white matter hyperintensities (WMH). We hypothesized that these effects could be related to vascular damage. Fifty-three individuals in the suspected vascular cluster (Normal 2) were compared with 31 individuals from the cluster characterized as healthy/typical (Normal 1) on a variety of outcomes, including magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) biomarkers, vascular risk factors and outcomes, cognitive trajectory, and medications for vascular conditions. Normal 2 was significantly older but did not differ on ApoE4+ prevalence. Normal 2 differed significantly from Normal 1 on all MRI measures but not on Amyloid-Beta1-42 or total tau protein. Normal 2 had significantly higher body mass index (BMI), Hachinksi score, and creatinine levels, and took significantly more medications for vascular conditions. Normal 2 had marginally significantly higher triglycerides and blood glucose. Normal 2 had a worse cognitive trajectory on the Rey's Auditory Verbal Learning Test (RAVLT) 30-min delay test and the Functional Activity Questionnaire (FAQ). Cerebral atrophy associated with multiple vascular risks is common among cognitively normal individuals, forming a distinct subgroup with significantly increased cognitive decline. Further studies are needed to determine the clinical impact of these findings.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Nettiksimmons, Jasmine and Beckett, Laurel and Schwarz, Christopher and Carmichael, Owen and Fletcher, Evan and DeCarli, Charles},
doi = {10.1037/a0031063},
eprint = {NIHMS150003},
isbn = {1939-1498 (Electronic)$\backslash$n0882-7974 (Linking)},
issn = {08827974},
journal = {Psychol. Aging},
keywords = {ADNI,Biomarkers,Cluster,Cognitive decline,Vascular},
mendeley-groups = {PhDThesis/CIMLR},
number = {1},
pages = {191--201},
pmid = {23527743},
title = {{Subgroup of ADNI normal controls characterized by atrophy and cognitive decline associated with vascular damage}},
volume = {28},
year = {2013}
}
@article{Nettiksimmons2014,
abstract = {BACKGROUND: Previous work examining normal controls from the Alzheimer's Disease Neuroimaging Initiative (ADNI) identified substantial biological heterogeneity. We hypothesized that ADNI mild cognitive impairment (MCI) subjects would also exhibit heterogeneity with possible clinical implications. METHODS: ADNI subjects diagnosed with amnestic MCI (n=138) were clustered based on baseline magnetic resonance imaging, cerebrospinal fluid, and serum biomarkers. The clusters were compared with respect to longitudinal atrophy, cognitive trajectory, and time to conversion. RESULTS: Four clusters emerged with distinct biomarker patterns: The first cluster was biologically similar to normal controls and rarely converted to Alzheimer's disease (AD) during follow-up. The second cluster had characteristics of early Alzheimer's pathology. The third cluster showed the most severe atrophy but barely abnormal tau levels and a substantial proportion converted to clinical AD. The fourth cluster appeared to be pre-AD and nearly all converted to AD. CONCLUSIONS: Subjects with MCI who were clinically similar showed substantial heterogeneity in biomarkers.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Nettiksimmons, Jasmine and DeCarli, Charles and Landau, Susan and Beckett, Laurel},
doi = {10.1016/j.jalz.2013.09.003},
eprint = {NIHMS150003},
isbn = {1552-5260 1552-5279 (electronic)},
issn = {15525279},
journal = {Alzheimers. Dement.},
keywords = {ADNI,Alzheimer's disease,Amnestic MCI,Clustering,Heterogeneity},
mendeley-groups = {PhDThesis/CIMLR},
number = {5},
pages = {511--521},
pmid = {24418061},
title = {{Biological heterogeneity in ADNI amnestic mild cognitive impairment}},
volume = {10},
year = {2014}
}
@article{ClarkCMBedellBJetal2011,
abstract = {ContextThe ability to identify and quantify brain $\beta$-amyloid could increase the accuracy of a clinical diagnosis of Alzheimer disease.ObjectiveTo determine if florbetapir F 18 positron emission tomographic (PET) imaging performed during life accurately predicts the presence of $\beta$-amyloid in the brain at autopsy.Design, Setting, and ParticipantsProspective clinical evaluation conducted February 2009 through March 2010 of florbetapir-PET imaging performed on 35 patients from hospice, long-term care, and community health care facilities near the end of their lives (6 patients to establish the protocol and 29 to validate) compared with immunohistochemistry and silver stain measures of brain $\beta$-amyloid after their death used as the reference standard. PET images were also obtained in 74 young individuals (18-50 years) presumed free of brain amyloid to better understand the frequency of a false-positive interpretation of a florbetapir-PET image.Main Outcome MeasuresCorrelation of florbetapir-PET image interpretation (based on the median of 3 nuclear medicine physicians' ratings) and semiautomated quantification of cortical retention with postmortem $\beta$-amyloid burden, neuritic amyloid plaque density, and neuropathological diagnosis of Alzheimer disease in the first 35 participants autopsied (out of 152 individuals enrolled in the PET pathological correlation study).ResultsFlorbetapir-PET imaging was performed a mean of 99 days (range, 1-377 days) before death for the 29 individuals in the primary analysis cohort. Fifteen of the 29 individuals (51.7{\%}) met pathological criteria for Alzheimer disease. Both visual interpretation of the florbetapir-PET images and mean quantitative estimates of cortical uptake were correlated with presence and quantity of $\beta$-amyloid pathology at autopsy as measured by immunohistochemistry (Bonferroni $\rho$, 0.78 [95{\%} confidence interval, 0.58-0.89]; P {\textless}.001]) and silver stain neuritic plaque score (Bonferroni $\rho$, 0.71 [95{\%} confidence interval, 0.47-0.86]; P {\textless}.001). Florbetapir-PET images and postmortem results rated as positive or negative for $\beta$-amyloid agreed in 96{\%} of the 29 individuals in the primary analysis cohort. The florbetapir-PET image was rated as amyloid negative in the 74 younger individuals in the nonautopsy cohort.ConclusionsFlorbetapir-PET imaging was correlated with the presence and density of $\beta$-amyloid. These data provide evidence that a molecular imaging procedure can identify $\beta$-amyloid pathology in the brains of individuals during life. Additional studies are required to understand the appropriate use of florbetapir-PET imaging in the clinical diagnosis of Alzheimer disease and for the prediction of progression to dementia.},
author = {{Clark CM Bedell BJ et al}, Schneider J A},
doi = {10.1001/jama.2010.2008},
journal = {Jama},
mendeley-groups = {PhDThesis/CIMLR},
number = {3},
pages = {275--283},
title = {{Use of florbetapir-pet for imaging $\beta$-amyloid pathology}},
volume = {305},
year = {2011}
}
@article{Whitwell2009,
abstract = {The behavioural variant of frontotemporal dementia is a progressive neurodegenerative syndrome characterized by changes in personality and behaviour. It is typically associated with frontal lobe atrophy, although patterns of atrophy are heterogeneous. The objective of this study was to examine case-by-case variability in patterns of grey matter atrophy in subjects with the behavioural variant of frontotemporal dementia and to investigate whether behavioural variant of frontotemporal dementia can be divided into distinct anatomical subtypes. Sixty-six subjects that fulfilled clinical criteria for a diagnosis of the behavioural variant of frontotemporal dementia with a volumetric magnetic resonance imaging scan were identified. Grey matter volumes were obtained for 26 regions of interest, covering frontal, temporal and parietal lobes, striatum, insula and supplemental motor area, using the automated anatomical labelling atlas. Regional volumes were divided by total grey matter volume. A hierarchical agglomerative cluster analysis using Ward's clustering linkage method was performed to cluster the behavioural variant of frontotemporal dementia subjects into different anatomical clusters. Voxel-based morphometry was used to assess patterns of grey matter loss in each identified cluster of subjects compared to an age and gender-matched control group at P {\textless}0.05 (family-wise error corrected). We identified four potentially useful clusters with distinct patterns of grey matter loss, which we posit represent anatomical subtypes of the behavioural variant of frontotemporal dementia. Two of these subtypes were associated with temporal lobe volume loss, with one subtype showing loss restricted to temporal lobe regions (temporal-dominant subtype) and the other showing grey matter loss in the temporal lobes as well as frontal and parietal lobes (temporofrontoparietal subtype). Another two subtypes were characterized by a large amount of frontal lobe volume loss, with one subtype showing grey matter loss in the frontal lobes as well as loss of the temporal lobes (frontotemporal subtype) and the other subtype showing loss relatively restricted to the frontal lobes (frontal-dominant subtype). These four subtypes differed on clinical measures of executive function, episodic memory and confrontation naming. There were also associations between the four subtypes and genetic or pathological diagnoses which were obtained in 48{\%} of the cohort. The clusters did not differ in behavioural severity as measured by the Neuropsychiatric Inventory; supporting the original classification of the behavioural variant of frontotemporal dementia in these subjects. Our findings suggest behavioural variant of frontotemporal dementia can therefore be subdivided into four different anatomical subtypes.},
author = {Whitwell, Jennifer L and Przybelski, Scott A and Weigand, Stephen D and Ivnik, Robert J and Vemuri, Prashanthi and Gunter, Jeffrey L and Senjem, Matthew L and Shiung, Maria M and Boeve, Bradley F and Knopman, David S and Parisi, Joseph E and Dickson, Dennis W and Petersen, Ronald C and Jack, Clifford R and Josephs, Keith A},
doi = {10.1093/brain/awp232},
isbn = {1460-2156 (Electronic)$\backslash$n0006-8950 (Linking)},
issn = {14602156},
journal = {Brain},
keywords = {Atrophy,Behavioural variant frontotemporal dementia,Cluster analysis,Voxel-based morphometry},
mendeley-groups = {PhDThesis/CIMLR},
number = {11},
pages = {2932--2946},
pmid = {19762452},
title = {{Distinct anatomical subtypes of the behavioural variant of frontotemporal dementia: A cluster analysis study}},
volume = {132},
year = {2009}
}
@article{Zelnik-Manor,
abstract = {We study a number of open issues in spectral clustering: (i) Selecting the appropriate scale of analysis, (ii) Handling multi-scale data, (iii) Clustering with irregular background clutter, and, (iv) Finding automatically the number of groups. We first propose that a ‘local ' scale should be used to compute the affinity between each pair of points. This local scaling leads to better clustering especially when the data includes multiple scales and when the clusters are placed within a cluttered background. We further suggest exploiting the structure of the eigenvectors to infer automatically the number of groups. This leads to a new algorithm in which the final randomly initialized k-means stage is eliminated. 1},
author = {Lihi and Zelnik-manor, Lihi and Perona, Pietro and Perona, Pietro},
doi = {10.1.1.84.7940},
isbn = {9780769535081},
issn = {10495258},
journal = {Adv. Neural Inf. Process. Syst. 17},
mendeley-groups = {PhDThesis/CIMLR},
pages = {1601--1608},
title = {{Self-tuning spectral clustering}},
volume = {2},
year = {2004}
}
@article{Wolz2011,
abstract = {Recent work suggests that the space of brain magnetic resonance (MR) images can be described by a nonlinear and low-dimensional manifold. In the context of classifying Alzheimer's disease (AD) patients from healthy controls, we propose a method to incorporate subject meta-information into the manifold learning step. Information such as gender, age or genotype is often available in clinical studies and can inform the classification of a given query subject. In the proposed method, such information, whether discrete or continuous, can be used as an additional input to manifold learning and to enrich a distance measure derived from pairwise image similarities. Building on previous work, the Laplacian eigenmap objective function is extended to include the additional information. We use the ApoE genotype, the CSF-concentration of A$\beta$42 and hippocampal volume as meta-information to achieve significantly improved classification results for subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.},
author = {Wolz, Robin and Aljabar, Paul and Hajnal, Joseph V and L{\"{o}}tj{\"{o}}nen, Jyrki and Rueckert, Daniel},
doi = {10.1109/ISBI.2011.5872717},
isbn = {9781424441280},
issn = {19457928},
journal = {Proc. - Int. Symp. Biomed. Imaging},
keywords = {Alzheimer's disease,classification,manifold learning,structural MR images},
mendeley-groups = {PhDThesis/CIMLR},
pages = {1637--1640},
title = {{Manifold learning combining imaging with non-imaging information}},
year = {2011}
}
@article{Thambisetty2011,
abstract = {Peripheral biomarkers of Alzheimer's disease (AD) reflecting early neuropathological change are critical to the development of treatments for this condition. The most widely used indicator of AD pathology in life at present is neuroimaging evidence of brain atrophy. We therefore performed a proteomic analysis of plasma to derive biomarkers associated with brain atrophy in AD. Using gel based proteomics we previously identified seven plasma proteins that were significantly associated with hippocampal volume in a combined cohort of subjects with AD (N = 27) and MCI (N = 17). In the current report, we validated this finding in a large independent cohort of AD (N = 79), MCI (N = 88) and control (N = 95) subjects using alternative complementary methods-quantitative immunoassays for protein concentrations and estimation of pathology by whole brain volume. We confirmed that plasma concentrations of five proteins, together with age and sex, explained more than 35{\%} of variance in whole brain volume in AD patients. These proteins are complement components C3 and C3a, complement factor-I, $\gamma$-fibrinogen and alpha-1-microglobulin. Our findings suggest that these plasma proteins are strong predictors of in vivo AD pathology. Moreover, these proteins are involved in complement activation and coagulation, providing further evidence for an intrinsic role of these pathways in AD pathogenesis.},
author = {Thambisetty, Madhav and Simmons, Andrew and Hye, Abdul and Campbell, James and Westman, Eric and Zhang, Yi and Wahlund, Lars Olof and Kinsey, Anna and Causevic, Mirsada and Killick, Richard and Kloszewska, Iwona and Mecocci, Patrizia and Soininen, Hilkka and Tsolaki, Magda and Vellas, Bruno and Spenger, Christian and Lovestone, Simon},
doi = {10.1371/journal.pone.0028527},
editor = {Breitner, John C S},
isbn = {1932-6203 (Electronic)$\backslash$r1932-6203 (Linking)},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/CIMLR},
number = {12},
pages = {e28527},
pmid = {22205954},
publisher = {Public Library of Science},
title = {{Plasma biomarkers of brain atrophy in Alzheimer's disease}},
volume = {6},
year = {2011}
}
@article{Lovheim2017,
abstract = {Introduction Biomarkers that identify individuals at risk of Alzheimer's disease (AD) development would be highly valuable. Plasma concentration of amyloid $\beta$ (A$\beta$)—central in the pathogenesis of AD—is a logical candidate, but studies to date have produced conflicting results on its utility. Methods Plasma samples from 339 preclinical AD cases (76.4{\%} women, mean age 61.3 years) and 339 age- and sex-matched dementia-free controls, taken an average of 9.4 years before AD diagnosis, were analyzed using Luminex xMAP technology and INNO-BIA plasma A$\beta$ form assays to determine concentrations of free plasma A$\beta$40and A$\beta$42. Results Plasma concentrations of free A$\beta$40and A$\beta$42did not differ between preclinical AD cases and dementia-free controls, in the full sample or in subgroups defined according to sex and age group ({\textless}60 and ≥ 60 years). The interval between sampling and AD diagnosis did not affect the results. A$\beta$ concentrations did not change in the years preceding AD diagnosis among individuals for whom longitudinal samples were available. Discussion Plasma concentrations of free A$\beta$ could not predict the development of clinical AD, and A$\beta$ concentrations did not change in the years preceding AD diagnosis in this sample. These results indicate that free plasma A$\beta$ is not a useful biomarker for the identification of individuals at risk of developing clinical AD.},
author = {L{\"{o}}vheim, Hugo and Elgh, Fredrik and Johansson, Anders and Zetterberg, Henrik and Blennow, Kaj and Hallmans, G{\"{o}}ran and Eriksson, Sture},
doi = {10.1016/j.jalz.2016.12.004},
isbn = {1552-5260},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {A$\beta$,Alzheimer's disease,Biomarker,Dementia,Plasma amyloid $\beta$,Preclinical Alzheimer's disease},
mendeley-groups = {PhDThesis/CIMLR},
number = {7},
pages = {778--782},
pmid = {27693182},
title = {{Plasma concentrations of free amyloid $\beta$ cannot predict the development of Alzheimer's disease}},
volume = {13},
year = {2017}
}
@inproceedings{Hogervorst2004,
abstract = {The purpose of this study was to assess pituitary gonadotropins and free testosterone levels in a larger cohort of men with Alzheimer's disease (AD, n=112) and age-matched controls (n=98) from the Oxford Project to Investigate Memory and Ageing (OPTIMA). We measured gonadotropins (follicle stimulating hormone, FSH, and luteinizing hormone, LH), sex hormone binding globulin (SHBG, which determines the amount of free testosterone) and total testosterone (TT) using enzyme immunoassays. AD cases had significantly higher LH and FSH and lower free testosterone levels. LH, FSH and SHBG all increased with age, while free testosterone decreased. Low free testosterone was an independent predictor for AD. Its variance was overall explained by high SHBG, low TT, high LH, an older age and low body mass index (BMI). In controls, low thyroid stimulating hormone levels were also associated with low free testosterone. Elderly AD cases had raised levels of gonadotropins. This response may be an attempt to normalize low free testosterone levels. In non-demented participants, subclinical hyperthyroid disease (a risk factor for AD) which can result in higher SHBG levels, was associated with low free testosterone. Lowering SHBG and/or screening for subclinical thyroid disease may prevent cognitive decline and/or wasting in men at risk for AD. {\textcopyright}2004 Elsevier Inc. All rights reserved.},
author = {Hogervorst, E and Bandelow, S and Combrinck, M and Smith, A D},
booktitle = {Exp. Gerontol.},
doi = {10.1016/j.exger.2004.06.019},
isbn = {0531-5565},
issn = {05315565},
keywords = {Alzheimer's disease,Dementia,FSH,Gonadotropins,LH,SHBG,Testosterone},
mendeley-groups = {PhDThesis/CIMLR},
month = {nov},
number = {11-12 SPEC. ISS.},
pages = {1633--1639},
pmid = {15582279},
publisher = {Pergamon},
title = {{Low free testosterone is an independent risk factor for Alzheimer's disease}},
volume = {39},
year = {2004}
}
@article{Meda2012,
abstract = {The underlying genetic etiology of late onset Alzheimer's disease (LOAD) remains largely unknown, likely due to its polygenic architecture and a lack of sophisticated analytic methods to evaluate complex genotype-phenotype models. The aim of the current study was to overcome these limitations in a bi-multivariate fashion by linking intermediate magnetic resonance imaging (MRI) phenotypes with a genome-wide sample of common single nucleotide polymorphism (SNP) variants. We compared associations between 94 different brain regions of interest derived from structural MRI scans and 533,872 genome-wide SNPs using a novel multivariate statistical procedure, parallel-independent component analysis, in a large, national multi-center subject cohort. The study included 209 elderly healthy controls, 367 subjects with amnestic mild cognitive impairment and 181 with mild, early-stage LOAD, all of them Caucasian adults, from the Alzheimer's Disease Neuroimaging Initiative cohort. Imaging was performed on comparable 1.5. T scanners at over 50 sites in the USA/Canada. Four primary "genetic components" were associated significantly with a single structural network including all regions involved neuropathologically in LOAD. Pathway analysis suggested that each component included several genes already known to contribute to LOAD risk (e.g. APOE4) or involved in pathologic processes contributing to the disorder, including inflammation, diabetes, obesity and cardiovascular disease. In addition significant novel genes identified included ZNF673, VPS13, SLC9A7, ATP5G2 and SHROOM2. Unlike conventional analyses, this multivariate approach identified distinct groups of genes that are plausibly linked in physiologic pathways, perhaps epistatically. Further, the study exemplifies the value of this novel approach to explore large-scale data sets involving high-dimensional gene and endophenotype data. {\textcopyright}2012 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Meda, Shashwath A and Narayanan, Balaji and Liu, Jingyu and Perrone-Bizzozero, Nora I and Stevens, Michael C and Calhoun, Vince D and Glahn, David C and Shen, Li and Risacher, Shannon L and Saykin, Andrew J and Pearlson, Godfrey D},
doi = {10.1016/j.neuroimage.2011.12.076},
eprint = {NIHMS150003},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Enrichment,Epistasis,Genotype-phenotype,ICA,Multivariate,Pathway},
mendeley-groups = {PhDThesis/CIMLR},
number = {3},
pages = {1608--1621},
pmid = {22245343},
title = {{A large scale multivariate parallel ICA method reveals novel imaging-genetic relationships for Alzheimer's disease in the ADNI cohort}},
volume = {60},
year = {2012}
}

@article{Adaszewski2013,
author = {Adaszewski, Stanis{\l}aw and Dukart, Juergen and Kherif, Ferath and Frackowiak, Richard and Draganski, Bogdan},
doi = {10.1016/j.neurobiolaging.2013.06.015},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Adaszewski et al. - 2013 - How early can we predict Alzheimer's disease using computational anatomy(2).pdf:pdf},
isbn = {1558-1497 (Electronic)$\backslash$r0197-4580 (Linking)},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Biomarker,Mild cognitive impairment,Structural magnetic resonance imaging},
mendeley-groups = {Review2,PhDThesis/Review},
month = {dec},
number = {12},
pages = {2815--2826},
pmid = {23890839},
publisher = {Elsevier},
title = {{How early can we predict Alzheimer's disease using computational anatomy?}},
volume = {34},
year = {2013}
}


@article{Fischl2012,
abstract = {FreeSurfer is a suite of tools for the analysis of neuroimaging data that provides an array of algorithms to quantify the functional, connectional and structural properties of the human brain. It has evolved from a package primarily aimed at generating surface representations of the cerebral cortex into one that automatically creates models of most macroscopically visible structures in the human brain given any reasonable T1-weighted input image. It is freely available, runs on a wide variety of hardware and software platforms, and is open source. {\textcopyright}2012 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Fischl, Bruce},
journal = {Neuroimage},
doi = {10.1016/j.neuroimage.2012.01.021},
eprint = {NIHMS150003},
isbn = {1053-8119},
issn = {10538119},
keywords = {MRI,Morphometry,Registration,Segmentation},
mendeley-groups = {PhDThesis/CIMLR},
number = {2},
pages = {774--781},
pmid = {22248573},
publisher = {NIH Public Access},
title = {{FreeSurfer}},
volume = {62},
year = {2012}
}

@techreport{DataPrimer,
author = {Consortium, ADNI Biomarkers},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/siuciakja - 2010 - Biomarkers Consortium Plasma Proteomics Data Primer 15Nov2010 FINAL.pdf:pdf},
mendeley-groups = {PhDThesis/CIMLR},
pages = {1--25},
title = {{Biomarkers Consortium Project Use of Targeted Multiplex Proteomic Strategies to Identify Plasma-Based Biomarkers in Alzheimer's Disease}},
year = {2010}
}


@article{VanDerMaaten2008,
abstract = {We present a new technique called " t-SNE " that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large data sets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of data sets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualiza-tions produced by t-SNE are significantly better than those produced by the other techniques on almost all of the data sets.},
author = {{Van Der Maaten}, Laurens and Hinton, Geoffrey},
journal = {J. Mach. Learn. Res.},
keywords = {dimensionality reduction,embedding algorithms,manifold learning,multidimensional scaling,visualization},
mendeley-groups = {PhDThesis/CIMLR},
pages = {2579--2605},
title = {{Visualizing Data using t-SNE}},
volume = {9},
year = {2008}
}

@article{He2005,
author = {He, Xiaofei and Cai, Deng and Niyogi, Partha},
isbn = {1049-5258},
issn = {10495258},
journal = {Adv. Neural Inf. Process. Syst. 18},
mendeley-groups = {PhDThesis/CIMLR},
pages = {507--514},
title = {{Laplacian Score for Feature Selection}},
year = {2005}
}

@article{Nogueira2020,
abstract = {Alternative stress echocardiography protocols such as handgrip exercise are potentially more favorable towards large-scale screening scenarios than those currently adopted in clinical practice. However, these are still underexplored because the maximal exercise levels are not easily quantified and regulated, requiring the analysis of the complete data sequences (thousands of images), which represents a challenging task for the clinician. We propose a framework for the analysis of these complex datasets, and illustrate it on a handgrip exercise dataset including complete acquisitions of 10 healthy controls and 5 ANT1 mutation patients (1377 cardiac cycles). The framework is based on an unsupervised formulation of multiple kernel learning, which is used to integrate information coming from myocardial velocity traces and heart rate to obtain a lower-dimensional representation of the data. Such simplified representation is then explored to discriminate groups of response and understand the underlying pathophysiological mechanisms. The analysis pipeline involves the reconstruction of population-specific signatures using multiscale kernel regression, and the clustering of subjects based on the trajectories defined by their projected sequences. The results confirm that the proposed framework is able to detect distinctive clusters of response and to provide insight regarding the underlying pathophysiology.},
author = {Nogueira, Mariana and {De Craene}, Mathieu and Sanchez-Martinez, Sergio and Chowdhury, Devyani and Bijnens, Bart and Piella, Gemma},
doi = {10.1016/j.media.2019.101594},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Nogueira et al. - 2020 - Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction.pdf:pdf},
issn = {13618423},
journal = {Med. Image Anal.},
keywords = {Multiple kernel learning,Multiview dimensionality reduction,Pattern analysis,Stress echocardiography},
mendeley-groups = {Papers bib/blood{\_}paper{\_}2,PhDThesis/CIMLR},
publisher = {Elsevier B.V.},
title = {{Analysis of nonstandardized stress echocardiography sequences using multiview dimensionality reduction}},
volume = {60},
year = {2020}
}

@article{Cuturi2011,
abstract = {We propose novel approaches to cast the widely-used family of Dynamic Time Warping (DTW) distances and similarities as positive definite kernels for time series. To this effect, we provide new theoretical insights on the family of Global Alignment kernels introduced by Cuturi et al. (2007) and propose alternative kernels which are both positive definite and faster to compute. We provide experimental evidence that these alternatives are both faster and more efficient in classification tasks than other kernels based on the DTW formalism. Copyright 2011 by the author(s)/owner(s).},
author = {Cuturi, Marco},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Cuturi - 2011 - Fast global alignment kernels.pdf:pdf},
isbn = {9781450306195},
journal = {Proc. 28th Int. Conf. Mach. Learn. ICML 2011},
keywords = {kernel methods, dynamic time warping, machine lear},
mendeley-groups = {PHD/CIMLR-extension,Papers bib/blood{\_}paper{\_}2},
pages = {929--936},
title = {{Fast global alignment kernels}},
year = {2011}
}
@article{Cuturi2017,
abstract = {We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically solves a minimal-cost alignment problem between two time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and gradient can be computed with quadratic time/space complexity (DTW has quadratic time but linear space complexity). We show that this regular-ization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines (Petitjean et al., 2011). Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense.},
archivePrefix = {arXiv},
arxivId = {arXiv:1703.01541v2},
author = {Cuturi, Marco and Blondel, Mathieu},
eprint = {arXiv:1703.01541v2},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Cuturi, Blondel - 2017 - Soft-DTW A differentiable loss function for time-series.pdf:pdf},
isbn = {9781510855144},
journal = {34th Int. Conf. Mach. Learn. ICML 2017},
mendeley-groups = {Papers bib/blood{\_}paper{\_}2},
pages = {1483--1505},
title = {{Soft-DTW: A differentiable loss function for time-series}},
volume = {2},
year = {2017}
}


@article{Lin2011,
abstract = {In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting data representations are typically high-dimensional and assume diverse forms. Hence, finding a way of transforming them into a unified space of lower dimension generally facilitates the underlying tasks such as object recognition or clustering. To this end, the proposed approach (termed MKL-DR) generalizes the framework of multiple kernel learning for dimensionality reduction, and distinguishes itself with the following three main contributions: First, our method provides the convenience of using diverse image descriptors to describe useful characteristics of various aspects about the underlying data. Second, it extends a broad set of existing dimensionality reduction techniques to consider multiple kernel learning, and consequently improves their effectiveness. Third, by focusing on the techniques pertaining to dimensionality reduction, the formulation introduces a new class of applications with the multiple kernel learning framework to address not only the supervised learning problems but also the unsupervised and semi-supervised ones. {\textcopyright} 2006 IEEE.},
author = {Lin, Yen Yu and Liu, Tyng Luh and Fuh, Chiou Shann},
doi = {10.1109/TPAMI.2010.183},
file = {:C$\backslash$:/Users/gerar/Desktop/2010101823544777830.pdf:pdf},
issn = {01628828},
journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
keywords = {Dimensionality reduction,face recognition,image clustering,multiple kernel learning,object categorization},
mendeley-groups = {Papers bib/blood{\_}paper{\_}2,PhDThesis/CIMLR},
number = {6},
pages = {1147--1160},
title = {{Multiple kernel learning for dimensionality reduction}},
volume = {33},
year = {2011}
}

@article{Bakkour2013,
abstract = {Although both normal aging and Alzheimer's disease (AD) are associated with regional cortical atrophy, few studies have directly compared the spatial patterns and magnitude of effects of these two processes. The extant literature has not addressed two important questions: 1) Is the pattern of age-related cortical atrophy different if cognitively intact elderly individuals with silent AD pathology are excluded? and 2) Does the age- or AD-related atrophy relate to cognitive function? Here we studied 142 young controls, 87 older controls, and 28 mild AD patients. In addition, we studied 35 older controls with neuroimaging data indicating the absence of brain amyloid. Whole-cortex analyses identified regions of interest (ROIs) of cortical atrophy in aging and in AD. Results showed that some regions are predominantly affected by age with relatively little additional atrophy in patients with AD, e.g., calcarine cortex; other regions are predominantly affected by AD with much less of an effect of age, e.g., medial temporal cortex. Finally, other regions are affected by both aging and AD, e.g., dorsolateral prefrontal cortex and inferior parietal lobule. Thus, the processes of aging and AD have both differential and partially overlapping effects on specific regions of the cerebral cortex. In particular, some frontoparietal regions are affected by both processes, most temporal lobe regions are affected much more prominently by AD than aging, while sensorimotor and some prefrontal regions are affected specifically by aging and minimally more by AD. Within normal older adults, atrophy in aging-specific cortical regions relates to cognitive performance, while in AD patients atrophy in AD-specific regions relates to cognitive performance. Further work is warranted to investigate the behavioral and clinical relevance of these findings in additional detail, as well as their histological basis; ROIs generated from the present study could be used strategically in such investigations. {\textcopyright} 2013 Elsevier Inc.},
author = {Bakkour, Akram and Morris, John C. and Wolk, David A. and Dickerson, Bradford C.},
doi = {10.1016/j.neuroimage.2013.02.059},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Bakkour et al. - 2013 - The effects of aging and Alzheimer's disease on cerebral cortical anatomy Specificity and differential relations.pdf:pdf},
issn = {10538119},
journal = {Neuroimage},
keywords = {Aging,Alzheimer' disease,Cerebral cortex,Frontal lobe,Magnetic resonance imaging,Parietal lobe,Temporal lobe},
mendeley-groups = {PhDThesis/VAE},
month = {aug},
pages = {332--344},
pmid = {23507382},
publisher = {NIH Public Access},
title = {{The effects of aging and Alzheimer's disease on cerebral cortical anatomy: Specificity and differential relationships with cognition}},
volume = {76},
year = {2013}
}


@article{Sanchez-Martinez2017,
abstract = {We propose an independent objective method to characterize different patterns of functional responses to stress in the heart failure with preserved ejection fraction (HFPEF) syndrome by combining multiple temporally-aligned myocardial velocity traces at rest and during exercise, together with temporal information on the occurrence of cardiac events (valves openings/closures and atrial activation). The method builds upon multiple kernel learning, a machine learning technique that allows the combination of data of different nature and the reduction of their dimensionality towards a meaningful representation (output space). The learning process is kept unsupervised, to study the variability of the input traces without being conditioned by data labels. To enhance the physiological interpretation of the output space, the variability that it encodes is analyzed in the space of input signals after reconstructing the velocity traces via multiscale kernel regression. The methodology was applied to 2D sequences from a stress echocardiography protocol from 55 subjects (22 healthy, 19 HFPEF and 14 breathless subjects). The results confirm that characterization of the myocardial functional response to stress in the HFPEF syndrome may be improved by the joint analysis of multiple relevant features.},
author = {Sanchez-Martinez, Sergio and Duchateau, Nicolas and Erdei, Tamas and Fraser, Alan G. and Bijnens, Bart H. and Piella, Gemma},
doi = {10.1016/j.media.2016.06.007},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sanchez-Martinez et al. - 2017 - Characterization of myocardial motion patterns by unsupervised multiple kernel learning.pdf:pdf},
issn = {13618423},
journal = {Med. Image Anal.},
keywords = {Echocardiography,Multiple kernel learning,Myocardial motion,Pattern analysis},
mendeley-groups = {Papers bib/hipppaper,Papers bib/blood{\_}paper{\_}2,PhDThesis/CIMLR},
month = {jan},
pages = {70--82},
publisher = {Elsevier},
title = {{Characterization of myocardial motion patterns by unsupervised multiple kernel learning}},
volume = {35},
year = {2017}
}


@article{Dage2016,
abstract = {Introduction Tau protein levels in plasma may be a marker of neuronal damage. We examined associations between plasma tau levels and Alzheimer's disease (AD)–related magnetic resonance imaging (MRI) and positron emission tomography (PET) neuroimaging measures among nondemented individuals. Methods Participants included 378 cognitively normal (CN) and 161 mild cognitive impairment (MCI) individuals enrolled in the Mayo Clinic Study of Aging with concurrent neuropsychological measures and amyloid PET, fluorodeoxyglucose PET, and MRI. Baseline plasma tau levels were measured using the Quanterix Simoa-HD1 tau assay. Results Plasma tau levels were higher in MCI compared with CN (4.34 vs. 4.14 pg/mL, P = .078). In regression models adjusted for age, gender, education, and APOE, higher plasma tau was associated with worse memory performance (b = −0.30, P = .02) and abnormal cortical thickness in an AD signature region (odds ratio = 1.80, P = .018). Discussion Plasma tau is associated with cortical thickness and memory performance. Longitudinal studies will better elucidate the associations between plasma tau, neurodegeneration, and cognition.},
author = {Dage, Jeffrey L and Wennberg, Alexandra M V and Airey, David C and Hagen, Clinton E and Knopman, David S and Machulda, Mary M and Roberts, Rosebud O and Jack, Clifford R and Petersen, Ronald C and Mielke, Michelle M},
doi = {10.1016/j.jalz.2016.06.001},
isbn = {1552-5260},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {Amyloid,Cognition,Cortical thickness,MCI,MRI,Memory,Plasma tau},
mendeley-groups = {PhDThesis/CIMLR},
number = {12},
pages = {1226--1234},
pmid = {27436677},
title = {{Levels of tau protein in plasma are associated with neurodegeneration and cognitive function in a population-based elderly cohort}},
volume = {12},
year = {2016}
}
@article{Fischl2002,
abstract = {We present a technique for automatically assigning a neuroanatomical label to each voxel in an MRI volume based on probabilistic information automatically estimated from a manually labeled training set. In contrast to existing segmentation procedures that only label a small number of tissue classes, the current method assigns one of 37 labels to each voxel, including left and right caudate, putamen, pallidum, thalamus, lateral ventricles, hippocampus, and amygdala. The classification technique employs a registration procedure that is robust to anatomical variability, including the ventricular enlargement typically associated with neurological diseases and aging. The technique is shown to be comparable in accuracy to manual labeling, and of sufficient sensitivity to robustly detect changes in the volume of noncortical structures that presage the onset of probable Alzheimer's disease.},
author = {Fischl, Bruce and Salat, David H and Busa, Evelina and Albert, Marilyn and Dieterich, Megan and Haselgrove, Christian and van der Kouwe, Andre and Killiany, Ron and Kennedy, David and Klaveness, Shuna and Montillo, Albert and Makris, Nikos and Rosen, Bruce and Dale, Anders M},
doi = {10.1016/S0896-6273(02)00569-X},
isbn = {0896-6273 (Print)},
issn = {08966273},
journal = {Neuron},
mendeley-groups = {PhDThesis/CIMLR},
number = {3},
pages = {341--355},
pmid = {11832223},
title = {{Whole Brain Segmentation: Neurotechnique Automated Labeling of NeuroanatomicalStructures in the Human Brain}},
volume = {33},
year = {2002}
}
@article{Nakamura2018,
abstract = {Alzheimer's disease is characterized by the deposition of amyloid-$\beta$ (A$\beta$) peptide in the brain. The only available methods to reliably determine the levels of A$\beta$ deposition are A$\beta$-PET imaging or measurement of A$\beta$ levels in the cerebrospinal fluid. Therefore, identifying a blood-based biomarker that can be assessed in a minimally invasive and cost-effective manner is highly desirable. Katsuhiko Yanagisawa and colleagues use immunoprecipitation and mass spectrometry to measure the levels of several A$\beta$-related peptide fragments in blood. The APP669–711/A$\beta$1–42 and A$\beta$1–40/A$\beta$1–42 ratios and a composite score reliably predict individual levels of A$\beta$ deposition in the brain. These results highlight the potential clinical utility of plasma biomarkers in predicting brain A$\beta$ burden at an individual level.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Nakamura, Akinori and Kaneko, Naoki and Villemagne, Victor L and Kato, Takashi and Doecke, James and Dor{\'{e}}, Vincent and Fowler, Chris and Li, Qiao Xin and Martins, Ralph and Rowe, Christopher and Tomita, Taisuke and Matsuzaki, Katsumi and Ishii, Kenji and Ishii, Kazunari and Arahata, Yutaka and Iwamoto, Shinichi and Ito, Kengo and Tanaka, Koichi and Masters, Colin L and Yanagisawa, Katsuhiko},
doi = {10.1038/nature25456},
eprint = {NIHMS150003},
isbn = {0028-0836},
issn = {14764687},
journal = {Nature},
mendeley-groups = {PhDThesis/CIMLR},
number = {7691},
pages = {249--254},
pmid = {29420472},
title = {{High performance plasma amyloid-$\beta$ biomarkers for Alzheimer's disease}},
volume = {554},
year = {2018}
}
@article{Ovod2017,
abstract = {Introduction Cerebrospinal fluid analysis and other measurements of amyloidosis, such as amyloid-binding positron emission tomography studies, are limited by cost and availability. There is a need for a more practical amyloid $\beta$ (A$\beta$) biomarker for central nervous system amyloid deposition. Methods We adapted our previously reported stable isotope labeling kinetics protocol to analyze the turnover kinetics and concentrations of A$\beta$38, A$\beta$40, and A$\beta$42 in human plasma. Results A$\beta$ isoforms have a half-life of approximately 3 hours in plasma. A$\beta$38 demonstrated faster turnover kinetics compared with A$\beta$40 and A$\beta$42. Faster fractional turnover of A$\beta$42 relative to A$\beta$40 and lower A$\beta$42 and A$\beta$42/A$\beta$40 concentrations in amyloid-positive participants were observed. Discussion Blood plasma A$\beta$42 shows similar amyloid-associated alterations as we have previously reported in cerebrospinal fluid, suggesting a blood-brain transportation mechanism of A$\beta$. The stability and sensitivity of plasma A$\beta$ measurements suggest this may be a useful screening test for central nervous system amyloidosis.},
author = {Ovod, Vitaliy and Ramsey, Kara N and Mawuenyega, Kwasi G and Bollinger, Jim G and Hicks, Terry and Schneider, Theresa and Sullivan, Melissa and Paumier, Katrina and Holtzman, David M and Morris, John C and Benzinger, Tammie and Fagan, Anne M and Patterson, Bruce W and Bateman, Randall J},
doi = {10.1016/j.jalz.2017.06.2266},
isbn = {1552-5260},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {A$\beta$42,Amyloid $\beta$,Human,Kinetics,Plasma,Turnover},
mendeley-groups = {PhDThesis/CIMLR},
number = {8},
pages = {841--849},
pmid = {28734653},
title = {{Amyloid $\beta$ concentrations and stable isotope labeling kinetics of human plasma specific to central nervous system amyloidosis}},
volume = {13},
year = {2017}
}
@article{Wang2017a,
abstract = {Single-cell RNA-seq technologies enable high throughput gene expression measurement of individual cells, and allow the discovery of heterogeneity within cell populations. Measurement of cell-to-cell gene expression similarity is critical to identification, visualization and analysis of cell populations. However, single-cell data introduce challenges to conventional measures of gene expression similarity because of the high level of noise, outliers and dropouts. Here, we propose a novel similarity-learning framework, SIMLR (single-cell interpretation via multi-kernel learning), which learns an appropriate distance metric from the data for dimension reduction, clustering and visualization. We show that SIMLR separates subpopulations more accurately in single-cell data sets than do existing dimension reduction methods. Additionally, SIMLR demonstrates high sensitivity and accuracy on high-throughput peripheral blood mononuclear cells (PBMC) data sets generated by the GemCode single-cell technology from 10x Genomics.},
author = {Wang, Bo and Zhu, Junjie and Pierson, Emma and Ramazzotti, Daniele and Batzoglou, Serafim},
doi = {10.1038/nMeth.4207},
isbn = {1548-7105},
issn = {15487105},
journal = {Nat. Methods},
keywords = {Gene expression,Genome informatics,Machine learning,Statistical methods},
mendeley-groups = {PhDThesis/CIMLR},
number = {4},
pages = {414--416},
pmid = {28263960},
publisher = {Nature Publishing Group},
title = {{Visualization and analysis of single-cell rna-seq data by kernel-based similarity learning}},
volume = {14},
year = {2017}
}
@article{Cortes1995,
abstract = {In this paper, the optimal margin algorithm is generalized to non-separable problems by the introduction of slack variables in the statement of the optimization problem.},
archivePrefix = {arXiv},
arxivId = {arXiv:1011.1669v3},
author = {{C. Cortes} and {V. Vapnik}},
doi = {10.1007/BF00994018},
eprint = {arXiv:1011.1669v3},
isbn = {0885-6125},
issn = {08856125},
journal = {Mach. Learn.},
mendeley-groups = {PhDThesis/CIMLR},
number = {3},
pages = {273--297},
pmid = {19549084},
publisher = {Kluwer Academic Publishers},
title = {{Support Vector Networks}},
volume = {20},
year = {1995}
}
@article{Weiner2017,
abstract = {Introduction The Alzheimer's Disease Neuroimaging Initiative (ADNI) has continued development and standardization of methodologies for biomarkers and has provided an increased depth and breadth of data available to qualified researchers. This review summarizes the over 400 publications using ADNI data during 2014 and 2015. Methods We used standard searches to find publications using ADNI data. Results (1) Structural and functional changes, including subtle changes to hippocampal shape and texture, atrophy in areas outside of hippocampus, and disruption to functional networks, are detectable in presymptomatic subjects before hippocampal atrophy; (2) In subjects with abnormal $\beta$-amyloid deposition (A$\beta$+), biomarkers become abnormal in the order predicted by the amyloid cascade hypothesis; (3) Cognitive decline is more closely linked to tau than A$\beta$ deposition; (4) Cerebrovascular risk factors may interact with A$\beta$ to increase white-matter (WM) abnormalities which may accelerate Alzheimer's disease (AD) progression in conjunction with tau abnormalities; (5) Different patterns of atrophy are associated with impairment of memory and executive function and may underlie psychiatric symptoms; (6) Structural, functional, and metabolic network connectivities are disrupted as AD progresses. Models of prion-like spreading of A$\beta$ pathology along WM tracts predict known patterns of cortical A$\beta$ deposition and declines in glucose metabolism; (7) New AD risk and protective gene loci have been identified using biologically informed approaches; (8) Cognitively normal and mild cognitive impairment (MCI) subjects are heterogeneous and include groups typified not only by “classic” AD pathology but also by normal biomarkers, accelerated decline, and suspected non-Alzheimer's pathology; (9) Selection of subjects at risk of imminent decline on the basis of one or more pathologies improves the power of clinical trials; (10) Sensitivity of cognitive outcome measures to early changes in cognition has been improved and surrogate outcome measures using longitudinal structural magnetic resonance imaging may further reduce clinical trial cost and duration; (11) Advances in machine learning techniques such as neural networks have improved diagnostic and prognostic accuracy especially in challenges involving MCI subjects; and (12) Network connectivity measures and genetic variants show promise in multimodal classification and some classifiers using single modalities are rivaling multimodal classifiers. Discussion Taken together, these studies fundamentally deepen our understanding of AD progression and its underlying genetic basis, which in turn informs and improves clinical trial design.},
annote = {From Duplicate 2 (Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials - Weiner, Michael W.; Veitch, Dallas P.; Aisen, Paul S.; Beckett, Laurel A.; Cairns, Nigel J.; Green, Robert C.; Harvey, Danielle; Jack, Clifford R.; Jagust, William; Morris, John C.; Petersen, Ronald C.; Saykin, Andrew J.; Shaw, Leslie M.; Toga, Arthur W.; Trojanowski, John Q.)

From Duplicate 2 (Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials - Weiner, Michael W; Veitch, Dallas P; Aisen, Paul S; Beckett, Laurel A; Cairns, Nigel J; Green, Robert C; Harvey, Danielle; Jack, Clifford R; Jagust, William; Morris, John C; Petersen, Ronald C; Saykin, Andrew J; Shaw, Leslie M; Toga, Arthur W; Trojanowski, John Q)

To extract even more papers},
author = {Weiner, Michael W and Veitch, Dallas P and Aisen, Paul S and Beckett, Laurel A and Cairns, Nigel J and Green, Robert C and Harvey, Danielle and Jack, Clifford R and Jagust, William and Morris, John C and Petersen, Ronald C and Saykin, Andrew J and Shaw, Leslie M and Toga, Arthur W and Trojanowski, John Q},
doi = {10.1016/j.jalz.2016.11.007},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {Alzheimer's disease,Amyloid,Biomarker,Disease progression,Mild cognitive impairment,Tau},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {e1----e85},
pmid = {28342697},
title = {{Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials}},
volume = {13},
year = {2017}
}
@article{Wolz2010,
annote = {- Extract biomarkers from manifold where longitudinal image information is included. SVM.

-ADNI Dataset.

- Classification between NC,MCI and AD.

- Features are the described imaged biomarkers.

- Results in various types of manifolds, and 72{\%} AD-MCI, 68{\%} pMCI-sMCI.},
author = {Wolz, Robin and Aljabar, Paul and Hajnal, J V V and Rueckert, Daniel},
doi = {10.1007/978-3-642-15948-0_15},
journal = {Mach. Learn. Med. Imaging},
mendeley-groups = {PhDThesis/Review},
pages = {116--123},
publisher = {Springer Berlin Heidelberg},
title = {{Manifold learning for biomarker discovery in MR imaging}},
volume = {6357},
year = {2010}
}
@article{Wyman2013,
abstract = {The Alzheimer's Disease Neuroimaging Initiative (ADNI) three-dimensional T1-weighted magnetic resonance imaging (MRI) acquisitions provide a rich data set for developing and testing analysis techniques for extracting structural endpoints. To promote greater rigor in analysis and meaningful comparison of different algorithms, the ADNI MRI Core has created standardized analysis sets of data comprising scans that met minimum quality control requirements. We encourage researchers to test and report their techniques against these data. Standard analysis sets of volumetric scans from ADNI-1 have been created, comprising screening visits, 1-year completers (subjects who all have screening, 6- and 12-month scans), 2-year annual completers (screening, 1-year and 2-year scans), 2-year completers (screening, 6-months, 1-year, 18-months [mild cognitive impaired (MCI) only], and 2-year scans), and complete visits (screening, 6-month, 1-year, 18-month [MCI only], 2-year, and 3-year [normal and MCI only] scans). As the ADNI-GO/ADNI-2 data become available, updated standard analysis sets will be posted regularly. {\textcopyright}2013 The Alzheimer's Association. All rights reserved.},
annote = {From Duplicate 1 (Standardization of analysis sets for reporting results from ADNI MRI data - Wyman, Bradley T; Harvey, Danielle J; Crawford, Karen; Bernstein, Matt A; Carmichael, Owen; Cole, Patricia E; Crane, Paul K; Decarli, Charles; Fox, Nick C; Gunter, Jeffrey L; Hill, Derek; Killiany, Ronald J; Pachai, Chahin; Schwarz, Adam J; Schuff, Norbert; Senjem, Matthew L; Suhy, Joyce; Thompson, Paul M; Weiner, Michael; Jack, Clifford R)

Explanation of the standarized datasets of ADNI. Very useful. Should use it for all my tests.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Wyman, Bradley T and Harvey, Danielle J and Crawford, Karen and Bernstein, Matt A and Carmichael, Owen and Cole, Patricia E and Crane, Paul K and Decarli, Charles and Fox, Nick C and Gunter, Jeffrey L and Hill, Derek and Killiany, Ronald J and Pachai, Chahin and Schwarz, Adam J and Schuff, Norbert and Senjem, Matthew L and Suhy, Joyce and Thompson, Paul M and Weiner, Michael and Jack, Clifford R},
doi = {10.1016/j.jalz.2012.06.004},
eprint = {NIHMS150003},
isbn = {8604418032},
issn = {15525260},
journal = {Alzheimer's Dement.},
keywords = {ADNI,Alzheimer's disease,Analysis standards,Biomarkers,Magnetic resonance imaging},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {332--337},
pmid = {23110865},
title = {{Standardization of analysis sets for reporting results from ADNI MRI data}},
volume = {9},
year = {2013}
}
@article{Xu2014,
abstract = {Most existing genome-wide association analyses are cross-sectional, utilizing only phenotypic data at a single time point, e.g. baseline. On the other hand, longitudinal studies, such as Alzheimer's Disease Neuroimaging Initiative (ADNI), collect phenotypic information at multiple time points. In this article, as a case study, we conducted both longitudinal and cross-sectional analyses of the ADNI data with several brain imaging (not clinical diagnosis) phenotypes, demonstrating the power gains of longitudinal analysis over cross-sectional analysis. Specifically, we scanned genome-wide single nucleotide polymorphisms (SNPs) with 56 brain-wide imaging phenotypes processed by FreeSurfer on 638 subjects. At the genome-wide significance level P {\textless}1.8 x 10(9)) or a less stringent level (e.g. P {\textless}10(7)), longitudinal analysis of the phenotypic data from the baseline to month 48 identified more SNP-phenotype associations than cross-sectional analysis of only the baseline data. In particular, at the genome-wide significance level, both SNP rs429358 in gene APOE and SNP rs2075650 in gene TOMM40 were confirmed to be associated with various imaging phenotypes in multiple regions of interests (ROIs) by both analyses, though longitudinal analysis detected more regional phenotypes associated with the two SNPs and indicated another significant SNP rs439401 in gene APOE. In light of the power advantage of longitudinal analysis, we advocate its use in current and future longitudinal neuroimaging studies.},
author = {Xu, Zhiyuan and Shen, Xiaotong and Pan, Wei},
doi = {10.1371/journal.pone.0102312},
isbn = {1932-6203 (Electronic) 1932-6203 (Linking)},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Review},
number = {8},
pmid = {25098835},
title = {{Longitudinal analysis is more powerful than cross-sectional analysis in detecting genetic association with neuroimaging phenotypes}},
volume = {9},
year = {2014}
}
@article{Yang2011,
abstract = {Hypothetical models of AD progression typically relate clinical stages of AD to sequential changes in CSF biomarkers, imaging, and cognition. However, quantifying the continuous trajectories proposed by these models over time is difficult because of the difficulty in relating the dynamics of different biomarkers during a clinical trial that is significantly shorter than the duration of the disease. We seek to show that through proper synchronization, it is possible to de-convolve these trends and quantify the periods of time associated with different pathophysiological changes associated with Alzheimer's disease (AD). We developed a model that replicated the observed progression of ADAS-Cog 13 scores and used this as a more precise estimate of disease-duration and thus pathologic stage. We then synchronized cerebrospinal fluid (CSF) and imaging biomarkers according to our new disease timeline. By de-convolving disease progression via ADAS-Cog 13, we were able to confirm the predictions of previous hypothetical models of disease progression as well as establish concrete timelines for different pathobiological events. Specifically, our work supports a sequential pattern of biomarker changes in AD in which reduction in CSF A$\beta$(42) and brain atrophy precede the increases in CSF tau and phospho-tau.},
author = {Yang, Eric and Farnum, Michael and Lobanov, Victor and Schultz, Tim and Raghavan, Nandini and Samtani, Mahesh N and Novak, Gerald and Narayan, Vaibhav and Dibernardo, Allitia},
doi = {10.3233/JAD-2011-110551},
isbn = {1875-8908},
issn = {13872877},
journal = {J. Alzheimer's Dis.},
keywords = {clinical trials,disease timeline,progression modeling,synchronization},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {745--753},
pmid = {21694449},
title = {{Quantifying the pathophysiological timeline of Alzheimer's disease}},
volume = {26},
year = {2011}
}
@article{Yang2018,
abstract = {BACKGROUND: Brain functional connectivity network (BFCN) has been widely applied to identify biomarkers for the brain function understanding and brain diseases analysis. OBJECTIVE: Building a biologically meaningful brain network is a crucial work in these applications. For this task, sparse learning has been widely applied for the network construction. If multiple time-point data is added to the brain imaging application, the disease progression pattern in the longitudinal analysis can be better revealed. METHODS: A novel longitudinal analysis for MCI classification is devised based on resting-state functional magnetic resonating imaging (rs-fMRI). Specifically, this paper proposes a novel multi-task learning method to integrate fused penalty by regularization. In addition, a novel objective function is developed for fused sparse learning via smoothness constraint. RESULTS: The proposed method achieves the best classification performance with an accuracy of 95.74{\%} for baseline and 93.64{\%} for year 1 data. CONCLUSIONS: The experimental results show that our proposed method achieves quite promising classification performance.},
author = {Yang, Peng and Ni, Dong and Chen, Siping and Wang, Tianfu and Wu, Donghui and Lei, Baiying},
doi = {10.3233/THC-174587},
issn = {1878-7401 (Electronic)},
journal = {Technol. Heal. Care},
keywords = { Computer-Assisted, Factual,Algorithms,Biomarkers,Brain,Cognitive Dysfunction,Computer-Assisted,Databases,Disease Progression,Factual,Humans,Image Processing,Magnetic Resonance Imaging,Support Vector Machine,diagnosis,diagnostic imaging,methods,physiopathology},
mendeley-groups = {PhDThesis/Review},
number = {S1},
pages = {437--448},
pmid = {29710750},
title = {{Multi-task fused sparse learning for mild cognitive impairment identification.}},
volume = {26},
year = {2018}
}
@article{Yau2015,
abstract = {BACKGROUND: The biomarker model of Alzheimer's disease postulates a dynamic sequence of amyloidosis, neurodegeneration, and cognitive decline as an individual progresses from preclinical Alzheimer's disease to dementia. Despite supportive evidence from cross-sectional studies, verification with long-term within-individual data is needed. METHODS: For this prospective cohort study, carriers of autosomal dominant Alzheimer's disease mutations (aged {\textgreater}/=21 years) were recruited from across the USA through referrals by physicians or from affected families. People with mutations in PSEN1, PSEN2, or APP were assessed at the University of Pittsburgh Alzheimer's Disease Research Center every 1-2 years, between March 23, 2003, and Aug 1, 2014. We measured global cerebral amyloid beta (Abeta) load using (11)C-Pittsburgh Compound-B PET, posterior cortical metabolism with (18)F-fluorodeoxyglucose PET, hippocampal volume (age and sex corrected) with T1-weighted MRI, verbal memory with the ten-item Consortium to Establish a Registry for Alzheimer's Disease Word List Learning Delayed Recall Test, and general cognition with the Mini Mental State Examination. We estimated overall biomarker trajectories across estimated years from symptom onset using linear mixed models, and compared these estimates with cross-sectional data from cognitively normal control individuals (age 65-89 years) who were negative for amyloidosis, hypometabolism, and hippocampal atrophy. In the mutation carriers who had the longest follow-up, we examined the within-individual progression of amyloidosis, metabolism, hippocampal volume, and cognition to identify progressive within-individual changes (a significant change was defined as an increase or decrease of more than two Z scores standardised to controls). FINDINGS: 16 people with mutations in PSEN1, PSEN2, or APP, aged 28-56 years, completed between two and eight assessments (a total of 83 assessments) over 2-11 years. Significant differences in mutation carriers compared with controls (p{\textless}0.01) were detected in the following order: increased amyloidosis (7.5 years before expected onset), decreased metabolism (at time of expected onset), decreased hippocampal volume and verbal memory (7.5 years after expected onset), and decreased general cognition (10 years after expected onset). Among the seven participants with longest follow-up (seven or eight assessments spanning 6-11 years), three individuals had active amyloidosis without progressive neurodegeneration or cognitive decline, two amyloid-positive individuals showed progressive neurodegeneration and cognitive decline without further progressive amyloidosis, and two amyloid-positive individuals showed neither active amyloidosis nor progressive neurodegeneration or cognitive decline. INTERPRETATION: Our results support amyloidosis as the earliest component of the biomarker model in autosomal dominant Alzheimer's disease. Our within-individual examination suggests three sequential phases in the development of autosomal dominant Alzheimer's disease-active amyloidosis, a stable amyloid-positive period, and progressive neurodegeneration and cognitive decline-indicating that Abeta accumulation is largely complete before progressive neurodegeneration and cognitive decline occur. These findings offer supportive evidence for efforts to target early Abeta deposition for secondary prevention in individuals with autosomal dominant Alzheimer's disease. FUNDING: National Institutes of Health and Howard Hughes Medical Institute.},
author = {Yau, Wai-Ying Wendy and Tudorascu, Dana L and McDade, Eric M and Ikonomovic, Snezana and James, Jeffrey A and Minhas, Davneet and Mowrey, Wenzhu and Sheu, Lei K and Snitz, Beth E and Weissfeld, Lisa and Gianaros, Peter J and Aizenstein, Howard J and Price, Julie C and Mathis, Chester A and Lopez, Oscar L and Klunk, William E},
doi = {10.1016/S1474-4422(15)00135-0},
issn = {1474-4465 (Electronic)},
journal = {Lancet. Neurol.},
keywords = { 80 and over,Adult,Aged,Alzheimer Disease,Amyloid beta-Peptides,Amyloidosis,Aniline Compounds,Biomarkers,Cerebral Cortex,Disease Progression,Female,Hippocampus,Humans,Male,Middle Aged,Prospective Studies,Thiazoles,genetics,metabolism,pathology,physiopathology},
mendeley-groups = {PhDThesis/Review},
number = {8},
pages = {804--813},
pmid = {26139022},
title = {{Longitudinal assessment of neuroimaging and clinical markers in autosomal dominant Alzheimer's disease: a prospective cohort study.}},
volume = {14},
year = {2015}
}

@article{Karikari2020,
abstract = {Background: CSF and PET biomarkers of amyloid $\beta$ and tau accurately detect Alzheimer's disease pathology, but the invasiveness, high cost, and poor availability of these detection methods restrict their widespread use as clinical diagnostic tools. CSF tau phosphorylated at threonine 181 (p-tau181) is a highly specific biomarker for Alzheimer's disease pathology. We aimed to assess whether blood p-tau181 could be used as a biomarker for Alzheimer's disease and for prediction of cognitive decline and hippocampal atrophy. Methods: We developed and validated an ultrasensitive blood immunoassay for p-tau181. Assay performance was evaluated in four clinic-based prospective cohorts. The discovery cohort comprised patients with Alzheimer's disease and age-matched controls. Two validation cohorts (TRIAD and BioFINDER-2) included cognitively unimpaired older adults (mean age 63–69 years), participants with mild cognitive impairment (MCI), Alzheimer's disease, and frontotemporal dementia. In addition, TRIAD included healthy young adults (mean age 23 years) and BioFINDER-2 included patients with other neurodegenerative disorders. The primary care cohort, which recruited participants in Montreal, Canada, comprised control participants from the community without a diagnosis of a neurological condition and patients referred from primary care physicians of the Canadian National Health Service for specialist care. Concentrations of plasma p-tau181 were compared with established CSF and PET biomarkers and longitudinal measurements using Spearman correlation, area under the curve (AUC), and linear regression analyses. Findings: We studied 37 individuals in the discovery cohort, 226 in the first validation cohort (TRIAD), 763 in the second validation cohort (BioFINDER-2), and 105 in the primary care cohort (n=1131 individuals). In all cohorts, plasma p-tau181 showed gradual increases along the Alzheimer's disease continuum, from the lowest concentrations in amyloid $\beta$-negative young adults and cognitively unimpaired older adults, through higher concentrations in the amyloid $\beta$-positive cognitively unimpaired older adults and MCI groups, to the highest concentrations in the amyloid $\beta$-positive MCI and Alzheimer's disease groups (p{\textless}0{\textperiodcentered}001, Alzheimer's disease vs all other groups). Plasma p-tau181 distinguished Alzheimer's disease dementia from amyloid $\beta$-negative young adults (AUC=99{\textperiodcentered}40{\%}) and cognitively unimpaired older adults (AUC=90{\textperiodcentered}21–98{\textperiodcentered}24{\%} across cohorts), as well as other neurodegenerative disorders, including frontotemporal dementia (AUC=82{\textperiodcentered}76–100{\%} across cohorts), vascular dementia (AUC=92{\textperiodcentered}13{\%}), progressive supranuclear palsy or corticobasal syndrome (AUC=88{\textperiodcentered}47{\%}), and Parkinson's disease or multiple systems atrophy (AUC=81{\textperiodcentered}90{\%}). Plasma p-tau181 was associated with PET-measured cerebral tau (AUC=83{\textperiodcentered}08–93{\textperiodcentered}11{\%} across cohorts) and amyloid $\beta$ (AUC=76{\textperiodcentered}14–88{\textperiodcentered}09{\%} across cohorts) pathologies, and 1-year cognitive decline (p=0{\textperiodcentered}0015) and hippocampal atrophy (p=0{\textperiodcentered}015). In the primary care cohort, plasma p-tau181 discriminated Alzheimer's disease from young adults (AUC=100{\%}) and cognitively unimpaired older adults (AUC=84{\textperiodcentered}44{\%}), but not from MCI (AUC=55{\textperiodcentered}00{\%}). Interpretation: Blood p-tau181 can predict tau and amyloid $\beta$ pathologies, differentiate Alzheimer's disease from other neurodegenerative disorders, and identify Alzheimer's disease across the clinical continuum. Blood p-tau181 could be used as a simple, accessible, and scalable test for screening and diagnosis of Alzheimer's disease. Funding: Alzheimer Drug Discovery Foundation, European Research Council, Swedish Research Council, Swedish Alzheimer Foundation, Swedish Dementia Foundation, Alzheimer Society Research Program.},
author = {Karikari, Thomas K. and Pascoal, Tharick A. and Ashton, Nicholas J. and Janelidze, Shorena and Benedet, Andr{\'{e}}a Lessa and Rodriguez, Juan Lantero and Chamoun, Mira and Savard, Melissa and Kang, Min Su and Therriault, Joseph and Sch{\"{o}}ll, Michael and Massarweh, Gassan and Soucy, Jean Paul and H{\"{o}}glund, Kina and Brinkmalm, Gunnar and Mattsson, Niklas and Palmqvist, Sebastian and Gauthier, Serge and Stomrud, Erik and Zetterberg, Henrik and Hansson, Oskar and Rosa-Neto, Pedro and Blennow, Kaj},
doi = {10.1016/S1474-4422(20)30071-5},
issn = {14744465},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis/CIMLR},
month = {may},
number = {5},
pages = {422--433},
pmid = {32333900},
publisher = {Lancet Publishing Group},
title = {{Blood phosphorylated tau 181 as a biomarker for Alzheimer's disease: a diagnostic performance and prediction modelling study using data from four prospective cohorts}},
volume = {19},
year = {2020}
}


@article{Young2017,
abstract = {The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique-Subtype and Stage Inference (SuStaIn)-able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer's disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p = 7.18 × 10 −4) or temporal stage (p = 3.96 × 10 −5). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine.},
author = {Young, Alexandra L. and Marinescu, Razvan V. and Oxtoby, Neil P. and Bocchetta, Martina and Yong, Keir and Firth, Nicholas C. and Cash, David M. and Thomas, David L. and Dick, Katrina M. and Cardoso, Jorge and van Swieten, John and Borroni, Barbara and Galimberti, Daniela and Masellis, Mario and Tartaglia, Maria Carmela and Rowe, James B. and Graff, Caroline and Tagliavini, Fabrizio and Frisoni, Giovanni B. and Laforce, Robert and Finger, Elizabeth and de Mendon{\c{c}}a, Alexandre and Sorbi, Sandro and Warren, Jason D. and Crutch, Sebastian and Fox, Nick C. and Ourselin, Sebastien and Schott, Jonathan M. and Rohrer, Jonathan D. and Alexander, Daniel C. and Andersson, Christin and Archetti, Silvana and Arighi, Andrea and Benussi, Luisa and Binetti, Giuliano and Black, Sandra and Cosseddu, Maura and Fallstr{\"{o}}m, Marie and Ferreira, Carlos and Fenoglio, Chiara and Freedman, Morris and Fumagalli, Giorgio G. and Gazzina, Stefano and Ghidoni, Roberta and Grisoli, Marina and Jelic, Vesna and Jiskoot, Lize and Keren, Ron and Lombardi, Gemma and Maruta, Carolina and Meeter, Lieke and Mead, Simon and van Minkelen, Rick and Nacmias, Benedetta and {\"{O}}ijerstedt, Linn and Padovani, Alessandro and Panman, Jessica and Pievani, Michela and Polito, Cristina and Premi, Enrico and Prioni, Sara and Rademakers, Rosa and Redaelli, Veronica and Rogaeva, Ekaterina and Rossi, Giacomina and Rossor, Martin and Scarpini, Elio and Tang-Wai, David and Thonberg, Hakan and Tiraboschi, Pietro and Verdelho, Ana and Weiner, Michael W. and Aisen, Paul and Petersen, Ronald and Jack, Clifford R. and Jagust, William and Trojanowki, John Q. and Toga, Arthur W. and Beckett, Laurel and Green, Robert C. and Saykin, Andrew J. and Morris, John and Shaw, Leslie M. and Khachaturian, Zaven and Sorensen, Greg and Kuller, Lew and Raichle, Marc and Paul, Steven and Davies, Peter and Fillit, Howard and Hefti, Franz and Holtzman, Davie and Mesulam, M. Marcel and Potter, William and Snyder, Peter and Schwartz, Adam and Montine, Tom and Thomas, Ronald G. and Donohue, Michael and Walter, Sarah and Gessert, Devon and Sather, Tamie and Jiminez, Gus and Harvey, Danielle and Bernstein, Matthew and Thompson, Paul and Schuff, Norbert and Borowski, Bret and Gunter, Jeff and Senjem, Matt and Vemuri, Prashanthi and Jones, David and Kantarci, Kejal and Ward, Chad and Koeppe, Robert A. and Foster, Norm and Reiman, Eric M. and Chen, Kewei and Mathis, Chet and Landau, Susan and Cairns, Nigel J. and Householder, Erin and Taylor-Reinwald, Lisa and Lee, Virginia and Korecka, Magdalena and Figurski, Michal and Crawford, Karen and Neu, Scott and Foroud, Tatiana M. and Potkin, Steven and Shen, Li and Faber, Kelley and Kim, Sungeun and Nho, Kwangsik and Thal, Leon and Buckholtz, Neil and Albert, Marylyn and Frank, Richard and Hsiao, John and Kaye, Jeffrey and Quinn, Joseph and Lind, Betty and Carter, Raina and Dolen, Sara and Schneider, Lon S. and Pawluczyk, Sonia and Beccera, Mauricio and Teodoro, Liberty and Spann, Bryan M. and Brewer, James and Vanderswag, Helen and Fleisher, Adam and Heidebrink, Judith L. and Lord, Joanne L. and Mason, Sara S. and Albers, Colleen S. and Knopman, David and Johnson, Kris and Doody, Rachelle S. and Villanueva-Meyer, Javier and Chowdhury, Munir and Rountree, Susan and Dang, Mimi and Stern, Yaakov and Honig, Lawrence S. and Bell, Karen L. and Ances, Beau and Carroll, Maria and Leon, Sue and Mintun, Mark A. and Schneider, Stacy and Oliver, Angela and Marson, Daniel and Griffith, Randall and Clark, David and Geldmacher, David and Brockington, John and Roberson, Erik and Grossman, Hillel and Mitsis, Effie and de Toledo-Morrell, Leyla and Shah, Raj C. and Duara, Ranjan and Varon, Daniel and Greig, Maria T. and Roberts, Peggy and Albert, Marilyn and Onyike, Chiadi and D'Agostino, Daniel and Kielb, Stephanie and Galvin, James E. and Cerbone, Brittany and Michel, Christina A. and Rusinek, Henry and de Leon, Mony J. and Glodzik, Lidia and {De Santi}, Susan and Doraiswamy, P. Murali and Petrella, Jeffrey R. and Wong, Terence Z. and Arnold, Steven E. and Karlawish, Jason H. and Wolk, David and Smith, Charles D. and Jicha, Greg and Hardy, Peter and Sinha, Partha and Oates, Elizabeth and Conrad, Gary and Lopez, Oscar L. and Oakley, Mary Ann and Simpson, Donna M. and Porsteinsson, Anton P. and Goldstein, Bonnie S. and Martin, Kim and Makino, Kelly M. and Ismail, M. Saleem and Brand, Connie and Mulnard, Ruth A. and Thai, Gaby and Mc-Adams-Ortiz, Catherine and Womack, Kyle and Mathews, Dana and Quiceno, Mary and Diaz-Arrastia, Ramon and King, Richard and Weiner, Myron and Martin-Cook, Kristen and DeVous, Michael and Levey, Allan I. and Lah, James J. and Cellar, Janet S. and Burns, Jeffrey M. and Anderson, Heather S. and Swerdlow, Russell H. and Apostolova, Liana and Tingus, Kathleen and Woo, Ellen and Silverman, Daniel Hs and Lu, Po H. and Bartzokis, George and Graff-Radford, Neill R. and Parfitt, Francine and Kendall, Tracy and Johnson, Heather and Farlow, Martin R. and Hake, Ann Marie and Matthews, Brandy R. and Herring, Scott and Hunt, Cynthia and van Dyck, Christopher H. and Carson, Richard E. and MacAvoy, Martha G. and Chertkow, Howard and Bergman, Howard and Hosein, Chris and Stefanovic, Bojana and Caldwell, Curtis and Hsiung, Ging Yuek Robin and Feldman, Howard and Mudge, Benita and Assaly, Michele and Kertesz, Andrew and Rogers, John and Bernick, Charles and Munic, Donna and Kerwin, Diana and Mesulam, Marek Marsel and Lipowski, Kristine and Wu, Chuang Kuo and Johnson, Nancy and Sadowsky, Carl and Martinez, Walter and Villena, Teresa and Turner, Raymond Scott and Johnson, Kathleen and Reynolds, Brigid and Sperling, Reisa A. and Johnson, Keith A. and Marshall, Gad and Frey, Meghan and Lane, Barton and Rosen, Allyson and Tinklenberg, Jared and Sabbagh, Marwan N. and Belden, Christine M. and Jacobson, Sandra A. and Sirrel, Sherye A. and Kowall, Neil and Killiany, Ronald and Budson, Andrew E. and Norbash, Alexander and Johnson, Patricia Lynn and Allard, Joanne and Lerner, Alan and Ogrocki, Paula and Hudson, Leon and Fletcher, Evan and Carmichael, Owen and Olichney, John and DeCarli, Charles and Kittur, Smita and Borrie, Michael and Lee, T. Y. and Bartha, Rob and Johnson, Sterling and Asthana, Sanjay and Carlsson, Cynthia M. and Potkin, Steven G. and Preda, Adrian and Nguyen, Dana and Tariot, Pierre and Reeder, Stephanie and Bates, Vernice and Capote, Horacio and Rainka, Michelle and Scharre, Douglas W. and Kataki, Maria and Adeli, Anahita and Zimmerman, Earl A. and Celmins, Dzintra and Brown, Alice D. and Pearlson, Godfrey D. and Blank, Karen and Anderson, Karen and Santulli, Robert B. and Kitzmiller, Tamar J. and Schwartz, Eben S. and Sink, Kaycee M. and Williamson, Jeff D. and Garg, Pradeep and Watkins, Franklin and Ott, Brian R. and Querfurth, Henry and Tremont, Geoffrey and Salloway, Stephen and Malloy, Paul and Correia, Stephen and Rosen, Howard J. and Miller, Bruce L. and Mintzer, Jacobo and Spicer, Kenneth and Bachman, David and Pasternak, Stephen and Rachinsky, Irina and Drost, Dick and Pomara, Nunzio and Hernando, Raymundo and Sarrael, Antero and Schultz, Susan K. and Ponto, Laura L.Boles and Shim, Hyungsub and Smith, Karen Elizabeth and Relkin, Norman and Chaing, Gloria and Raudin, Lisa and Smith, Amanda and Fargher, Kristin and Raj, Balebail Ashok and Neylan, Thomas and Grafman, Jordan and Davis, Melissa and Morrison, Rosemary and Hayes, Jacqueline and Finley, Shannon and Friedl, Karl and Fleischman, Debra and Arfanakis, Konstantinos and James, Olga and Massoglia, Dino and Fruehling, J. Jay and Harding, Sandra and Peskind, Elaine R. and Petrie, Eric C. and Li, Gail and Yesavage, Jerome A. and Taylor, Joy L. and Furst, Ansgar J.},
doi = {10.1038/s41467-018-05892-0},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Young et al. - 2018 - Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inferenc.pdf:pdf},
isbn = {4146701805},
issn = {20411723},
journal = {Nat. Commun.},
mendeley-groups = {Review2,PhDThesis},
number = {1},
pages = {1--16},
pmid = {30323170},
title = {{Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference}},
volume = {9},
year = {2018}
}

@article{Young2014,
abstract = {We demonstrate the use of a probabilistic generative model to explore the biomarker changes occurring as Alzheimer's disease develops and progresses. We enhanced the recently introduced event-based model for use with a multi-modal sporadic disease data set. This allows us to determine the sequence in which Alzheimer's disease biomarkers become abnormal without reliance on a priori clinical diagnostic information or explicit biomarker cut points. The model also characterizes the uncertainty in the ordering and provides a natural patient staging system. Two hundred and eighty-five subjects (92 cognitively normal, 129 mild cognitive impairment, 64 Alzheimer's disease) were selected from the Alzheimer's Disease Neuroimaging Initiative with measurements of 14 Alzheimer's disease-related biomarkers including cerebrospinal fluid proteins, regional magnetic resonance imaging brain volume and rates of atrophy measures, and cognitive test scores. We used the event-based model to determine the sequence of biomarker abnormality and its uncertainty in various population subgroups. We used patient stages assigned by the event-based model to discriminate cognitively normal subjects from those with Alzheimer's disease, and predict conversion from mild cognitive impairment to Alzheimer's disease and cognitively normal to mild cognitive impairment. The model predicts that cerebrospinal fluid levels become abnormal first, followed by rates of atrophy, then cognitive test scores, and finally regional brain volumes. In amyloid-positive (cerebrospinal fluid amyloid-beta1-42 {\textless}192 pg/ml) or APOE-positive (one or more APOE4 alleles) subjects, the model predicts with high confidence that the cerebrospinal fluid biomarkers become abnormal in a distinct sequence: amyloid-beta1-42, phosphorylated tau, total tau. However, in the broader population total tau and phosphorylated tau are found to be earlier cerebrospinal fluid markers than amyloid-beta1-42, albeit with more uncertainty. The model's staging system strongly separates cognitively normal and Alzheimer's disease subjects (maximum classification accuracy of 99{\%}), and predicts conversion from mild cognitive impairment to Alzheimer's disease (maximum balanced accuracy of 77{\%} over 3 years), and from cognitively normal to mild cognitive impairment (maximum balanced accuracy of 76{\%} over 5 years). By fitting Cox proportional hazards models, we find that baseline model stage is a significant risk factor for conversion from both mild cognitive impairment to Alzheimer's disease (P = 2.06 x 10(-7)) and cognitively normal to mild cognitive impairment (P = 0.033). The data-driven model we describe supports hypothetical models of biomarker ordering in amyloid-positive and APOE-positive subjects, but suggests that biomarker ordering in the wider population may diverge from this sequence. The model provides useful disease staging information across the full spectrum of disease progression, from cognitively normal to mild cognitive impairment to Alzheimer's disease. This approach has broad application across neurodegenerative disease, providing insights into disease biology, as well as staging and prognostication.},
author = {Young, Alexandra L and Oxtoby, Neil P and Daga, Pankaj and Cash, David M and Fox, Nick C and Ourselin, Sebastien and Schott, Jonathan M and Alexander, Daniel C},
doi = {10.1093/brain/awu176},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1460-2156 (Electronic)},
journal = {Brain},
keywords = { 80 and over, Factual, Neurological,Aged,Alzheimer Disease,Amyloid beta-Peptides,Apolipoproteins E,Biomarkers,Cognitive Dysfunction,Cross-Sectional Studies,Databases,Female,Follow-Up Studies,Humans,Longitudinal Studies,Male,Models,Neuropsychological Tests,Peptide Fragments,cerebrospinal fluid,diagnosis,psychology,tau Proteins,trends},
mendeley-groups = {PhDThesis/Review},
number = {Pt 9},
pages = {2564--2577},
pmid = {25012224},
title = {{A data-driven model of biomarker changes in sporadic Alzheimer's disease.}},
volume = {137},
year = {2014}
}
@article{Young2013,
abstract = {Abstract Accurately identifying the patients that have mild cognitive impairment (MCI) who will go on to develop Alzheimer's disease (AD) will become essential as new treatments will require identification of AD patients at earlier stages in the disease process. Most previous work in this area has centred around the same automated techniques used to diagnose AD patients from healthy controls, by coupling high dimensional brain image data or other relevant biomarker data to modern machine learning techniques. Such studies can now distinguish between AD patients and controls as accurately as an experienced clinician. Models trained on patients with AD and control subjects can also distinguish between MCI patients that will convert to AD within a given timeframe (MCI-c) and those that remain stable (MCI-s), although differences between these groups are smaller and thus, the corresponding accuracy is lower. The most common type of classifier used in these studies is the support vector machine, which gives categorical class decisions. In this paper, we introduce Gaussian process (GP) classification to the problem. This fully Bayesian method produces naturally probabilistic predictions, which we show correlate well with the actual chances of converting to AD within 3 years in a population of 96 MCI-s and 47 MCI-c subjects. Furthermore, we show that GPs can integrate multimodal data (in this study volumetric MRI, FDG-PET, cerebrospinal fluid, and APOE genotype with the classification process through the use of a mixed kernel). The GP approach aids combination of different data sources by learning parameters automatically from training data via type-II maximum likelihood, which we compare to a more conventional method based on cross validation and an SVM classifier. When the resulting probabilities from the GP are dichotomised to produce a binary classification, the results for predicting MCI conversion based on the combination of all three types of data show a balanced accuracy of 74{\%}. This is a substantially higher accuracy than could be obtained using any individual modality or using a multikernel SVM, and is competitive with the highest accuracy yet achieved for predicting conversion within three years on the widely used ADNI dataset.},
annote = {Interesting but NOT longitudinal},
author = {Young, Jonathan and Modat, Marc and Cardoso, Manuel J and Mendelson, Alex and Cash, Dave and Ourselin, Sebastien},
doi = {https://doi.org/10.1016/j.nicl.2013.05.004},
issn = {2213-1582},
journal = {NeuroImage Clin.},
keywords = {Alzheimer's disease,Gaussian process,Mild cognitive impairment,Multimodality,Probabilistic classification,Risk scores,Support vector machine},
mendeley-groups = {PhDThesis/Review},
pages = {735--745},
title = {{Accurate multimodal probabilistic prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment}},
volume = {2},
year = {2013}
}
@article{Zhang2012a,
abstract = {Accurate prediction of clinical changes of mild cognitive impairment (MCI) patients, including both qualitative change (i.e., conversion to Alzheimer's disease (AD)) and quantitative change (i.e., cognitive scores) at future time points, is important for early diagnosis of AD and for monitoring the disease progression. In this paper, we propose to predict future clinical changes of MCI patients by using both baseline and longitudinal multimodality data. To do this, we first develop a longitudinal feature selection method to jointly select brain regions across multiple time points for each modality. Specifically, for each time point, we train a sparse linear regression model by using the imaging data and the corresponding clinical scores, with an extra 'group regularization' to group the weights corresponding to the same brain region across multiple time points together and to allow for selection of brain regions based on the strength of multiple time points jointly. Then, to further reflect the longitudinal changes on the selected brain regions, we extract a set of longitudinal features from the original baseline and longitudinal data. Finally, we combine all features on the selected brain regions, from different modalities, for prediction by using our previously proposed multi-kernel SVM. We validate our method on 88 ADNI MCI subjects, with both MRI and FDG-PET data and the corresponding clinical scores (i.e., MMSE and ADAS-Cog) at 5 different time points. We first predict the clinical scores (MMSE and ADAS-Cog) at 24-month by using the multimodality data at previous time points, and then predict the conversion of MCI to AD by using the multimodality data at time points which are at least 6-month ahead of the conversion. The results on both sets of experiments show that our proposed method can achieve better performance in predicting future clinical changes of MCI patients than the conventional methods.},
author = {Zhang, Daoqiang and Shen, Dinggang},
doi = {10.1371/journal.pone.0033182},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1932-6203 (Electronic)},
journal = {PLoS One},
keywords = { 80 and over,Aged,Alzheimer Disease,Brain,Cognition Disorders,Disease Progression,Female,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neuropsychological Tests,Positron-Emission Tomography,Severity of Illness Index,diagnostic imaging,pathology},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {e33182},
pmid = {22457741},
title = {{Predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers.}},
volume = {7},
year = {2012}
}
@article{Zhang2012b,
abstract = {Many machine learning and pattern classification methods have been applied to the diagnosis of Alzheimer's disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). Recently, rather than predicting categorical variables as in classification, several pattern regression methods have also been used to estimate continuous clinical variables from brain images. However, most existing regression methods focus on estimating multiple clinical variables separately and thus cannot utilize the intrinsic useful correlation information among different clinical variables. On the other hand, in those regression methods, only a single modality of data (usually only the structural MRI) is often used, without considering the complementary information that can be provided by different modalities. In this paper, we propose a general methodology, namely multi-modal multi-task (M3T) learning, to jointly predict multiple variables from multi-modal data. Here, the variables include not only the clinical variables used for regression but also the categorical variable used for classification, with different tasks corresponding to prediction of different variables. Specifically, our method contains two key components, i.e., (1) a multi-task feature selection which selects the common subset of relevant features for multiple variables from each modality, and (2) a multi-modal support vector machine which fuses the above-selected features from all modalities to predict multiple (regression and classification) variables. To validate our method, we perform two sets of experiments on ADNI baseline MRI, FDG-PET, and cerebrospinal fluid (CSF) data from 45 AD patients, 91 MCI patients, and 50 healthy controls (HC). In the first set of experiments, we estimate two clinical variables such as Mini Mental State Examination (MMSE) and Alzheimer's Disease Assessment Scale-Cognitive Subscale (ADAS-Cog), as well as one categorical variable (with value of ‘AD', ‘MCI' or ‘HC'), from the baseline MRI, FDG-PET, and CSF data. In the second set of experiments, we predict the 2-year changes of MMSE and ADAS-Cog scores and also the conversion of MCI to AD from the baseline MRI, FDG-PET, and CSF data. The results on both sets of experiments demonstrate that our proposed M3T learning scheme can achieve better performance on both regression and classification tasks than the conventional learning methods.},
annote = {not longitudinal},
author = {Zhang, Daoqiang and Shen, Dinggang},
doi = {https://doi.org/10.1016/j.neuroimage.2011.09.069},
issn = {1053-8119},
journal = {Neuroimage},
keywords = {ADAS-Cog,Alzheimer's disease (AD),MCI conversion,MMSE,Multi-modal multi-task (M3T) learning,Multi-modality,Multi-task feature selection},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {895--907},
title = {{Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer's disease}},
volume = {59},
year = {2012}
}
@article{Zhang2017,
abstract = {Algorithmic image-based diagnosis and prognosis of neurodegenerative diseases on longitudinal data has drawn great interest from computer vision researchers. The current state-of-the-art models for many image classification tasks are based on the Convolutional Neural Networks (CNN). However, a key challenge in applying CNN to biological problems is that the available labeled training samples are very limited. Another issue for CNN to be applied in computer aided diagnosis applications is that to achieve better diagnosis and prognosis accuracy, one usually has to deal with the longitudinal dataset, i.e., the dataset of images scanned at different time points. Here we argue that an enhanced CNN model with transfer learning for the joint analysis of tasks from multiple time points or regions of interests may have a potential to improve the accuracy of computer aided diagnosis. To reach this goal, we innovate a CNN based deep learning multi-task dictionary learning framework to address the above challenges. Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks. Then, we propose a novel unsupervised learning method, termed Multi-task Stochastic Coordinate Coding (MSCC), for learning different tasks by using shared and individual dictionaries and generating the sparse features required to predict the future cognitive clinical scores. We apply our new model in a publicly available neuroimaging cohort to predict clinical measures with two different feature sets and compare them with seven other state-of-the-art methods. The experimental results show our proposed method achieved superior results.},
annote = {Predict future MMSE and ADAS-Cog scores with Lasso Regression.

Use a pretrained AlexNet to extract features, and then uses a novel dictionary method to create dictionary based multi task learning combining differents time points (3, no missing data) and to predict MMSE and ADAS-Cog.},
archivePrefix = {arXiv},
arxivId = {1709.00042},
author = {Zhang, Jie and Li, Qingyang and Caselli, Richard J and Ye, Jieping and Wang, Yalin},
eprint = {1709.00042},
journal = {ArXiv},
mendeley-groups = {PhDThesis/Review},
title = {{Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images}},
year = {2017}
}

@article{Zhang2014,
abstract = {Longitudinal neuroimaging studies are becoming increasingly prevalent, where brain images are collected on multiple subjects at multiple time points. Analyses of such data are scientifically important, but also challenging. Brain images are in the form of multidimensional arrays, or tensors, which are characterized by both ultrahigh dimensionality and a complex structure. Longitudinally repeated images and induced temporal correlations add a further layer of complexity. Despite some recent efforts, there exist very few solutions for longitudinal imaging analyses. In response to the increasing need to analyze longitudinal imaging data, we propose several tensor generalized estimating equations (GEEs). The proposed GEE ap- proach accounts for intra-subject correlation, and an imposed low-rank structure on the coefficient tensor effectively reduces the dimensionality. We also propose a scalable estimation algorithm, establish the asymptotic properties of the solu- tion to the tensor GEEs, and investigate sparsity regularization for the purpose of region selection. We demonstrate the proposed method using simulations and by analyzing a real data set from the Alzheimer's Disease Neuroimaging Initiative.},
archivePrefix = {arXiv},
arxivId = {1412.6592},
author = {Zhang, Xiang and Li, Lexin and Zhou, Hua and Zhou, Yeqing and Shen, Dinggang},
doi = {10.5705/ss.202017.0153},
eprint = {1412.6592},
issn = {10170405},
journal = {Stat. Sin.},
keywords = {Generalized estimating equations,Longitudinal imaging,Magnetic resonance imaging,Multidimensional array,Tensor regression,low rank tensor decomposition},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {1977--2005},
title = {{Tensor generalized estimating equations for longitudinal imaging analysis}},
volume = {29},
year = {2020}
}


@article{Zhou2013a,
abstract = {Alzheimer's disease (AD), the most common type of dementia, is a severe neurodegenerative disorder. Identifying biomarkers that can track the progress of the disease has recently received increasing attentions in AD research. An accurate prediction of disease progression would facilitate optimal decision-making for clinicians and patients. A definitive diagnosis of AD requires autopsy confirmation, thus many clinical/cognitive measures including Mini Mental State Examination (MMSE) and Alzheimer's Disease Assessment Scale cognitive subscale (ADAS-Cog) have been designed to evaluate the cognitive status of the patients and used as important criteria for clinical diagnosis of probable AD. In this paper, we consider the problem of predicting disease progression measured by the cognitive scores and selecting biomarkers predictive of the progression. Specifically, we formulate the prediction problem as a multi-task regression problem by considering the prediction at each time point as a task and propose two novel multi-task learning formulations. We have performed extensive experiments using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Specifically, we use the baseline MRI features to predict MMSE/ADAS-Cog scores in the next 4. years. Results demonstrate the effectiveness of the proposed multi-task learning formulations for disease progression in comparison with single-task learning algorithms including ridge regression and Lasso. We also perform longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression. We observe that cortical thickness average of left middle temporal, cortical thickness average of left and right Entorhinal, and white matter volume of left Hippocampus play significant roles in predicting ADAS-Cog at all time points. We also observe that several MRI biomarkers provide significant information for predicting MMSE scores for the first 2. years, however very few are shown to be significant in predicting MMSE score at later stages. The lack of predictable MRI biomarkers in later stages may contribute to the lower prediction performance of MMSE than that of ADAS-Cog in our study and other related studies. {\textcopyright}2013 Elsevier Inc.},
annote = {From Duplicate 1 (Modeling disease progression via multi-task learning - Zhou, Jiayu; Liu, Jun; Narayan, Vaibhav A.; Ye, Jieping)

Prediction paper, there are several papers similar to this},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Zhou, Jiayu and Liu, Jun and Narayan, Vaibhav A and Ye, Jieping},
doi = {10.1016/j.neuroimage.2013.03.073},
eprint = {NIHMS150003},
institution = {Alzheimer's Disease Neuroimaging Initiative},
isbn = {1095-9572},
issn = {10538119},
journal = {Neuroimage},
keywords = {ADAS-Cog,Aged,Algorithms,Alzheimer Disease,Alzheimer's disease,Artificial Intelligence,Disease Progression,Disease progression,Female,Fused Lasso,Humans,MMSE,Magnetic Resonance Imaging,Male,Multi-task learning,Regression Analysis,pathology},
mendeley-groups = {PhDThesis/Review},
pages = {233--248},
pmid = {23583359},
publisher = {Academic Press},
title = {{Modeling disease progression via multi-task learning}},
volume = {78},
year = {2013}
}
@article{Zhu2014,
abstract = {Abstract Recent studies on AD/MCI diagnosis have shown that the tasks of identifying brain disease and predicting clinical scores are highly related to each other. Furthermore, it has been shown that feature selection with a manifold learning or a sparse model can handle the problems of high feature dimensionality and small sample size. However, the tasks of clinical score regression and clinical label classification were often conducted separately in the previous studies. Regarding the feature selection, to our best knowledge, most of the previous work considered a loss function defined as an element-wise difference between the target values and the predicted ones. In this paper, we consider the problems of joint regression and classification for AD/MCI diagnosis and propose a novel matrix-similarity based loss function that uses high-level information inherent in the target response matrix and imposes the information to be preserved in the predicted response matrix. The newly devised loss function is combined with a group lasso method for joint feature selection across tasks, i.e., predictions of clinical scores and a class label. In order to validate the effectiveness of the proposed method, we conducted experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and showed that the newly devised loss function helped enhance the performances of both clinical score prediction and disease status identification, outperforming the state-of-the-art methods.},
author = {Zhu, Xiaofeng and Suk, Heung-Il and Shen, Dinggang},
doi = {https://doi.org/10.1016/j.neuroimage.2014.05.078},
issn = {1053-8119},
journal = {Neuroimage},
keywords = {Alzheimer's disease (AD),Feature selection,Joint sparse learning,Manifold learning,Mild Cognitive Impairment (MCI) conversion},
mendeley-groups = {PhDThesis/Review},
month = {oct},
pages = {91--105},
title = {{A novel matrix-similarity based loss function for joint regression and classification in AD diagnosis}},
volume = {100},
year = {2014}
}
@article{Zhu2018,
abstract = {In this work, we consider the problem of predicting the course of a progressive disease, such as cancer or Alzheimer's. Progressive diseases often start with mild symptoms that might precede a diagnosis, and each patient follows their own trajectory. Patient trajectories exhibit wild variability, which can be associated with many factors such as genotype, age, or sex. An additional layer of complexity is that, in real life, the amount and type of data available for each patient can differ significantly. For example, for one patient we might have no prior history, whereas for another patient we might have detailed clinical assessments obtained at multiple prior time-points. This paper presents a probabilistic model that can handle multiple modalities (including images and clinical assessments) and variable patient histories with irregular timings and missing entries, to predict clinical scores at future time-points. We use a sigmoidal function to model latent disease progression, which gives rise to clinical observations in our generative model. We implemented an approximate Bayesian inference strategy on the proposed model to estimate the parameters on data from a large population of subjects. Furthermore, the Bayesian framework enables the model to automatically fine-tune its predictions based on historical observations that might be available on the test subject. We applied our method to a longitudinal Alzheimer's disease dataset with more than 3000 subjects [23] and present a detailed empirical analysis of prediction performance under different scenarios, with comparisons against several benchmarks. We also demonstrate how the proposed model can be interrogated to glean insights about temporal dynamics in Alzheimer's disease.},
archivePrefix = {arXiv},
arxivId = {1803.05011},
author = {Zhu, Yingying and Sabuncu, Mert R},
doi = {arXiv:1803.05011v1},
eprint = {1803.05011},
journal = {ArXiV},
mendeley-groups = {PhDThesis/Review},
month = {mar},
title = {{A Probabilistic Disease Progression Model for Predicting Future Clinical Outcome}},
year = {2018}
}
@article{Zhu2016a,
abstract = {The diagnosis of Alzheimer's disease (AD) from neuroimaging data at the pre-clinical stage has been intensively investigated because of the immense social and economic cost. In the past decade, computational approaches on longitudinal image sequences have been actively investigated with special attention to Mild Cognitive Impairment (MCI), which is an intermediate stage between normal control (NC) and AD. However, current state-of-the-art diagnosis methods have limited power in clinical practice, due to the excessive requirements such as equal and immoderate number of scans in longitudinal imaging data. More critically, very few methods are specifically designed for the early alarm of AD uptake. To address these limitations, we propose a flexible spatial-temporal solution for early detection of AD by recognizing abnormal structure changes from longitudinal MR image sequence. Specifically, our method is leveraged by the non-reversible nature of AD progression. We employ temporally structured SVM to accurately alarm AD at early stage by enforcing the monotony on classification result to avoid unrealistic and inconsistent diagnosis result along time. Furthermore, in order to select best features which can well collaborate with the classifier, we present as joint feature selection and classification framework. The evaluation on more than 150 longitudinal subjects from ADNI dataset shows that our method is able to alarm the conversion of AD 12 months prior to the clinical diagnosis with at least 82.5 {\%} accuracy. It is worth noting that our proposed method works on widely used MR images and does not have restriction on the number of scans in the longitudinal sequence, which is very attractive to real clinical practice.},
author = {Zhu, Yingying and Zhu, Xiaofeng and Kim, Minjeong},
doi = {10.1007/978-3-319-46720-7_31},
isbn = {3642236286},
journal = {MICCAI},
mendeley-groups = {PhDThesis/Review},
pages = {264--272},
title = {{Early Diagnosis of Alzheimer's Disease by Joint Feature Selection and Classification on Temporally Structured Support Vector Machine}},
volume = {9900},
year = {2016}
}
@article{Ziegler2015b,
abstract = {We introduce a mass-univariate framework for the analysis of whole-brain structural trajectories using longitudinal Voxel-Based Morphometry data and Bayesian inference. Our approach to developmental and aging longitudinal studies characterizes heterogeneous structural growth/decline between and within groups. In particular, we propose a probabilistic generative model that parameterizes individual and ensemble average changes in brain structure using linear mixed-effects models of age and subject-specific covariates. Model inversion uses Expectation Maximization (EM), while voxelwise (empirical) priors on the size of individual differences are estimated from the data. Bayesian inference on individual and group trajectories is realized using Posterior Probability Maps (PPM). In addition to parameter inference, the framework affords comparisons of models with varying combinations of model order for fixed and random effects using model evidence. We validate the model in simulations and real MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) project. We further demonstrate how subject specific characteristics contribute to individual differences in longitudinal volume changes in healthy subjects, Mild Cognitive Impairment (MCI), and Alzheimer's Disease (AD).},
annote = {Mixed effects (fixed and random) models, creating diverse

Voxel based. 

Characterize different groups.},
author = {Ziegler, G and Penny, W D and Ridgway, G R and Ourselin, S and Friston, K J},
doi = {10.1016/j.neuroimage.2015.06.094},
isbn = {1053-8119},
issn = {10959572},
journal = {Neuroimage},
keywords = {Bayesian inference,Brain morphology,Dementia,Lifespan brain aging,Longitudinal analysis,Multi-level models},
mendeley-groups = {PhDThesis/Review},
pages = {51--68},
pmid = {26190405},
title = {{Estimating anatomical trajectories with Bayesian mixed-effects modeling}},
volume = {121},
year = {2015}
}
@article{Zipunnikov2014,
abstract = {{\textcopyright}Institute of Mathematical Statistics, 2014. We develop a flexible framework for modeling high-dimensional imaging data observed longitudinally. The approach decomposes the observed variability of repeatedly measured high-dimensional observations into three additive components: a subject-specific imaging random intercept that quantifies the cross-sectional variability, a subject-specific imaging slope that quantifies the dynamic irreversible deformation over multiple realizations, and a subject-visit-specific imaging deviation that quantifies exchangeable effects between visits. The proposed method is very fast, scalable to studies including ultrahigh-dimensional data, and can easily be adapted to and executed on modest computing infrastructures. The method is applied to the longitudinal analysis of diffusion tensor imaging (DTI) data of the corpus callosum of multiple sclerosis (MS) subjects. The study includes 176 subjects observed at 466 visits. For each subject and visit the study contains a registered DTI scan of the corpus callosum at roughly 30,000 voxels.},
archivePrefix = {arXiv},
arxivId = {arXiv:1501.04420v1},
author = {Zipunnikov, Vadim and Greven, Sonja and Shou, Haochang and Caffo, Brian S and Reich, Daniel S and Crainiceanu, Ciprian M},
doi = {10.1214/14-AOAS748},
eprint = {arXiv:1501.04420v1},
issn = {19417330},
journal = {Ann. Appl. Stat.},
keywords = {Brain imaging data,Diffusion tensor imaging,Linear mixed model,Multiple sclerosis,Principal components},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {2175--2202},
title = {{Longitudinal high-dimensional principal components analysis with application to diffusion tensor imaging of multiple sclerosis}},
volume = {8},
year = {2014}
}
@article{Dong2019,
abstract = {Apolipoprotein E (APOE) e4 is the major genetic risk factor for late-onset Alzheimer's disease (AD). The dose-dependent impact of this allele on hippocampal volumes has been documented, but its influence on general hippocampal morphology in cognitively unimpaired individuals is still elusive. Capitalizing on the study of a large number of cognitively unimpaired late middle aged and older adults with two, one and no APOE-e4 alleles, the current study aims to characterize the ability of our automated surface-based hippocampal morphometry algorithm to distinguish between these three levels of genetic risk for AD and demonstrate its superiority to a commonly used hippocampal volume measurement. We examined the APOE-e4 dose effect on cross-sectional hippocampal morphology analysis in a magnetic resonance imaging (MRI) database of 117 cognitively unimpaired subjects aged between 50 and 85 years (mean = 57.4, SD = 6.3), including 36 heterozygotes (e3/e4), 37 homozygotes (e4/e4) and 44 non-carriers (e3/e3). The proposed automated framework includes hippocampal surface segmentation and reconstruction, higher-order hippocampal surface correspondence computation, and hippocampal surface deformation analysis with multivariate statistics. In our experiments, the surface-based method identified APOE-e4 dose effects on the left hippocampal morphology. Compared to the widely-used hippocampal volume measure, our hippocampal morphometry statistics showed greater statistical power by distinguishing cognitively unimpaired subjects with two, one, and no APOE-e4 alleles. Our findings mirrored previous studies showing that APOE-e4 has a dose effect on the acceleration of brain structure deformities. The results indicated that the proposed surface-based hippocampal morphometry measure is a potential preclinical AD imaging biomarker for cognitively unimpaired individuals.},
author = {Dong, Qunxi and Zhang, Wen and Wu, Jianfeng and Li, Bolun and Schron, Emily H and McMahon, Travis and Shi, Jie and Gutman, Boris A and Chen, Kewei and Baxter, Leslie C and Thompson, Paul M and Reiman, Eric M and Caselli, Richard J and Wang, Yalin},
doi = {10.1016/j.nicl.2019.101744},
issn = {22131582},
journal = {NeuroImage Clin.},
keywords = {APOE-e4,Alzheimer's disease,Cognitively unimpaired,Hippocampal morphometry,Magnetic resonance imaging (MRI)},
mendeley-groups = {PhDThesis/Hippo},
number = {March},
pages = {101744},
pmid = {30852398},
publisher = {Elsevier},
title = {{Applying surface-based hippocampal morphometry to study APOE-E4 allele dose effects in cognitively unimpaired subjects}},
volume = {22},
year = {2019}
}
@article{Dill2015,
author = {Dill, Vanderson and Franco, Alexandre Rosa and Pinho, M{\'{a}}rcio Sarroglia},
doi = {10.1007/s12021-014-9243-4},
issn = {1539-2791},
journal = {Neuroinformatics},
mendeley-groups = {PhDThesis/Hippo},
number = {2},
pages = {133--150},
publisher = {Springer US},
title = {{Automated Methods for Hippocampus Segmentation: the Evolution and a Review of the State of the Art}},
volume = {13},
year = {2015}
}
@article{Hsu2002,
abstract = {To determine whether automatic and manual measurements of hippocampal volume differences on MRI between normal aging, cognitive impairment (CI), and Alzheimer's disease (AD) yield similar results.},
author = {Hsu, Yuan Yu and Schuff, Norbert and Du, An Tao and Mark, Kevin and Zhu, Xiaoping and Hardin, Dawn and Weiner, Michael W},
doi = {10.1002/jmri.10163},
issn = {10531807},
journal = {J. Magn. Reson. Imaging},
keywords = {Atrophy,Brain mapping,Neurodegeneration,Neuroimaging,Reliability},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {305--310},
pmid = {12205587},
publisher = {NIH Public Access},
title = {{Comparison of automated and manual MRI volumetry of hippocampus in normal aging and dementia}},
volume = {16},
year = {2002}
}
@article{TenKate2016,
abstract = {The apolipoprotein E $\epsilon$4 allele (APOE4) and family history of dementia (FH) are well-known risk factors for the development of sporadic Alzheimer's disease. We assessed the effects of these risk factors on gray matter (GM) volume in 295 cognitively healthy middle-aged community-dwelling subjects. Voxel-based morphometry was used to study GM volume differences between high- and low-risk subjects, based on APOE4 carriership (n = 74), first-degree FH (n = 228), or both (n = 62). No significant results were found using a corrected p value. Using a more lenient threshold (p {\textless}0.001 and minimum cluster size of 100 voxels), APOE4 carriers had reduced GM in the striatum compared to noncarriers. Subjects with FH had reduced GM in right precuneus compared to subjects without FH. Maternal and paternal FH provided similar atrophy patterns. APOE4 carriers with FH had GM reductions in bilateral insula compared to subjects with neither APOE4 nor FH. We conclude that a family history of dementia and APOE4 carriership are both associated with regional GM decreases in cognitively healthy middle-aged subjects, with differential effects on brain regions typically affected in Alzheimer's disease.},
author = {{Ten Kate}, Mara and Sanz-Arigita, Ernesto J and Tijms, Betty M and Wink, Alle Meije and Clerigue, Montserrat and Garcia-Sebastian, Maite and Izagirre, Andrea and Ecay-Torres, Miriam and Estanga, Ainara and Villanua, Jorge and Vrenken, Hugo and Visser, Pieter Jelle and Martinez-Lage, Pablo and Barkhof, Frederik},
doi = {10.1016/j.neurobiolaging.2015.10.018},
issn = {15581497},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Apolipoprotein E,Dementia,Family history,MRI,Voxel-based morphometry},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
pages = {14--20},
publisher = {Elsevier},
title = {{Impact of APOE-$\varepsilon$4 and family history of dementia on gray matter atrophy in cognitively healthy middle-aged adults}},
volume = {38},
year = {2016}
}
@article{Genin2011,
abstract = {Apolipoprotein E (APOE) dependent lifetime risks (LTRs) for Alzheimer Disease (AD) are currently not accurately known and odds ratios alone are insufficient to assess these risks. We calculated AD LTR in 7351 cases and 10 132 controls from Caucasian ancestry using Rochester (USA) incidence data. At the age of 85 the LTR of AD without reference to APOE genotype was 11{\%} in males and 14{\%} in females. At the same age, this risk ranged from 51{\%} for APOE44 male carriers to 60{\%} for APOE44 female carriers, and from 23{\%} for APOE34 male carriers to 30{\%} for APOE34 female carriers, consistent with semi-dominant inheritance of a moderately penetrant gene. Using PAQUID (France) incidence data, estimates were globally similar except that at age 85 the LTRs reached 68 and 35{\%} for APOE 44 and APOE 34 female carriers, respectively. These risks are more similar to those of major genes in Mendelian diseases, such as BRCA1 in breast cancer, than those of low-risk common alleles identified by recent GWAS in complex diseases. In addition, stratification of our data by age groups clearly demonstrates that APOE4 is a risk factor not only for late-onset but for early-onset AD as well. Together, these results urge a reappraisal of the impact of APOE in Alzheimer disease. {\textcopyright}2011 Macmillan Publishers Limited All rights reserved.},
author = {Genin, E and Hannequin, D and Wallon, D and Sleegers, K and Hiltunen, M and Combarros, O and Bullido, M J and Engelborghs, S and {De Deyn}, P and Berr, C and Pasquier, F and Dubois, B and Tognoni, G and Fi{\'{e}}vet, N and Brouwers, N and Bettens, K and Arosio, B and Coto, E and {Del Zompo}, M and Mateo, I and Epelbaum, J and Frank-Garcia, A and Helisalmi, S and Porcellini, E and Pilotto, A and Forti, P and Ferri, R and Scarpini, E and Siciliano, G and Solfrizzi, V and Sorbi, S and Spalletta, G and Valdivieso, F and Veps{\"{a}}l{\"{a}}inen, S and Alvarez, V and Bosco, P and Mancuso, M and Panza, F and Nacmias, B and Boss, P and Hanon, O and Piccardi, P and Annoni, G and Seripa, D and Galimberti, D and Licastro, F and Soininen, H and Dartigues, J F and Kamboh, M I and {Van Broeckhoven}, C and Lambert, J C and Amouyel, P and Campion, D},
doi = {10.1038/mp.2011.52},
issn = {13594184},
journal = {Mol. Psychiatry},
keywords = {APOE,Alzheimer,epidemiology,genetics,lifetime risks},
mendeley-groups = {PhDThesis/Hippo},
number = {9},
pages = {903--907},
pmid = {21556001},
publisher = {Nature Publishing Group},
title = {{APOE and Alzheimer disease: A major gene with semi-dominant inheritance}},
volume = {16},
year = {2011}
}
@article{Jack2010a,
abstract = {Functions of the Alzheimer's Disease Neuroimaging Initiative (ADNI) magnetic resonance imaging (MRI) core fall into three categories: (1) those of the central MRI core laboratory at Mayo Clinic, Rochester, Minnesota, needed to generate high quality MRI data in all subjects at each time point; (2) those of the funded ADNI MRI core imaging analysis groups responsible for analyzing the MRI data; and (3) the joint function of the entire MRI core in designing and problem solving MR image acquisition, pre-processing, and analyses methods. The primary objective of ADNI was and continues to be improving methods for clinical trials in Alzheimer's disease. Our approach to the present ("ADNI- GO") and future ("ADNI-2," if funded) MRI protocol will be to maintain MRI methodological consistency in the previously enrolled "ADNI-1" subjects who are followed up longitudinally in ADNI-GO and ADNI-2. We will modernize and expand the MRI protocol for all newly enrolled ADNI-GO and ADNI-2 subjects. All newly enrolled subjects will be scanned at 3T with a core set of three sequence types: 3D T1-weighted volume, FLAIR, and a long TE gradient echo volumetric acquisition for micro hemorrhage detection. In addition to this core ADNI-GO and ADNI-2 protocol, we will perform vendor-specific pilot sub-studies of arterial spin-labeling perfusion, resting state functional connectivity, and diffusion tensor imaging. One of these sequences will be added to the core protocol on systems from each MRI vendor. These experimental sub-studies are designed to demonstrate the feasibility of acquiring useful data in a multicenter (but single vendor) setting for these three emerging MRI applications. {\textcopyright}2010 The Alzheimer's Association. All rights reserved.},
author = {Jack, Clifford R and Bernstein, Matt A and Borowski, Bret J and Gunter, Jeffrey L and Fox, Nick C and Thompson, Paul M and Schuff, Norbert and Krueger, Gunnar and Killiany, Ronald J and Decarli, Charles S and Dale, Anders M and Carmichael, Owen W and Tosun, Duygu and Weiner, Michael W},
doi = {10.1016/j.jalz.2010.03.004},
issn = {15525260},
journal = {Alzheimer's Dement.},
keywords = {ADNI,Alzheimer's disease,Magnetic resonance imaging},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {212--220},
publisher = {Elsevier Inc.},
title = {{Update on the Magnetic Resonance Imaging core of the Alzheimer's Disease Neuroimaging Initiative}},
volume = {6},
year = {2010}
}
@article{Reiman2020,
abstract = {Each additional copy of the apolipoprotein E4 (APOE4) allele is associated with a higher risk of Alzheimer's dementia, while the APOE2 allele is associated with a lower risk of Alzheimer's dementia, it is not yet known whether APOE2 homozygotes have a particularly low risk. We generated Alzheimer's dementia odds ratios and other findings in more than 5,000 clinically characterized and neuropathologically characterized Alzheimer's dementia cases and controls. APOE2/2 was associated with a low Alzheimer's dementia odds ratios compared to APOE2/3 and 3/3, and an exceptionally low odds ratio compared to APOE4/4, and the impact of APOE2 and APOE4 gene dose was significantly greater in the neuropathologically confirmed group than in more than 24,000 neuropathologically unconfirmed cases and controls. Finding and targeting the factors by which APOE and its variants influence Alzheimer's disease could have a major impact on the understanding, treatment and prevention of the disease.},
author = {Reiman, Eric M and Arboleda-Velasquez, Joseph F and Quiroz, Yakeel T and Huentelman, Matthew J and Beach, Thomas G and Caselli, Richard J and Chen, Yinghua and Su, Yi and Myers, Amanda J and Hardy, John and {Paul Vonsattel}, Jean and Younkin, Steven G and Bennett, David A and {De Jager}, Philip L and Larson, Eric B and Crane, Paul K and Keene, C Dirk and Kamboh, M Ilyas and Kofler, Julia K and Duque, Linda and Gilbert, John R and Gwirtsman, Harry E and Buxbaum, Joseph D and Dickson, Dennis W and Frosch, Matthew P and Ghetti, Bernardino F and Lunetta, Kathryn L and Wang, Li San and Hyman, Bradley T and Kukull, Walter A and Foroud, Tatiana and Haines, Jonathan L and Mayeux, Richard P and Pericak-Vance, Margaret A and Schneider, Julie A and Trojanowski, John Q and Farrer, Lindsay A and Schellenberg, Gerard D and Beecham, Gary W and Montine, Thomas J and Jun, Gyungah R and Abner, Erin and Adams, Perrie M and Albert, Marilyn S and Albin, Roger L and Apostolova, Liana G and Arnold, Steven E and Asthana, Sanjay and Atwood, Craig S and Baldwin, Clinton T and Barber, Robert C and Barnes, Lisa L and Barral, Sandra and Becker, James T and Beekly, Duane and Bigio, Eileen H and Bird, Thomas D and Blacker, Deborah and Boeve, Bradley F and Bowen, James D and Boxer, Adam and Burke, James R and Burns, Jeffrey M and Cairns, Nigel J and Cantwell, Laura B and Cao, Chuanhai and Carlson, Chris S and Carlsson, Cynthia M and Carney, Regina M and Carrasquillo, Minerva M and Chui, Helena C and Cribbs, David H and Crocco, Elizabeth A and Cruchaga, Carlos and DeCarli, Charles and Dick, Malcolm and Doody, Rachelle S and Duara, Ranjan and Ertekin-Taner, Nilufer and Evans, Denis A and Faber, Kelley M and Fairchild, Thomas J and Fallon, Kenneth B and Fardo, David W and Farlow, Martin R and Ferris, Steven and Galasko, Douglas R and Gearing, Marla and Geschwind, Daniel H and Ghisays, Valentina and Goate, Alison M and Graff-Radford, Neill R and Green, Robert C and Growdon, John H and Hakonarson, Hakon and Hamilton, Ronald L and Hamilton-Nelson, Kara L and Harrell, Lindy E and Honig, Lawrence S and Huebinger, Ryan M and Hulette, Christine M and Jarvik, Gail P and Jin, Lee Way and Karydas, Anna and Katz, Mindy J and Kauwe, John S K and Kaye, Jeffrey A and Kim, Ronald and Kowall, Neil W and Kramer, Joel H and Kunkle, Brian W and Kuzma, Amanda P and LaFerla, Frank M and Lah, James J and Leung, Yuk Ye and Leverenz, James B and Levey, Allan I and Li, Ge and Lieberman, Andrew P and Lipton, Richard B and Lopez, Oscar L and Lyketsos, Constantine G and Malamon, John and Marson, Daniel C and Martin, Eden R and Martiniuk, Frank and Mash, Deborah C and Masliah, Eliezer and McCormick, Wayne C and McCurry, Susan M and McDavid, Andrew N and McDonough, Stefan and McKee, Ann C and Mesulam, Marsel and Miller, Bruce L and Miller, Carol A and Miller, Joshua W and Morris, John C and Mukherjee, Shubhabrata and Naj, Adam C and O'Bryant, Sid and Olichney, John M and Parisi, Joseph E and Paulson, Henry L and Peskind, Elaine and Petersen, Ronald C and Pierce, Aimee and Poon, Wayne W and Potter, Huntington and Qu, Liming and Quinn, Joseph F and Raj, Ashok and Raskind, Murray and Reisberg, Barry and Reisch, Joan S and Reitz, Christiane and Ringman, John M and Roberson, Erik D and Rogaeva, Ekaterina and Rosen, Howard J and Rosenberg, Roger N and Royall, Donald R and Sager, Mark A and Sano, Mary and Saykin, Andrew J and Schneider, Lon S and Seeley, William W and Smith, Amanda G and Sonnen, Joshua A and Spina, Salvatore and George-Hyslop, Peter St and Stern, Robert A and Swerdlow, Russell H and Tanzi, Rudolph E and Troncoso, Juan C and Tsuang, Debby W and Valladares, Otto and {Van Deerlin}, Vivianna M and {Van Eldik}, Linda J and Vardarajan, Badri N and Vinters, Harry V and Weintraub, Sandra and Welsh-Bohmer, Kathleen A and Wilhelmsen, Kirk C and Williamson, Jennifer and Wingo, Thomas S and Woltjer, Randall L and Wright, Clinton B and Wu, Chuang Kuo and Yu, Chang En and Yu, Lei and Zhao, Yi},
doi = {10.1038/s41467-019-14279-8},
issn = {20411723},
journal = {Nat. Commun.},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pmid = {32015339},
title = {{Exceptionally low likelihood of Alzheimer's dementia in APOE2 homozygotes from a 5,000-person neuropathological study}},
volume = {11},
year = {2020}
}
@article{Wolk2010,
abstract = {The $\zeta$4 allele of the apolipoprotein E (APOE) gene is the major genetic risk factor for Alzheimer's disease (AD), but limited work has suggested that APOE genotype may modulate disease phenotype. Carriers of the $\zeta$4 allele have been reported to have greater medial temporal lobe (MTL) pathology and poorer memory than noncarriers. Less attention has focused on whether there are domains of cognition and neuroanatomical regions more affected in noncarriers. Further, a major potential confound of prior in vivo studies is the possibility of different rates of clinical misdiagnosis for carriers vs. noncarriers. We compared phenotypic differences in cognition and topography of regional cortical atrophy of $\zeta$4 carriers (n = 67) vs. noncarriers (n = 24) with mild AD from the Alzheimer's Disease Neuroimaging Initiative, restricted to those with a cerebrospinal fluid (CSF) molecular profile consistent with AD. Between-group comparisons were made for psychometric tests and morphometric measures of cortical thickness and hippocampal volume. Carriers displayed significantly greater impairment on measures of memory retention, whereas noncarriers were more impaired on tests of working memory, executive control, and lexical access. Consistent with this cognitive dissociation, carriers exhibited greater MTL atrophy, whereas noncarriers had greater frontoparietal atrophy. Performance deficits in particular cognitive domains were associated with disproportionate regional brain atrophy within nodes of cortical networks thought to subserve these cognitive processes. These convergent cognitive and neuroanatomic findings in individuals with a CSF molecular profile consistent with AD support the hypothesis that APOE genotype modulates the clinical phenotype of AD through influence on specific large-scale brain networks.},
author = {Wolk, David A and Dickerson, Bradford C},
doi = {10.1073/pnas.1001412107},
issn = {00278424},
journal = {Proc. Natl. Acad. Sci. U. S. A.},
keywords = {Cognition,Cortical thickness,Dementia,Medial temporal lobe,Neuroimaging},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {22},
pages = {10256--10261},
pmid = {20479234},
publisher = {National Academy of Sciences},
title = {{Apolipoprotein E (APOE) genotype has dissociable effects on memory and attentional-executive network function in Alzheimer's disease}},
volume = {107},
year = {2010}
}
@article{Tuminello2011,
abstract = {Research on apolipoprotein E (APOE) has consistently revealed a relationship between the gene's $\epsilon$4 allele and risk for development of Alzheimer's disease (AD). However, research with younger populations of $\epsilon$4 carriers has suggested that the APOE $\epsilon$4 allele may in fact be beneficial in earlier ages and may only confer risk of cognitive decline later in life. Accordingly, we and others have proposed that APOE may represent an example of antagonistic pleiotropy. Antagonistic pleiotropy is an evolutionary biology concept that proposes certain genes or alleles that may differentially impact fitness during different life stages. We critically review this hypothesis in light of new research of the impact of APOE on cognition and neural integrity across the lifespan. We provide recommendations for the revision of the antagonistic pleiotropy hypothesis of APOE and suggest important avenues for future research in this area.},
author = {Tuminello, Elizabeth R and Han, S Duke},
doi = {10.4061/2011/726197},
issn = {20900252},
journal = {Int. J. Alzheimer. Dis.},
mendeley-groups = {PhDThesis/Hippo},
title = {{The apolipoprotein e antagonistic pleiotropy hypothesis: Review and recommendations}},
volume = {2011},
year = {2011}
}
@article{Hostage2013,
abstract = {OBJECTIVE: To investigate whether there is a specific dose-dependent effect of the Apolipoprotein E (APOE) $\epsilon$4 and $\epsilon$2 alleles on hippocampal volume, across the cognitive spectrum, from normal aging to Alzheimer's Disease (AD).$\backslash$n$\backslash$nMATERIALS AND METHODS: We analyzed MR and genetic data on 662 patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database-198 cognitively normal controls (CN), 321 mild-cognitive impairment (MCI) subjects, and 143 AD subjects-looking for dose-dependent effects of the $\epsilon$4 and $\epsilon$2 alleles on hippocampal volumes. Volumes were measured using a fully-automated algorithm applied to high resolution T1-weighted MR images. Statistical analysis consisted of a multivariate regression with repeated-measures model.$\backslash$n$\backslash$nRESULTS: There was a dose-dependent effect of the $\epsilon$4 allele on hippocampal volume in AD (p = 0.04) and MCI (p = 0.02)-in both cases, each allele accounted for loss of {\textgreater}150 mm(3) (approximately 4{\%}) of hippocampal volume below the mean volume for AD and MCI subjects with no such alleles (Cohen's d = -0.16 and -0.19 for AD and MCI, respectively). There was also a dose-dependent, main effect of the $\epsilon$2 allele (p{\textless}0.0001), suggestive of a moderate protective effect on hippocampal volume-an approximately 20{\%} per allele volume increase as compared to CN with no $\epsilon$2 alleles (Cohen's d = 0.23).$\backslash$n$\backslash$nCONCLUSION: Though no effect of $\epsilon$4 was seen in CN subjects, our findings confirm and extend prior data on the opposing effects of the APOE $\epsilon$4 and $\epsilon$2 alleles on hippocampal morphology across the spectrum of cognitive aging.},
author = {Hostage, Christopher A and {Roy Choudhury}, Kingshuk and Doraiswamy, Pudugramam Murali and Petrella, Jeffrey R},
doi = {10.1371/journal.pone.0054483},
editor = {Breitner, John C S},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {2},
pages = {e54483},
publisher = {Public Library of Science},
title = {{Dissecting the Gene Dose-Effects of the APOE $\epsilon$4 and $\epsilon$2 Alleles on Hippocampal Volumes in Aging and Alzheimer's Disease}},
volume = {8},
year = {2013}
}
@article{Protas2013,
abstract = {OBJECTIVE: To characterize and compare measurements of the posterior cingulate glucose metabolism, the hippocampal glucose metabolism, and hippocampal volume so as to distinguish cognitively normal, late-middle-aged persons with 2, 1, or 0 copies of the apolipoprotein E (APOE) $\epsilon$4 allele, reflecting 3 levels of risk for late-onset Alzheimer disease.$\backslash$n$\backslash$nDESIGN: Cross-sectional comparison of measurements of cerebral glucose metabolism using 18F-fluorodeoxyglucose positron emission tomography and measurements of brain volume using magnetic resonance imaging in cognitively normal $\epsilon$4 homozygotes, $\epsilon$4 heterozygotes, and noncarriers.$\backslash$n$\backslash$nSETTING: Academic medical center.$\backslash$n$\backslash$nPARTICIPANTS: A total of 31 $\epsilon$4 homozygotes, 42 $\epsilon$4 heterozygotes, and 76 noncarriers, 49 to 67 years old, matched for sex, age, and educational level.$\backslash$n$\backslash$nMAIN OUTCOME MEASURES: The measurements of posterior cingulate and hippocampal glucose metabolism were characterized using automated region-of-interest algorithms and normalized for whole-brain measurements. The hippocampal volume measurements were characterized using a semiautomated algorithm and normalized for total intracranial volume.$\backslash$n$\backslash$nRESULTS: Although there were no significant differences among the 3 groups of participants in their clinical ratings, neuropsychological test scores, hippocampal volumes (P = .60), or hippocampal glucose metabolism measurements (P = .12), there were significant group differences in their posterior cingulate glucose metabolism measurements (P = .001). The APOE $\epsilon$4 gene dose was significantly associated with posterior cingulate glucose metabolism (r = 0.29, P = .0003), and this association was significantly greater than those with hippocampal volume or hippocampal glucose metabolism (P {\textless}.05, determined by use of pairwise Fisher z tests).$\backslash$n$\backslash$nCONCLUSIONS: Although our findings may depend in part on the analysis algorithms used, they suggest that a reduction in posterior cingulate glucose metabolism precedes a reduction in hippocampal volume or metabolism in cognitively normal persons at increased genetic risk for Alzheimer disease.},
author = {Protas, Hillary D and Chen, Kewei and Langbaum, Jessica B S and Fleisher, Adam S and Alexander, Gene E and Lee, Wendy and Bandy, Daniel and {De Leon}, Mony J and Mosconi, Lisa and Buckley, Shannon and Truran-Sacrey, Diana and Schuff, Norbert and Weiner, Michael W and Caselli, Richard J and Reiman, Eric M},
doi = {10.1001/2013.jamaneurol.286},
issn = {21686149},
journal = {JAMA Neurol.},
keywords = {alleles,alzheimer disease,alzheimer's disease,apolipoprotein e,brain,brain volume,genes,genetic risk,glucose metabolism,heterozygote,hippocampus,homozygote,late onset,magnetic resonance imaging,positron-emission tomography},
mendeley-groups = {PhDThesis/Hippo},
month = {mar},
number = {3},
pages = {320--325},
publisher = {American Medical Association},
title = {{Posterior cingulate glucose metabolism, hippocampal glucose metabolism, and hippocampal volume in cognitively normal, late-middle-aged persons at 3 levels of genetic risk for alzheimer disease}},
volume = {70},
year = {2013}
}
@article{Reiman2004,
abstract = {Fluorodeoxyglucose positron emission tomography (PET) studies have found that patients with Alzheimer's dementia (AD) have abnormally low rates of cerebral glucose metabolism in posterior cingulate, parietal, temporal, and prefrontal cortex, We previously found that cognitively normal, late-middle-aged carriers of the apolipoprotein E $\epsilon$4 allele, a common susceptibility gene for late-onset Alzheimer's dementia, have abnormally low rates of glucose metabolism in the same brain regions as patients with probable AD. We now consider whether $\epsilon$4 carriers have these regional brain abnormalities as relatively young adults. Apolipoprotein E genotypes were established in normal volunteers 20-39 years of age. Clinical ratings, neuropsychological tests, magnetic resonance imaging, and PET were performed in 12 $\epsilon$4 heterozygotes, all with the $\epsilon$3/$\epsilon$4 genotype, and 15 noncarriers of the $\epsilon$4 allele, 12 of whom were individually matched for sex, age, and educational level. An automated algorithm was used to generate an aggregate surface-projection map that compared regional PET measurements in the two groups. The young adult $\epsilon$4 carriers and noncarriers did not differ significantly in their sex, age, educational level, clinical ratings, or neuropsychological test scores. Like previously studied patients with probable AD and late-middle-aged $\epsilon$4 carriers, the young $\epsilon$4 carriers had abnormally low rates of glucose metabolism bilaterally in the posterior cingulate, parietal, temporal, and prefrontal cortex. Carriers of a common Alzheimer's susceptibility gene have functional brain abnormalities in young adulthood, several decades before the possible onset of dementia.},
author = {Reiman, E M and Chen, K and Alexander, G E and Caselli, R J and Bandy, D and Osborne, D and Saunders, A M and Hardy, J},
doi = {10.1073/pnas.2635903100},
issn = {0027-8424},
journal = {Proc. Natl. Acad. Sci.},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pages = {284--289},
title = {{Functional brain abnormalities in young adults at genetic risk for late-onset Alzheimer's dementia}},
volume = {101},
year = {2004}
}
@article{Reiman2009,
author = {Reiman, Eric M and Chen, Kewei and Liu, Xiaofen and Bandy, Daniel and Yu, Meixiang and Lee, Wendy and Alexander, Gene E and Klunk, William E and Mathis, Chester A and Price, Julie C and Aizenstein, Howard J and Dekosky, Steven T and Caselli, Richard J},
doi = {10.1073/pnas.0900345106},
journal = {PNAS},
mendeley-groups = {PhDThesis/Hippo},
number = {16},
title = {{Fibrillar amyloid-$\beta$ burden in cognitively normal people at 3 levels of genetic risk for Alzheimer's disease}},
volume = {106},
year = {2009}
}
@article{Molinuevo2016,
abstract = {Introduction The preclinical phase of Alzheimer's disease (AD) is optimal for identifying early pathophysiological events and developing prevention programs, which are shared aims of the ALFA project, including the ALFA registry and parent cohort and the nested ALFA+ cohort study. Methods The ALFA parent cohort baseline visit included full cognitive evaluation, lifestyle habits questionnaires, DNA extraction, and MRI. The nested ALFA+ study adds wet and imaging biomarkers for deeper phenotyping. Results A total of 2743 participants aged 45 to 74 years were included in the ALFA parent cohort. We show that this cohort, mostly composed of cognitively normal offspring of AD patients, is enriched for AD genetic risk factors. Discussion The ALFA project represents a valuable infrastructure that will leverage with different studies and trials to prevent AD. The longitudinal ALFA+ cohort will serve to untangle the natural history of the disease and to model the preclinical stages to develop successful trials.},
author = {Molinuevo, Jos{\'{e}} Luis and Gramunt, Nina and Gispert, Juan Domingo and Fauria, Karine and Esteller, Manel and Minguillon, Carolina and S{\'{a}}nchez-Benavides, Gonzalo and Huesa, Gema and Mor{\'{a}}n, Sebasti{\'{a}}n and Dal-R{\'{e}}, Rafael and Cam{\'{i}}, Jordi},
doi = {10.1016/j.trci.2016.02.003},
issn = {23528737},
journal = {Alzheimer's Dement. Transl. Res. Clin. Interv.},
keywords = {Alzheimer's disease,Biomarkers,Cognition,Cohort studies,Dementia,Prevention,Risk factors},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {2},
pages = {82--92},
publisher = {Elsevier},
title = {{The ALFA project: A research platform to identify early pathophysiological features of Alzheimer's disease}},
volume = {2},
year = {2016}
}

@article{Campion1999,
abstract = {To determine the prevalence of early-onset Alzheimer disease (EOAD) and of autosomal dominant forms of EOAD (ADEOAD), we performed a population-based study in the city of Rouen (426,710 residents). EOAD was defined as onset of disease at age {\textless}61 years, and ADEOAD was defined as the occurrence of at least three EOAD cases in three generations. Using these stringent criteria, we calculated that the EOAD and ADEOAD prevalences per 100,000 persons at risk were 41.2 and 5.3, respectively. We then performed a mutational analysis of the genes for amyloid precursor protein (APP), presenilin 1 (PSEN1), and presenilin 2 (PSEN2) in 34 families with ADEOAD ascertained in France. In 19 (56{\%}) of these families, we identified 16 distinct PSEN1 missense mutations, including 4 (Thr147Ile, Trp165Cys, Leu173Trp, and Ser390Ile) not reported elsewhere. APP mutations, including a novel mutation located at codon 715, were identified in 5 (15{\%}) of the families. In the 10 remaining ADEOAD families and in 9 additional autosomal dominant Alzheimer disease families that did not fulfill the strict criteria for ADEOAD, no PSEN1, PSEN2, or APP mutation was identified. These results show that (1) PSEN1 and APP mutations account for 71{\%} of ADEOAD families and (2) nonpenetrance at age {\textless}61 years is probably infrequent for PSEN1 or APP mutations.},
author = {Campion, Dominique and Dumanchin, C{\'{e}}cile and Hannequin, Didier and Dubois, Bruno and Belliard, Serge and Puel, Mich{\`{e}}le and Thomas-Anterion, Catherine and Michon, Agn{\`{e}}s and Martin, Cosette and Charbonnier, Fran{\c{c}}oise and Raux, Gr{\'{e}}gory and Camuzat, Agn{\`{e}}s and Penet, Christiane and Mesnage, Val{\'{e}}rie and Martinez, Maria and Clerget-Darpoux, Fran{\c{c}}oise and Brice, Alexis and Frebourg, Thierry},
doi = {10.1086/302553},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Campion et al. - 1999 - Early-onset autosomal dominant Alzheimer disease Prevalence, genetic heterogeneity, and mutation spectrum.pdf:pdf},
issn = {00029297},
journal = {Am. J. Hum. Genet.},
mendeley-groups = {PhDThesis/Introduction},
month = {sep},
number = {3},
pages = {664--670},
pmid = {10441572},
publisher = {University of Chicago Press},
title = {{Early-onset autosomal dominant Alzheimer disease: Prevalence, genetic heterogeneity, and mutation spectrum}},
volume = {65},
year = {1999}
}


@article{Huang2020,
abstract = {Alzheimer disease (AD) accounts for 60-70{\%} of dementia cases. Given the seriousness of the disease and continual increase in patient numbers, developing effective therapies to treat AD has become urgent. Presently, the drugs available for AD treatment, including cholinesterase inhibitors and an antagonist of the N-methyl-D-aspartate receptor, can only inhibit dementia symptoms for a limited period of time but cannot stop or reverse disease progression. On the basis of the amyloid hypothesis, many global drug companies have conducted many clinical trials on amyloid clearing therapy but without success. Thus, the amyloid hypothesis may not be completely feasible. The number of anti-amyloid trials decreased in 2019, which might be a turning point. An in-depth and comprehensive understanding of the contribution of amyloid beta and other factors of AD is crucial for developing novel pharmacotherapies. In ongoing clinical trials, researchers have developed and are testing several possible interventions aimed at various targets, including anti-amyloid and anti-tau interventions, neurotransmitter modification, anti-neuroinflammation and neuroprotection interventions, and cognitive enhancement, and interventions to relieve behavioral psychological symptoms. In this article, we present the current state of clinical trials for AD at clinicaltrials.gov. We reviewed the underlying mechanisms of these trials, tried to understand the reason why prior clinical trials failed, and analyzed the future trend of AD clinical trials.},
author = {Huang, Li Kai and Chao, Shu Ping and Hu, Chaur Jong},
doi = {10.1186/s12929-019-0609-7},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Huang, Chao, Hu - 2020 - Clinical trials of new drugs for Alzheimer disease.pdf:pdf},
issn = {14230127},
journal = {J. Biomed. Sci.},
keywords = {Alzheimer disease,Anti-amyloid,Anti-tau,Clinical trials of drugs,Cognitive enhancement,Neuroinflammation,Neuroprotection},
mendeley-groups = {PhDThesis/Introduction},
month = {jan},
number = {1},
pages = {18},
pmid = {31906949},
publisher = {BioMed Central Ltd.},
title = {{Clinical trials of new drugs for Alzheimer disease}},
volume = {27},
year = {2020}
}

@article{Mehta2017,
abstract = {Introduction: There are dozens of drugs in development for AD with billions of dollars invested. Despite the massive investment in AD drugs and a burgeoning pipeline, there have been more setbacks and failures than treatment successes. Areas covered: The classes of drugs that have failed to date include the monoclonal antibodies, the gamma secretase inhibitors, dimebon, neurochemical enhancers, and one tau drug. Data for these compounds were sought through a PubMed search and a clinicaltrials.gov search. Expert opinion: The obvious question to be posed is: Why are they failing? Is the treatment of symptomatic dementia too late? Are the therapeutic targets incorrect? Are the clinical methodologies imprecise, misleading, or inaccurate? This review summarizes the drugs that have failed during 2010–2015 and offers possible theories as to why they have failed.},
author = {Mehta, Dev and Jackson, Robert and Paul, Gaurav and Shi, Jiong and Sabbagh, Marwan},
doi = {10.1080/13543784.2017.1323868},
issn = {17447658},
journal = {Expert Opin. Investig. Drugs},
keywords = {Alzheimer's,Amyloid,clinical trials,dimebon,monoclonal antibodies,secretase inhibitors},
mendeley-groups = {PhDThesis/Introduction},
month = {jun},
number = {6},
pages = {735--739},
pmid = {28460541},
publisher = {Taylor and Francis Ltd},
title = {{Why do trials for Alzheimer's disease drugs keep failing? A discontinued drug perspective for 2010-2015}},
volume = {26},
year = {2017}
}


@article{Ryan2016,
abstract = {Background The causes of phenotypic heterogeneity in familial Alzheimer's disease with autosomal dominant inheritance are not well understood. We aimed to characterise clinical phenotypes and genetic associations with APP and PSEN1 mutations in symptomatic autosomal dominant familial Alzheimer's disease (ADAD). Methods We retrospectively analysed genotypic and phenotypic data (age at symptom onset, initial cognitive or behavioural symptoms, and presence of myoclonus, seizures, pyramidal signs, extrapyramidal signs, and cerebellar signs) from all individuals with ADAD due to APP or PSEN1 mutations seen at the Dementia Research Centre in London, UK. We examined the frequency of presenting symptoms and additional neurological features, investigated associations with age at symptom onset, APOE genotype, and mutation position, and explored phenotypic differences between APP and PSEN1 mutation carriers. The proportion of individuals presenting with various symptoms was analysed with descriptive statistics, stratified by mutation type. Findings Between July 1, 1987, and Oct 31, 2015, age at onset was recorded for 213 patients (168 with PSEN1 mutations and 45 with APP mutations), with detailed history and neurological examination findings available for 121 (85 with PSEN1 mutations and 36 with APP mutations). We identified 38 different PSEN1 mutations (four novel) and six APP mutations (one novel). Age at onset differed by mutation, with a younger onset for individuals with PSEN1 mutations than for those with APP mutations (mean age 43{\textperiodcentered}6 years [SD 7{\textperiodcentered}2] vs 50{\textperiodcentered}4 years [SD 5{\textperiodcentered}2], respectively, p{\textless}0{\textperiodcentered}0001); within the PSEN1 group, 72{\%} of age at onset variance was explained by the specific mutation. A cluster of five mutations with particularly early onset (mean age at onset {\textless}40 years) involving PSEN1's first hydrophilic loop suggests critical functional importance of this region. 71 (84{\%}) individuals with PSEN1 mutations and 35 (97{\%}) with APP mutations presented with amnestic symptoms, making atypical cognitive presentations significantly more common in PSEN1 mutation carriers (n=14; p=0{\textperiodcentered}037). Myoclonus and seizures were the most common additional neurological features; individuals with myoclonus (40 [47{\%}] with PSEN1 mutations and 12 [33{\%}] with APP mutations) were significantly more likely to develop seizures (p=0{\textperiodcentered}001 for PSEN1; p=0{\textperiodcentered}036 for APP), which affected around a quarter of the patients in each group (20 [24{\%}] and nine [25{\%}], respectively). A number of patients with PSEN1 mutations had pyramidal (21 [25{\%}]), extrapyramidal (12 [14{\%}]), or cerebellar (three [4{\%}]) signs. Interpretation ADAD phenotypes are heterogeneous, with both age at onset and clinical features being influenced by mutation position as well as causative gene. This highlights the importance of considering genetic testing in young patients with dementia and additional neurological features in order to appropriately diagnose and treat their symptoms, and of examining different mutation types separately in future research. Funding Medical Research Council and National Institute for Health Research.},
author = {Ryan, Natalie S. and Nicholas, Jennifer M. and Weston, Philip S.J. and Liang, Yuying and Lashley, Tammaryn and Guerreiro, Rita and Adamson, Gary and Kenny, Janna and Beck, Jon and Chavez-Gutierrez, Lucia and de Strooper, Bart and Revesz, Tamas and Holton, Janice and Mead, Simon and Rossor, Martin N. and Fox, Nick C.},
doi = {10.1016/S1474-4422(16)30193-4},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Ryan et al. - 2016 - Clinical phenotype and genetic associations in autosomal dominant familial Alzheimer's disease a case series.pdf:pdf},
issn = {14744465},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis,PhDThesis/Introduction},
month = {dec},
number = {13},
pages = {1326--1335},
pmid = {27777022},
publisher = {Lancet Publishing Group},
title = {{Clinical phenotype and genetic associations in autosomal dominant familial Alzheimer's disease: a case series}},
volume = {15},
year = {2016}
}

@article{Shi2018,
abstract = {Blood-based biomarkers represent a less invasive and potentially cheaper approach for aiding Alzheimer's disease (AD) detection compared with cerebrospinal fluid and some neuroimaging biomarkers. Acknowledging that many in the field have made great progress, here we review some of the work that our group has pursued to identify and validate blood-based proteomic biomarkers through both case control and AD pathology endophenotype-based approaches. Our focus is primarily to identify a minimally invasive and hopefully cost-effective blood-based biomarker to reduce screen failure in clinical trials where participants have prodromal or even pre-clinical disease. We summarize some of the key findings and approaches taken in these biomarker studies, while addressing the main challenges, including that of limited replication in the field, and discuss opportunities for biomarker development.},
author = {Shi, Liu and Baird, Alison L. and Westwood, Sarah and Hye, Abdul and Dobson, Richard and Thambisetty, Madhav and Lovestone, Simon},
doi = {10.3233/JAD-170531},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Shi et al. - 2018 - A Decade of Blood Biomarkers for Alzheimer's Disease Research An Evolving Field, Improving Study Designs, and the Ch.pdf:pdf},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {Alzheimer's disease,blood proteomic biomarkers,endophenotype,replication,validation},
mendeley-groups = {Papers bib/cimlr{\_}extension,PhDThesis/Introduction},
number = {3},
pages = {1181--1198},
title = {{A Decade of Blood Biomarkers for Alzheimer's Disease Research: An Evolving Field, Improving Study Designs, and the Challenge of Replication}},
volume = {62},
year = {2018}
}

@article{TenKate2018,
abstract = {Alzheimer's disease is a heterogeneous disorder. Understanding the biological basis for this heterogeneity is key for developing personalized medicine. We identified atrophy subtypes in Alzheimer's disease dementia and tested whether these subtypes are already present in prodromal Alzheimer's disease and could explain interindividual differences in cognitive decline. First we retrospectively identified atrophy subtypes from structural MRI with a data-driven cluster analysis in three datasets of patients with Alzheimer's disease dementia: discovery data (dataset 1: n = 299, age = 67 8, 50{\%} female), and two independent external validation datasets (dataset 2: n = 181, age = 66 7, 52{\%} female; dataset 3: n = 227, age = 74 8, 44{\%} female). Subtypes were compared on clinical, cognitive and biological characteristics. Next, we classified prodromal Alzheimer's disease participants (n = 603, age = 72 8, 43{\%} female) according to the best matching subtype to their atrophy pattern, and we tested whether subtypes showed cognitive decline in specific domains. In all Alzheimer's disease dementia datasets we consistently identified four atrophy subtypes: (i) medial-temporal predominant atrophy with worst memory and language function, older age, lowest CSF tau levels and highest amount of vascular lesions; (ii) parieto-occipital atrophy with poor executive/attention and visuospatial functioning and high CSF tau; (iii) mild atrophy with best cognitive performance, young age, but highest CSF tau levels; and (iv) diffuse cortical atrophy with intermediate clinical, cognitive and biological features. Prodromal Alzheimer's disease participants classified into one of these subtypes showed similar subtype characteristics at baseline as Alzheimer's disease dementia subtypes. Compared across subtypes in prodromal Alzheimer's disease, the medial-temporal subtype showed fastest decline in memory and language over time; the parieto-occipital subtype declined fastest on executive/attention domain; the diffuse subtype in visuospatial functioning; and the mild subtype showed intermediate decline in all domains. Robust atrophy subtypes exist in Alzheimer's disease with distinct clinical and biological disease expression. Here we observe that these subtypes can already be detected in prodromal Alzheimer's disease, and that these may inform on expected trajectories of cognitive decline.},
author = {{Ten Kate}, Mara and Dicks, Ellen and Visser, Pieter Jelle and {Van Der Flier}, Wiesje M. and Teunissen, Charlotte E and Barkhof, Frederik and Scheltens, Philip and Tijms, Betty M},
doi = {10.1093/brain/awy264},
issn = {14602156},
journal = {Brain},
keywords = {Alzheimer's disease,Disease heterogeneity,Mild cognitive impairment,Non-negative matrix factorization,Prognosis},
mendeley-groups = {PhDThesis/Relevant papers},
month = {dec},
number = {12},
pages = {3443--3456},
pmid = {30351346},
publisher = {Oxford University Press},
title = {{Atrophy subtypes in prodromal Alzheimer's disease are associated with cognitive decline}},
volume = {141},
year = {2018}
}

@article{Emrani2020,
abstract = {Possession of the $\epsilon$4 allele of apolipoprotein E (APOE) is the primary genetic risk factor for the sporadic form of Alzheimer's disease (AD). While researchers have extensively characterized the impact that APOE $\epsilon$4 (APOE4) has on the susceptibility of AD, far fewer studies have investigated the phenotypic differences of patients with AD who are APOE4 carriers vs. those who are non-carriers. In order to understand these differences, we performed a qualitative systematic literature review of the reported cognitive and pathological differences between APOE4-positive (APOE4+) vs. APOE4-negative (APOE4−) AD patients. The studies performed on this topic to date suggest that APOE4 is not only an important mediator of AD susceptibility, but that it likely confers specific phenotypic heterogeneity in AD presentation, as well. Specifically, APOE4+ AD patients appear to possess more tau accumulation and brain atrophy in the medial temporal lobe, resulting in greater memory impairment, compared to APOE4− AD patients. On the other hand, APOE4− AD patients appear to possess more tau accumulation and brain atrophy in the frontal and parietal lobes, resulting in greater impairment in executive function, visuospatial abilities, and language, compared to APOE4+ AD patients. Although more work is necessary to validate and interrogate these findings, these initial observations of pathological and cognitive heterogeneity between APOE4+ vs. APOE4− AD patients suggest that there is a fundamental divergence in AD manifestation related to APOE genotype, which may have important implications in regard to the therapeutic treatment of these two patient populations.},
author = {Emrani, Sheina and Arain, Hirra A. and DeMarshall, Cassandra and Nuriel, Tal},
doi = {10.1186/s13195-020-00712-4},
issn = {17589193},file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Emrani et al. - 2020 - APOE4 is associated with cognitive and pathological heterogeneity in patients with Alzheimer's disease a systemat.pdf:pdf},

journal = {Alzheimer's Res. Ther.},
keywords = {AD,APOE,APOE4,Alzheimer's disease,Apolipoprotein E,Heterogeneity},
mendeley-groups = {PhDThesis/Relevant papers},
month = {dec},
number = {1},
pages = {1--19},
pmid = {33148345},
publisher = {BioMed Central Ltd},
title = {{APOE4 is associated with cognitive and pathological heterogeneity in patients with Alzheimer's disease: a systematic review}},
volume = {12},
year = {2020}
}


@article{Karikari2020a,
abstract = {Whilst cerebrospinal fluid (CSF) and positron emission tomography (PET) biomarkers for amyloid-$\beta$ (A$\beta$) and tau pathologies are accurate for the diagnosis of Alzheimer's disease (AD), their broad implementation in clinical and trial settings are restricted by high cost and limited accessibility. Plasma phosphorylated-tau181 (p-tau181) is a promising blood-based biomarker that is specific for AD, correlates with cerebral A$\beta$ and tau pathology, and predicts future cognitive decline. In this study, we report the performance of p-tau181 in {\textgreater}1000 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI), including cognitively unimpaired (CU), mild cognitive impairment (MCI) and AD dementia patients characterized by A$\beta$ PET. We confirmed that plasma p-tau181 is increased at the preclinical stage of Alzheimer and further increases in MCI and AD dementia. Individuals clinically classified as AD dementia but having negative A$\beta$ PET scans show little increase but plasma p-tau181 is increased if CSF A$\beta$ has already changed prior to A$\beta$ PET changes. Despite being a multicenter study, plasma p-tau181 demonstrated high diagnostic accuracy to identify AD dementia (AUC = 85.3{\%}; 95{\%} CI, 81.4–89.2{\%}), as well as to distinguish between A$\beta$− and A$\beta$+ individuals along the Alzheimer's continuum (AUC = 76.9{\%}; 95{\%} CI, 74.0–79.8{\%}). Higher baseline concentrations of plasma p-tau181 accurately predicted future dementia and performed comparably to the baseline prediction of CSF p-tau181. Longitudinal measurements of plasma p-tau181 revealed low intra-individual variability, which could be of potential benefit in disease-modifying trials seeking a measurable response to a therapeutic target. This study adds significant weight to the growing body of evidence in the use of plasma p-tau181 as a non-invasive diagnostic and prognostic tool for AD, regardless of clinical stage, which would be of great benefit in clinical practice and a large cost-saving in clinical trial recruitment.},
author = {Karikari, Thomas K and Benedet, Andr{\'{e}}a L and Ashton, Nicholas J and {Lantero Rodriguez}, Juan and Snellman, Anniina and Su{\'{a}}rez-Calvet, Marc and Saha-Chaudhuri, Paramita and Lussier, Firoza and Kvartsberg, Hlin and Rial, Alexis Moscoso and Pascoal, Tharick A and Andreasson, Ulf and Sch{\"{o}}ll, Michael and Weiner, Michael W and Rosa-Neto, Pedro and Trojanowski, John Q and Shaw, Leslie M and Blennow, Kaj and Zetterberg, Henrik and Initiative, for the Alzheimer's Disease Neuroimaging},
doi = {10.1038/s41380-020-00923-z},
issn = {1476-5578},
journal = {Mol. Psychiatry},
mendeley-groups = {PhDThesis/Introduction},
title = {{Diagnostic performance and prediction of clinical progression of plasma phospho-tau181 in the Alzheimer's Disease Neuroimaging Initiative}},
year = {2020}
}

@article{Tijms2020,
abstract = {Alzheimer's disease is biologically heterogeneous, and detailed understanding of the processes involved in patients is critical for development of treatments. CSF contains hundreds of proteins, with concentrations reflecting ongoing (patho)physiological processes. This provides the opportunity to study many biological processes at the same time in patients. We studied whether Alzheimer's disease biological subtypes can be detected in CSF proteomics using the dual clustering technique non-negative matrix factorization. In two independent cohorts (EMIF-AD MBD and ADNI) we found that 705 (77{\%} of 911 tested) proteins differed between Alzheimer's disease (defined as having abnormal amyloid, n = 425) and controls (defined as having normal CSF amyloid and tau and normal cognition, n = 127). Using these proteins for data-driven clustering, we identified three robust pathophysiological Alzheimer's disease subtypes within each cohort showing (i) hyperplasticity and increased BACE1 levels; (ii) innate immune activation; and (iii) blood–brain barrier dysfunction with low BACE1 levels. In both cohorts, the majority of individuals were labelled as having subtype 1 (80, 36{\%} in EMIF-AD MBD; 117, 59{\%} in ADNI), 71 (32{\%}) in EMIF-AD MBD and 41 (21{\%}) in ADNI were labelled as subtype 2, and 72 (32{\%}) in EMIF-AD MBD and 39 (20{\%}) individuals in ADNI were labelled as subtype 3. Genetic analyses showed that all subtypes had an excess of genetic risk for Alzheimer's disease (all P {\textgreater} 0.01). Additional pathological comparisons that were available for a subset in ADNI suggested that subtypes showed similar severity of Alzheimer's disease pathology, and did not differ in the frequencies of co-pathologies, providing further support that found subtypes truly reflect Alzheimer's disease heterogeneity. Compared to controls, all non-demented Alzheimer's disease individuals had increased risk of showing clinical progression (all P {\textless} 0.01). Compared to subtype 1, subtype 2 showed faster clinical progression after correcting for age, sex, level of education and tau levels (hazard ratio = 2.5; 95{\%} confidence interval = 1.2, 5.1; P = 0.01), and subtype 3 at trend level (hazard ratio = 2.1; 95{\%} confidence interval = 1.0, 4.4; P = 0.06). Together, these results demonstrate the value of CSF proteomics in studying the biological heterogeneity in Alzheimer's disease patients, and suggest that subtypes may require tailored therapy.},
author = {Tijms, Betty M and Gobom, Johan and Reus, Lianne and Jansen, Iris and Hong, Shengjun and Dobricic, Valerija and Kilpert, Fabian and ten Kate, Mara and Barkhof, Frederik and Tsolaki, Magda and Verhey, Frans R J and Popp, Julius and Martinez-Lage, Pablo and Vandenberghe, Rik and Lle{\'{o}}, Alberto and Molinuevo, Jos{\'{e}} Lu{\'{i}}s and Engelborghs, Sebastiaan and Bertram, Lars and Lovestone, Simon and Streffer, Johannes and Vos, Stephanie and Bos, Isabelle and (ADNI), The Alzheimer's Disease Neuroimaging Initiative and Blennow, Kaj and Scheltens, Philip and Teunissen, Charlotte E and Zetterberg, Henrik and Visser, Pieter Jelle},
doi = {10.1093/brain/awaa325},
issn = {0006-8950},
journal = {Brain},
mendeley-groups = {PhDThesis/Introduction},
month = {nov},
title = {{Pathophysiological subtypes of Alzheimer's disease based on cerebrospinal fluid proteomics}},
year = {2020}
}


@article{Lam2013,
abstract = {With increasing knowledge of clinical in vivo biomarkers and the pathological intricacies of Alzheimer's disease (AD), nosology is evolving. Harmonized consensus criteria that emphasize prototypic illness continue to develop to achieve diagnostic clarity for treatment decisions and clinical trials. However, it is clear that AD is clinically heterogeneous in presentation and progression, demonstrating variable topographic distributions of atrophy and hypometabolism/hypoperfusion. AD furthermore often keeps company with other conditions that may further nuance clinical expression, such as synucleinopathy exacerbating executive and visuospatial dysfunction and vascular pathologies (particularly small vessel disease that is increasingly ubiquitous with human aging) accentuating frontal-dysexecutive symptomatology. That some of these atypical clinical patterns recur may imply the existence of distinct AD variants. For example, focal temporal lobe dysfunction is associated with a pure amnestic syndrome, very slow decline, with atrophy and neurofibrillary tangles limited largely to the medial temporal region including the entorhinal cortex. Left parietal atrophy and/or hypometabolism/hypoperfusion are associated with language symptoms, younger age of onset, and faster rate of decline - a potential 'language variant' of AD. Conversely, the same pattern but predominantly affecting the right parietal lobe is associated with a similar syndrome but with visuospatial symptoms replacing impaired language function. Finally, the extremely rare frontal variant is associated with executive dysfunction out of keeping with degree of memory decline and may have prominent behavioural symptoms. Genotypic differences may underlie some of these subtypes; for example, absence of apolipoprotein E e4 is often associated with atypicality in younger onset AD. Understanding the mechanisms behind this variability merits further investigation, informed by recent advances in imaging techniques, biomarker assays, and quantitative pathological methods, in conjunction with standardized clinical, functional, neuropsychological and neurobehavioral evaluations. Such an understanding is needed to facilitate 'personalized AD medicine', and eventually allow for clinical trials targeting specific AD subtypes. Although the focus legitimately remains on prototypic illness, continuing efforts to develop disease-modifying therapies should not exclude the rarer AD subtypes and common comorbid presentations, as is currently often the case. Only by treating them as well can we address the full burden of this devastating dementia syndrome. {\textcopyright} 2013 BioMed Central Ltd.},
author = {Lam, Benjamin and Masellis, Mario and Freedman, Morris and Stuss, Donald T and Black, Sandra E},
doi = {10.1186/alzrt155},
file = {::},
issn = {1758-9193},
journal = {Alzheimers. Res. Ther.},
keywords = {Geriatric Psychiatry,Geriatrics/Gerontology,Neurology,Neurosciences},
mendeley-groups = {PhDThesis/Introduction},
month = {jan},
number = {1},
pages = {1},
publisher = {BioMed Central},
title = {{Clinical, imaging, and pathological heterogeneity of the Alzheimer's disease syndrome}},
volume = {5},
year = {2013}
}


@article{Poulakis2018,
abstract = {There is increasing evidence showing that brain atrophy varies between patients with Alzheimer's disease (AD), suggesting that different anatomical patterns might exist within the same disorder. We investigated AD heterogeneity based on cortical and subcortical atrophy patterns in 299 AD subjects from 2 multicenter cohorts. Clusters of patients and important discriminative features were determined using random forest pairwise similarity, multidimensional scaling, and distance-based hierarchical clustering. We discovered 2 typical (72.2{\%}) and 3 atypical (28.8{\%}) subtypes with significantly different demographic, clinical, and cognitive characteristics, and different rates of cognitive decline. In contrast to previous studies, our unsupervised random forest approach based on cortical and subcortical volume measures and their linear and nonlinear interactions revealed more typical AD subtypes with important anatomically discriminative features, while the prevalence of atypical cases was lower. The hippocampal-sparing and typical AD subtypes exhibited worse clinical progression in visuospatial, memory, and executive cognitive functions. Our findings suggest there is substantial heterogeneity in AD that has an impact on how patients function and progress over time.},
author = {Poulakis, Konstantinos and Pereira, Joana B. and Mecocci, Patrizia and Vellas, Bruno and Tsolaki, Magda and K{\l}oszewska, Iwona and Soininen, Hilkka and Lovestone, Simon and Simmons, Andrew and Wahlund, Lars Olof and Westman, Eric},
doi = {10.1016/j.neurobiolaging.2018.01.009},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Poulakis et al. - 2018 - Heterogeneous patterns of brain atrophy in Alzheimer's disease.pdf:pdf},
issn = {15581497},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Cluster analyses,Cortical volumes,Random forest similarity,Structural magnetic resonance imaging,Subcortical volumes},
mendeley-groups = {PhDThesis/Introduction},
month = {may},
pages = {98--108},
pmid = {29455029},
publisher = {Elsevier Inc.},
title = {{Heterogeneous patterns of brain atrophy in Alzheimer's disease}},
volume = {65},
year = {2018}
}



@book{Bird1993,
abstract = {The purpose of this overview is to increase the awareness of clinicians regarding Alzheimer disease (AD) and its genetic causes and management. The following are the goals of this overview. GOAL 1: Describe the clinical characteristics of AD. GOAL 2: Review the genetic causes of AD. GOAL 3: Provide an evaluation strategy to identify the genetic cause of AD in a proband (when possible). GOAL 4: Inform genetic counseling of family members of an individual with AD.},
author = {Bird, Thomas D},
booktitle = {GeneReviews{\textregistered}},
keywords = {1,2,APOE,APP,Alzheimer Disease,Amyloid,Apolipoprotein E,Early,Late,Onset Familial Alzheimer Disease,Overview,PSEN1,PSEN2,Presenilin,beta precursor protein},
mendeley-groups = {PhDThesis/Introduction},
month = {dec},
pmid = {20301340},
publisher = {University of Washington, Seattle},
title = {{Alzheimer Disease Overview}},
year = {1993}
}

@misc{AlzheimersAssociation,
annote = {Accessed: 2018-04-12},
author = {{Alzheimer's Association}},
mendeley-groups = {PhDThesis/Hippo},
title = {{Alzheimer's Dementia: Global Resources}},
url ={https://www.alz.org/global/},
year = {2018}
}

@article{Moreno-Jimenez2019,
abstract = {The hippocampus is one of the most affected areas in Alzheimer's disease (AD)1. Moreover, this structure hosts one of the most unique phenomena of the adult mammalian brain, namely, the addition of new neurons throughout life2. This process, called adult hippocampal neurogenesis (AHN), confers an unparalleled degree of plasticity to the entire hippocampal circuitry3,4. Nonetheless, direct evidence of AHN in humans has remained elusive. Thus, determining whether new neurons are continuously incorporated into the human dentate gyrus (DG) during physiological and pathological aging is a crucial question with outstanding therapeutic potential. By combining human brain samples obtained under tightly controlled conditions and state-of-the-art tissue processing methods, we identified thousands of immature neurons in the DG of neurologically healthy human subjects up to the ninth decade of life. These neurons exhibited variable degrees of maturation along differentiation stages of AHN. In sharp contrast, the number and maturation of these neurons progressively declined as AD advanced. These results demonstrate the persistence of AHN during both physiological and pathological aging in humans and provide evidence for impaired neurogenesis as a potentially relevant mechanism underlying memory deficits in AD that might be amenable to novel therapeutic strategies.},
author = {Moreno-Jim{\'{e}}nez, Elena P and Flor-Garc{\'{i}}a, Miguel and Terreros-Roncal, Julia and R{\'{a}}bano, Alberto and Cafini, Fabio and Pallas-Bazarra, Noem{\'{i}} and {\'{A}}vila, Jes{\'{u}}s and Llorens-Mart{\'{i}}n, Mar{\'{i}}a},
doi = {10.1038/s41591-019-0375-9},
issn = {1078-8956},
journal = {Nat. Med.},
keywords = {Adult neurogenesis,Alzheimer's disease},
mendeley-groups = {PhDThesis/Hippo},
month = {mar},
pages = {1},
publisher = {Nature Publishing Group},
title = {{Adult hippocampal neurogenesis is abundant in neurologically healthy subjects and drops sharply in patients with Alzheimer's disease}},
year = {2019}
}
@article{Lind2006,
abstract = {Apolipoprotein E $\varepsilon$4 (APOE $\varepsilon$4) is the main known genetic risk factor for Alzheimer's disease (AD). Some previous studies have reported structural brain changes as well as cognitive deficits in non-demented APOE $\varepsilon$4 carriers, but the pattern of results is inconsistent and studies with larger sample sizes have been called for. Here we compared hippocampal volume and recognition–memory performance between AD-symptom-free carriers (N=30) and non-carriers (N=30) of the APOE $\varepsilon$4 (age range: 49–79 years). We observed reduced right hippocampal volume in APOE $\varepsilon$4 carriers, and found that the difference was most pronounced before the age of 65. Further, the APOE $\varepsilon$4 carriers made significantly more false alarms in the recognition–memory test, and the number of false alarms correlated significantly with right hippocampus volume. These results indicate that relatively young individuals at genetic risk for AD have smaller hippocampal volume and lower performance on hippocampal-dependent cognitive tasks. A question for the future is whether smaller hippocampal volume represents early-onset hippocampal volume reduction or an inherent trait.},
author = {Lind, Johanna and Larsson, Anne and Persson, Jonas and Ingvar, Martin and Nilsson, Lars-G{\"{o}}ran and B{\"{a}}ckman, Lars and Adolfsson, Rolf and Cruts, Marc and Sleegers, Kristel and {Van Broeckhoven}, Christine and Nyberg, Lars},
doi = {10.1016/J.NEULET.2005.11.070},
issn = {0304-3940},
journal = {Neurosci. Lett.},
mendeley-groups = {PhDThesis/Hippo},
month = {mar},
number = {1},
pages = {23--27},
publisher = {Elsevier},
title = {{Reduced hippocampal volume in non-demented carriers of the apolipoprotein $\varepsilon$4: Relation to chronological age and recognition memory}},
volume = {396},
year = {2006}
}
@article{Mueller2008,
abstract = {BACKGROUND Details of the internal hippocampal structure visible at 4 T allow for in vivo volumetry of subfields. The aims of this study were: 1. To determine if Apo e4 has subfield specific effects in controls. 2. To study the influence of Apo e4 on hippocampal subfields in AD. METHODS 81 subjects (66 controls, mean age 60.8+/-13.6, range: 28-85 years), and 15 AD (mean age 67.5+/-9.3) were studied. Entorhinal cortex, subiculum, CA1, CA1-CA2 transition zone, CA3-4 and dentate gyrus (CA3{\&}DG) and total hippocampal volume were determined using a manual marking strategy. RESULTS Significant effects for Apo e4 on the CA3{\&}DG were found in the total control population (p=0.042) and in older controls (61-85 years) (p=0.036) but not in younger (28-60 years) controls. Significant effects for Apo e4 (p=0.0035) on CA3{\&}DG were also found in a subgroup of older subjects and AD subjects. AD with Apo e4 had smaller CA3{\&}DG than AD without Apo e4 (p=0.027). CONCLUSIONS These findings suggest that Apo e4 exerts a regionally selective effect on CA3{\&}DG in normal aging and AD.},
author = {Mueller, S G and Schuff, N and Raptentsetsang, S and Elman, J and Weiner, M W},
doi = {10.1016/j.neuroimage.2008.04.174},
issn = {1095-9572},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pages = {42--48},
pmid = {18534867},
publisher = {NIH Public Access},
title = {{Selective effect of Apo e4 on CA3 and dentate in normal aging and Alzheimer's disease using high resolution MRI at 4 T.}},
volume = {42},
year = {2008}
}
@article{Pievani2011,
abstract = {Prior studies reported that the hippocampal volume is smaller in Alzheimer's disease patients carrying the Apolipoprotein E $\epsilon$4 allele (APOE4) versus patients who are non-carriers of this allele. This effect however has not been detected consistently, possibly because of the regionally-specific involvement of the hippocampal formation in Alzheimer's disease. The aim of this study was to analyze the local effect of APOE4 on hippocampal atrophy in Alzheimer's disease patients. Using high-resolution T1-weighted images we investigated 14 patients heterozygous for the $\epsilon$4 allele (age 72 ± 8. SD years; MMSE 20 ± 4. SD) and 14 patients not carrying the $\epsilon$4 allele (age 71 ± 10; MMSE 20 ± 5. SD), and 28 age-, sex-, and education-matched controls (age 71 ± 8; MMSE 29 ± 1. SD). The hippocampal formation was outlined with manual tracing and 3D parametric surface models were created for each subject. Radial atrophy was assessed on the whole hippocampal surface using the UCLA mapping technique. E4 carriers and non-carriers did not differ in their level of impairment in global cognition (p =0.91, Mann-Whitney test) or memory (p {\textgreater}0.29). Hippocampal surface analysis showed the typical pattern of CA1 and subicular tissue atrophy in both $\epsilon$4-carriers and non-carriers compared with controls (e4 carriers: p {\textless}0.0002; $\epsilon$4 non-carriers: p {\textless}0.01, permutation test). The left hippocampal volume was significantly smaller in $\epsilon$4-carriers than non-carriers (p =0.044, Mann-Whitney test), the effect of APOE4 mapping to the subicular/CA1 region (p =0.041, permutation test). Differences were not statistically significant in the right hippocampus (p {\textgreater}0.20, permutation test). These findings show that hippocampal atrophy is greater in APOE4 carriers in regions typically affected by pathology. APOE4 may affect the structural expression of Alzheimer's disease. {\textcopyright}2011 Elsevier Inc.},
author = {Pievani, Michela and Galluzzi, Samantha and Thompson, Paul M and Rasser, Paul E and Bonetti, Matteo and Frisoni, Giovanni B},
doi = {10.1016/j.neuroimage.2010.12.081},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer disease,Apolipoprotein E,Hippocampal surface,MRI},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {909--919},
pmid = {21224004},
publisher = {Academic Press},
title = {{APOE4 is associated with greater atrophy of the hippocampal formation in Alzheimer's disease}},
volume = {55},
year = {2011}
}
@article{ODwyer2012,
abstract = {The E4 allele of the ApoE gene has consistently been shown to be related to an increased risk of Alzheimer's disease (AD). The E4 allele is also associated with functional and structural grey matter (GM) changes in healthy young, middle-aged and older subjects. Here, we assess volumes of deep grey matter structures of 22 healthy younger ApoE4 carriers and 22 non-carriers (20-38 years). Volumes of the nucleus accumbens, amygdala, caudate nucleus, hippocampus, pallidum, putamen, thalamus and brain stem were calculated by FMRIB's Integrated Registration and Segmentation Tool (FIRST) algorithm. A significant drop in volume was found in the right hippocampus of ApoE4 carriers (ApoE4+) relative to non-carriers (ApoE4-), while there was a borderline significant decrease in the volume of the left hippocampus of ApoE4 carriers. The volumes of no other structures were found to be significantly affected by genotype. Atrophy has been found to be a sensitive marker of neurodegenerative changes, and our results show that within a healthy young population, the presence of the ApoE4+ carrier gene leads to volume reduction in a structure that is vitally important for memory formation. Our results suggest that the hippocampus may be particularly vulnerable to further degeneration in ApoE4 carriers as they enter middle and old age. Although volume reductions were noted bilaterally in the hippocampus, atrophy was more pronounced in the right hippocampus. This finding relates to previous work which has noted a compensatory increase in right hemisphere activity in ApoE4 carriers in response to preclinical declines in memory function. Possession of the ApoE4 allele may lead to greater predilection for right hemisphere atrophy even in healthy young subjects in their twenties.},
author = {O'Dwyer, Laurence and Lamberton, Franck and Matura, Silke and Tanner, Colby and Scheibe, Monika and Miller, Julia and Rujescu, Dan and Prvulovic, David and Hampel, Harald},
doi = {10.1371/journal.pone.0048895},
editor = {Stamatakis, Emmanuel Andreas},
isbn = {1932-6203},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Hippo},
month = {nov},
number = {11},
pages = {e48895},
pmid = {23152815},
publisher = {Public Library of Science},
title = {{Reduced Hippocampal Volume in Healthy Young ApoE4 Carriers: An MRI Study}},
volume = {7},
year = {2012}
}
@inproceedings{Chetelat2013,
abstract = {The E4 allele of the apolipoprotein E (APOE4) is the major known genetic risk factor for Alzheimer's disease (AD), with a dramatic increase in the risk of developing AD as the number of APOE4 alleles increases from 0 to 2. For this reason, asymptomatic APOE4 carriers as a group offer a great opportunity to search for the presence of early biomarkers for AD. The present article reviews neuroimaging studies on APOE4 carriers, focusing on cognitively normal individuals and on the main neuroimaging biomarkers for AD, i.e. atrophy with structural MRI, hypometabolism with FDG-PET, and amyloid deposition with amyloid-PET imaging. State of the art There are a great number of studies on the effect of APOE4 on brain structures, and they tend to show significant atrophy in APOE4 carriers compared to non-carriers especially in regions susceptible to AD pathology such as the hippocampus. However, results are rather discrepant which suggests that the effect of APOE4 on brain structure is subtle. As for FDG-PET metabolism, the few available studies show decreased metabolism, again especially in AD-sensitive regions such as posterior associative parietal areas, with a dose-dependent effect (i.e. worsening as the number of APOE4 alleles increases). Finally, there is a unanimous and major effect of APOE4 on amyloid deposition with an increase in A$\beta$ load as the number of APOE4 alleles increases and a decrease in the age of predicted amyloid-positivity in APOE4 carriers. This graded effect of APOE4 on atrophy, hypometabolism, and amyloid deposition is consistent with multimodal neuroimaging studies suggestive of a predominant effect of APOE4 on amyloid rather than tau-related injury and on brain metabolism rather than brain structure. Neuroimaging studies also suggest that APOE4 effects may be mediated by both A$\beta$-dependent and A$\beta$-independent pathological processes. This contradicts the view that A$\beta$ pathology is a necessary upstream event to neuronal injury in AD. Perspectives and conclusion Future studies should tell whether the mechanisms and sequences evidenced in carriers are comparable to those found in non-carriers, but it is likely that APOE4 not only influences the risk for AD, but also modulates the pathophysiological cascade. Altogether, APOE4 carriers offer a great opportunity to investigate brain changes in the asymptomatic stages of AD and to further our understanding of the pathophysiology of the disease, although precaution is needed for interpretation in AD at large. {\textcopyright}2013 Elsevier Masson SAS.},
author = {Ch{\'{e}}telat, G and Fouquet, M},
booktitle = {Rev. Neurol. (Paris).},
doi = {10.1016/j.neurol.2013.07.025},
isbn = {0035-3787},
issn = {00353787},
keywords = {Amyloid PET imaging,Apolipoprotein E4,Atrophy,Early diagnosis,FDG-PET,Preclinical stage,Structural MRI},
mendeley-groups = {PhDThesis/Hippo},
month = {oct},
pages = {729--736},
pmid = {24016463},
publisher = {Elsevier Masson},
title = {{Neuroimaging biomarkers for Alzheimer's disease in asymptomatic APOE4 carriers}},
volume = {169},
year = {2013}
}
@article{Sanroma2014,
abstract = {Recently, multiple-atlas segmentation (MAS) has achieved a great success in the medical imaging area. The key assumption is that multiple atlases have greater chances of correctly labeling a target image than a single atlas. However, the problem of atlas selection still remains unexplored. Traditionally, image similarity is used to select a set of atlases. Unfortunately, this heuristic criterion is not necessarily related to the final segmentation performance. To solve this seemingly simple but critical problem, we propose a learning-based atlas selection method to pick up the best atlases that would lead to a more accurate segmentation. Our main idea is to learn the relationship between the pairwise appearance of observed instances (i.e., a pair of atlas and target images) and their final labeling performance (e.g., using the Dice ratio). In this way, we select the best atlases based on their expected labeling accuracy. Our atlas selection method is general enough to be integrated with any existing MAS method. We show the advantages of our atlas selection method in an extensive experimental evaluation in the ADNI, SATA, IXI, and LONI LPBA40 datasets. As shown in the experiments, our method can boost the performance of three widely used MAS methods, outperforming other learning-based and image-similarity-based atlas selection methods.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Sanroma, Gerard and Wu, Guorong and Gao, Yaozong and Shen, Dinggang},
doi = {10.1109/TMI.2014.2327516},
eprint = {NIHMS150003},
isbn = {2122633255},
issn = {1558254X},
journal = {IEEE Trans. Med. Imaging},
keywords = {Atlas selection,feature selection,multi-atlas based segmentation,support vector machine (SVM) rank},
mendeley-groups = {PhDThesis/Hippo},
number = {10},
pages = {1939--1953},
pmid = {24893367},
title = {{Learning to rank atlases for multiple-atlas segmentation}},
volume = {33},
year = {2014}
}
@article{Zhao2019,
abstract = {Background: The hippocampus and hippocampal subfields have been found to be diversely affected in Alzheimer's Disease (AD) and early stages of Alzheimer's disease by neuroimaging studies. However, our knowledge is still lacking about the trajectories of the hippocampus and hippocampal subfields atrophy with the progression of Alzheimer's disease. Objective: To identify which subfields of the hippocampus differ in the trajectories of Alzheimer's disease by magnetic resonance imaging (MRI) and to determine whether individual differences on memory could be explained by structural volumes of hippocampal subfields. Methods: Four groups of participants including 41 AD patients, 43 amnestic mild cognitive impairment (aMCI) patients, 35 subjective cognitive decline (SCD) patients and 42 normal controls (NC) received their structural MRI brain scans. Structural MR images were processed by the FreeSurfer 6.0 image analysis suite to extract the hippocampus and its subfields. Furthermore, we investigated relationships between hippocampal subfield volumes and memory test variables (AVLT-immediate recall, AVLT-delayed recall, AVLT-recognition) and the regression model analyses were controlled for age, gender, education and eTIV. Results: CA1, subiculum, presubiculum, molecular layer and fimbria showed the trend toward significant volume reduction among four groups with the progression of Alzheimer's disease. Volume of left subiculum was most strongly and actively correlated with performance across AVLT measures. Conclusion: The trend changes in the hippocampus subfields and further illustrates that SCD is the preclinical stage of AD earlier than aMCI. Future studies should aim to associate the atrophy of the hippocampal subfields in SCD with possible conversion to aMCI or AD with longitudinal design.},
author = {Zhao, Weina and Wang, Xuetong and Yin, Changhao and He, Mengfei and Li, Shuyu and Han, Ying},
doi = {10.3389/fninf.2019.00013},
issn = {16625196},
journal = {Front. Neuroinform.},
keywords = {Alzheimer's disease,Amnestic mild cognitive impairment,Hippocampal subfields,Magnetic resonance imaging,Subjective cognitive decline},
mendeley-groups = {PhDThesis/Hippo},
number = {March},
pages = {1--9},
title = {{Trajectories of the hippocampal subfields atrophy in the Alzheimer's Disease: A structural imaging study}},
volume = {13},
year = {2019}
}
@article{Iglesias2015,
author = {Iglesias, Juan Eugenio and Augustinack, Jean C and Nguyen, Khoa and Player, Christopher M and Player, Allison and Wright, Michelle and Roy, Nicole and Frosch, Matthew P},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Hippo},
pages = {115--137},
title = {{A computational atlas of the hippocampal formation using ex vivo, ultra-high resolution MRI}},
year = {2015}
}
@article{Fouquet2014,
abstract = {The $\epsilon$4 allele of the apolipoprotein E (APOE4) is associated with an increased risk of developing Alzheimer's disease (AD). Hence, several studies have compared the brain characteristics of APOE4 carriers versus non-carriers in presymptomatic stages to determine early AD biomarkers. The present review provides an overview on APOE4-related brain changes in cognitively normal individuals, focusing on the main neuroimaging biomarkers for AD, i.e. cortical beta-amyloid (A$\beta$) deposition, hypometabolism and atrophy. The most consistent findings are observed with A$\beta$ deposition as most studies report significantly higher cortical A$\beta$ load in APOE4 carriers compared with non-carriers. Fluorodeoxyglucose-positron emission tomography studies are rare and tend to show hypometabolism in brain regions typically impaired in AD. Structural magnetic resonance imaging findings are the most numerous and also the most discrepant, showing atrophy in AD-sensitive regions in some studies but contradicting results as well. Altogether, this suggests a graded effect of APOE4, with a predominant effect on A$\beta$ over brain structure and metabolism. Multimodal studies confirm this view and also suggest that APOE4 effects on brain structure and function are mediated by both A$\beta$-dependent and A$\beta$-independent pathological processes. Neuroimaging studies on asymptomatic APOE4 carriers offer relevant information to the understanding of early pathological mechanisms of the disease, although caution is needed as to whether APOE4 effects reflect AD pathological processes, and are representative of these effects in non-carriers.},
author = {Fouquet, Marine and Besson, Florent L and Gonneaud, Julie and {La Joie}, Renaud and Ch{\'{e}}telat, Ga{\"{e}}l},
doi = {10.1007/s11065-014-9263-8},
isbn = {1573-6660 (Electronic)$\backslash$r1040-7308 (Linking)},
issn = {15736660},
journal = {Neuropsychol. Rev.},
keywords = {Aging,Amyloid PET imaging,Apolipoprotein $\epsilon$4,FDG-PET,Preclinical stage,Structural MRI},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {290--299},
pmid = {25146994},
publisher = {Springer US},
title = {{Imaging Brain Effects of APOE4 in Cognitively Normal Individuals Across the Lifespan}},
volume = {24},
year = {2014}
}
@article{Mueller2009,
abstract = {Histopathological studies and animal models suggest that different physiological and pathophysiological processes exert different subfield specific effects on the hippocampus. High-resolution images at 4T depict details of the internal structure of the hippocampus allowing for in vivo volumetry of hippocampal subfields. The aims of this study were (1) to determine patterns of hippocampal subfield volume loss due to normal aging and Apo e4 carrier state, (2) to determine subfield specific volume losses due to preclinical (MCI) and clinical Alzheimer's disease (AD) and their modification due to age and Apo e4 carrier state. One hundred fifty seven subjects (119 cognitively healthy elderly controls, 20 MCI and 18 AD) were studied with a high resolution T2 weighted imaging sequence obtained at 4T aimed at the hippocampus. Apo e4 carrier state was known in 95 subjects (66 controls, 14 MCI, 15 AD). Subiculum (SUB), CA1, CA1-CA2 transition zone (CA1-2 transition), CA3- dentate gyrus (CA3{\&}DG) were manually marked. Multiple linear regression analysis was used to test for effects of age, Apo e4 carrier state and effects of MCI and AD on different hippocampal subfields. Age had a significant negative effect on CA1 and CA3{\&}DG volumes in controls (P {\textless}0.05). AD had significantly smaller volumes of SUB, CA1, CA1-2 transition, and MCI had smaller CA1-2 transition volumes than controls (P {\textless}0.05). Apo e4 carrier state was associated with volume loss in CA3{\&}DG compared to non-Apo e4 carriers in healthy controls and AD. Based on these findings, we conclude that subfield volumetry provides regional selective information that allows to distinguish between different normal and pathological processes affecting the hippocampus and thus for an improved differential diagnosis of neurodegenerative diseases affecting the hippocampus.},
author = {Mueller, Susanne G and Weiner, Michael W},
doi = {10.1002/hipo.20614},
isbn = {1098-1063 (Electronic)$\backslash$n1050-9631 (Linking)},
issn = {10509631},
journal = {Hippocampus},
keywords = {CA1,Dentate,MCI,Neurodegeneration,Volumetry},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {6},
pages = {558--564},
pmid = {19405132},
publisher = {John Wiley {\&} Sons, Ltd},
title = {{Selective effect of age, Apo e4, and Alzheimer's disease on hippocampal subfields}},
volume = {19},
year = {2009}
}
@article{Csernansky2005,
abstract = {Structural deformity of the hippocampus is characteristic of individuals with very mild and mild forms of dementia of the Alzheimer type (DAT). The purpose of this study was to determine whether a similar deformity of the hippocampus can predict the onset of dementia in nondemented elders. Using high dimensional diffeomorphic transformations of a neuroanatomical template, hippocampal volumes and surfaces were defined in 49 nondemented elders; the hippocampal surface was subsequently partitioned into three zones (i.e., lateral, superior and inferior-medial), which were proximal to the underlying CA1 subfield, CA2-4 subfields plus dentate gyrus, and subiculum, respectively. Annual clinical assessments using the Clinical Dementia Rating scale (CDR), where CDR 0 indicates no dementia and CDR 0.5 indicates very mild dementia, were then performed for a mean of 4.9 years (range 0.9-7.1 years) to monitor subjects who converted from CDR 0 to CDR 0.5. Inward variation of the lateral zone and left hippocampal volume significantly predicted conversion to CDR 0.5 in separate Cox proportional hazards models. When hippocampal surface variation and volume were included in a single model, inward variation of the lateral zone of the left hippocampal surface was selected as the only significant predictor of conversion. The pattern of hippocampal surface deformation observed in nondemented subjects who later converted to CDR 0.5 was similar to the pattern of hippocampal surface deformation previously observed to discriminate subjects with very mild DAT and nondemented subjects. These results suggest that inward deformation of the left hippocampal surface in a zone corresponding to the CA1 subfield is an early predictor of the onset of DAT in nondemented elderly subjects. {\textcopyright}2004 Elsevier Inc. All rights reserved.},
author = {Csernansky, J G and Wang, L and Swank, J and Miller, J P and Gado, M and McKeel, D and Miller, M I and Morris, J C},
doi = {10.1016/j.neuroimage.2004.12.036},
isbn = {1053-8119 (Print)$\backslash$n1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Clinical Dementia Rating scale,DAT},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {783--792},
pmid = {15808979},
publisher = {Academic Press},
title = {{Preclinical detection of Alzheimer's disease: Hippocampal shape and volume predict dementia onset in the elderly}},
volume = {25},
year = {2005}
}
@article{Reiman2005,
abstract = {Patients with Alzheimer's disease (AD) have abnormally low positron emission tomography (PET) measurements of the cerebral metabolic rate for glucose (CMRgI) in regions of the precuneus and the posterior cingulate, parietotemporal, and frontal cortex. Apolipoprotein E (APOE) $\epsilon$4 gene dose (i.e., the number of $\epsilon$4 alleles in a person's APOE genotype) is associated with a higher risk of AD and a younger age at dementia onset. We previously found that cognitively normal late-middle-aged APOE $\epsilon$4 carriers have abnormally low CMRgl in the same brain regions as patients with probable Alzheimer's dementia. In a PET study of 160 cognitively normal subjects 47-68 years of age, including 36 $\epsilon$4 homozygotes, 46 heterozygotes, and 78 $\epsilon$4 noncarriers who were individually matched for their gender, age, and educational level, we now find that $\epsilon$4 gene dose is correlated with lower CMRgl in each of these brain regions. This study raises the possibility of using PET as a quantitative presymptomatic endophenotype to help evaluate the individual and aggregate effects of putative genetic and nongenetic modifiers of AD risk. {\textcopyright}2005 by The National Academy of Sciences of the USA.},
author = {Reiman, Eric M and Chen, Kewei and Alexander, Gene E and Caselli, Richard J and Bandy, Daniel and Osborne, David and Saunders, Ann M and Hardy, John},
doi = {10.1073/pnas.0500579102},
issn = {0027-8424},
journal = {Proc. Natl. Acad. Sci.},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {23},
pages = {8299--8302},
pmid = {15932949},
publisher = {National Academy of Sciences},
title = {{Correlations between apolipoprotein E 4 gene dose and brain-imaging measurements of regional hypometabolism}},
volume = {102},
year = {2005}
}
@article{Saunders1993,
abstract = {Apolipoprotein E, type epsilon 4 allele (APOE epsilon 4), is associated with late-onset familial Alzheimer's disease (AD). There is high avidity and specific binding of amyloid beta-peptide with the protein ApoE. To test the hypothesis that late-onset familial AD may represent the clustering of sporadic AD in families large enough to be studied, we extended the analyses of APOE alleles to several series of sporadic AD patients. APOE epsilon 4 is significantly associated with a series of probable sporadic AD patients (0.36 +/- 0.042, AD, versus 0.16 +/- 0.027, controls [allele frequency estimate +/- standard error], p = 0.00031). Spouse controls did not differ from CEPH grandparent controls from the Centre d'Etude du Polymorphisme Humain (CEPH) or from literature controls. A large combined series of autopsy-documented sporadic AD patients also demonstrated highly significant association with the APOE epsilon 4 allele (0.40 +/- 0.026, p {\textless}or = 0.00001). These data support the involvement of ApoE epsilon 4 in the pathogenesis of late-onset familial and sporadic AD. ApoE isoforms may play an important role in the metabolism of beta-peptide, and APOE epsilon 4 may operate as a susceptibility gene (risk factor) for the clinical expression of AD.},
author = {Saunders, A M and Strittmatter, W J and Schmechel, D and George-Hyslop, P H and Pericak-Vance, M A and Joo, S H and Rosi, B L and Gusella, J F and Crapper-MacLachlan, D R and Alberts, M J},
doi = {10.1212/wnl.43.8.1467},
issn = {0028-3878},
journal = {Neurology},
mendeley-groups = {PhDThesis/Hippo},
number = {8},
pages = {1467--1472},
pmid = {8350998},
title = {{Association of apolipoprotein E allele epsilon 4 with late-onset familial and sporadic Alzheimer's disease.}},
volume = {43},
year = {1993}
}
@article{Crivello2010,
abstract = {In a sample of 1186 healthy subjects aged 65 to 89 years who were scanned twice with MRI 3.6 years apart, we studied the effects of age and ApoE-$\epsilon$4 allele load on the rate of atrophy of grey matter and hippocampus. Rates of grey matter and hippocampal volumes loss were computed from T1-weighted magnetic resonance images using voxel-based morphometry and region of interest analysis. Longitudinal analysis showed that an age-related annual rate of grey matter volume loss was only seen in $\epsilon$4 homozygotes only (n= 14) whereas no age effect was seen $\epsilon$4 heterozygotes (n= 239) and in noncarriers (n= 933). ApoE-$\epsilon$4 homozygotes also had a significantly larger rate of hippocampal volume loss than heterozygotes or noncarriers. During the same period, no effect or interaction of ApoE genotype and age was observed on cognitive decline, as assessed by the Mini Mental State Examination (MMSE). These data do not suggest an $\epsilon$4 gene dose effect on the rate of hippocampal volume loss in healthy elderly subjects as most of the effect was limited to homozygotes. Hippocampal volume loss may not be a good imaging marker to understand the effect of the ApoE-$\epsilon$4 allele on the risk of dementia in a population-based setting. It could be hypothesized that the impact of a single ApoE-$\epsilon$4 allele on brain structures is largely delayed in time. {\textcopyright}2010 Elsevier Inc.},
author = {Crivello, Fabrice and Lema{\^{i}}tre, Herv{\'{e}} and Dufouil, Carole and Grassiot, Blandine and Delcroix, Nicolas and Tzourio-Mazoyer, Nathalie and Tzourio, Christophe and Mazoyer, Bernard},
doi = {10.1016/j.neuroimage.2009.12.116},
isbn = {1095-9572},
issn = {10538119},
journal = {Neuroimage},
keywords = {$\epsilon$4 allele,3C study,ApoE genotype,Grey matter rate of volume loss,Hippocampal rate of volume loss,Longitudinal study,MMSE,MRI},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {1064--1069},
pmid = {20060049},
publisher = {Elsevier Inc.},
title = {{Effects of ApoE-$\epsilon$4 allele load and age on the rates of grey matter and hippocampal volumes loss in a longitudinal cohort of 1186 healthy elderly persons}},
volume = {53},
year = {2010}
}
@article{Chen2007,
author = {Chen, Kewei and Ph, D and Reiman, Eric M and Alexander, Gene E and Ph, D and Caselli, Richard J and Gerkin, Richard and Bandy, Daniel and Domb, Alisa and Osborne, David and Ph, D and Fox, Nick and Crum, William R and Phil, D and Saunders, Ann M and Ph, D and Hardy, John and Ph, D and Al, E T},
mendeley-groups = {PhDThesis/Hippo},
number = {June},
pages = {916--921},
title = {{Correlations Between Apolipoprotein E $\epsilon$4 Gene Dose.PDF}},
year = {2007}
}
@article{Lemaitre2005,
abstract = {The effect of ApoE genotype on grey matter (GM) atrophy was studied on a cohort of 750 healthy elderly volunteers (age range 63-75 years). High-resolution T1-weighted MR images were processed using both voxel-based morphometry and region of interest analysis for hippocampal volume estimation. Significant decrease of grey matter in $\epsilon$4homozygous subjects (n = 12), as compared both to $\epsilon$4heterozygous subjects (n = 175) and to noncarrier (n = 563) subjects, was found bilaterally in the medial temporal lobe, including the hippocampus, and extending over the superior temporal gyrus. By contrast, no significant difference was observed between $\epsilon$4heterozygous subjects and noncarriers at the level of the medial temporal lobe. Follow-up of the cohort cognitive performances over 4 years after their MRI exam revealed that, as compared to noncarrier subjects, the relative risk of cognitive impairment was 5.9 for $\epsilon$4homozygous subjects (P = 0.03), while it was not different from 1 for $\epsilon$4heterozygous subjects (P = 0.92). These findings indicate that, in the age range of this cohort, ApoE-4 effects on cortical atrophy and cognitive performances of healthy elderly are limited to $\epsilon$4homozygous subjects. {\textcopyright}2004 Elsevier Inc. All rights reserved.},
author = {Lema{\^{i}}tre, Herv{\'{e}} and Crivello, Fabrice and Dufouil, Carole and Grassiot, Blandine and Tzourio, Christophe and Alp{\'{e}}rovitch, Annick and Mazoyer, Bernard},
doi = {10.1016/j.neuroimage.2004.10.016},
isbn = {1053-8119},
issn = {10538119},
journal = {Neuroimage},
keywords = {$\epsilon$4allele,ApoE genotype,Hippocampal atrophy,MRI},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {1205--1213},
pmid = {15670698},
title = {{No $\epsilon$4gene dose effect on hippocampal atrophy in a large MRI database of healthy elderly subjects}},
volume = {24},
year = {2005}
}
@article{Clarke2011,
abstract = {Basic statistical analysis in genetic case-control studies},
author = {Clarke, Geraldine M and Anderson, Carl A and Pettersson, Fredrik H and Cardon, Lon R and Morris, Andrew P and Zondervan, Krina T},
doi = {10.1038/nprot.2010.182},
issn = {1754-2189},
journal = {Nat. Protoc.},
keywords = {Disease model,Genetic association study,Statistical methods},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {2},
pages = {121--133},
publisher = {Nature Publishing Group},
title = {{Basic statistical analysis in genetic case-control studies}},
volume = {6},
year = {2011}
}
@article{Wang2011,
abstract = {In genetic association study of quantitative traits using F∞ models, how to code the marker genotypes and interpret the model parameters appropriately is important for constructing hypothesis tests and making statistical inferences. Currently, the coding of marker genotypes in building F∞ models has mainly focused on the biallelic case. A thorough work on the coding of marker genotypes and interpretation of model parameters for F∞ models is needed especially for genetic markers with multiple alleles. In this study, we will formulate F∞ genetic models under various regression model frameworks and introduce three genotype coding schemes for genetic markers with multiple alleles. Starting from an allele-based modeling strategy, we first describe a regression framework to model the expected genotypic values at given markers. Then, as extension from the biallelic case, we introduce three coding schemes for constructing fully parameterized one-locus F∞ models and discuss the relationships between the model parameters and the expected genotypic values. Next, under a simplified modeling framework for the expected genotypic values, we consider several reduced one-locus F∞ models from the three coding schemes on the estimability and interpretation of their model parameters. Finally, we explore some extensions of the one-locus F∞ models to two loci. Several fully parameterized as well as reduced two-locus F∞ models are addressed. The genotype coding schemes provide different ways to construct F∞ models for association testing of multi-allele genetic markers with quantitative traits. Which coding scheme should be applied depends on how convenient it can provide the statistical inferences on the parameters of our research interests. Based on these F∞ models, the standard regression model fitting tools can be used to estimate and test for various genetic effects through statistical contrasts with the adjustment for environmental factors.},
author = {Wang, Tao},
doi = {10.1186/1471-2156-12-82},
issn = {1471-2156},
journal = {BMC Genet.},
keywords = {Animal Genetics and Genomics,Genetics and Population Dynamics,Life Sciences,Microbial Genetics and Genomics,Plant Genetics {\&} Genomics,general},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pages = {82},
publisher = {BioMed Central},
title = {{On coding genotypes for genetic markers with multiple alleles in genetic association study of quantitative traits}},
volume = {12},
year = {2011}
}
@article{Filippini2009,
abstract = {APOE e{\{}open{\}}4 is the best-established genetic risk factor for sporadic Alzheimer's disease (AD). However, while homozygotes show greater disease susceptibility and earlier age of onset than heterozygotes, they may not show faster rates of clinical progression. We hypothesize that there are differential APOE e{\{}open{\}}4 allele-load dependent influences on neuropathology across the brain. Our aim was to define the relationship between APOE e{\{}open{\}}4 allele load and regionally-specific brain cortical atrophy in Alzheimer's Disease (AD). For this reason voxel-based morphometry (VBM) was performed using T1-weighted MR images from 83 AD patients, contrasting regional cortical grey matter by APOE e{\{}open{\}}4 load according to either dominant or genotypic models. Patients fulfilled NINCDS-ADRDA criteria and were genotyped for APOE e{\{}open{\}}4 (15 e{\{}open{\}}4/e{\{}open{\}}4, 39 e{\{}open{\}}4/- and 29-/-). We observed that grey matter volume (GMV) decreased additively with increasing allele load in the medial (MTL) and anterior temporal lobes bilaterally. By contrast, a 2 degree-of-freedom genotypic model suggested a dominant effect of the APOE e{\{}open{\}}4 allele in the left temporal lobe. Brain regions showing a significant APOE e{\{}open{\}}4 allele load effect on GMV in AD included only some of those typically described as having greatest amyloid plaque deposition and atrophy. Temporal regions appeared to show a dominant effect of APOE e{\{}open{\}}4 allele load instead of the additive effect previously strongly associated with age of onset. Regional variations with allele load may be related to different mechanisms for effects of APOE e{\{}open{\}}4 load on susceptibility and disease progression. {\textcopyright}2008 Elsevier Inc. All rights reserved.},
author = {Filippini, Nicola and Rao, Anil and Wetten, Sally and Gibson, Rachel A and Borrie, Michael and Guzman, Danilo and Kertesz, Andrew and Loy-English, Inge and Williams, Julie and Nichols, Thomas and Whitcher, Brandon and Matthews, Paul M},
doi = {10.1016/j.neuroimage.2008.10.003},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {3},
pages = {724--728},
pmid = {19013250},
publisher = {Academic Press},
title = {{Anatomically-distinct genetic associations of APOE e{\{}open{\}}4 allele load with regional cortical atrophy in Alzheimer's disease}},
volume = {44},
year = {2009}
}
@article{Shakeri2016,
abstract = {Studying morphological changes of subcortical structures often predicate neurodevelopmental and neurodegenerative diseases, such as Alzheimer's disease and schizophrenia. Hence, methods for quantifying morphological variations in the brain anatomy, including groupwise shape analyses, are becoming increasingly important for studying neurological disorders. In this paper, a novel groupwise shape analysis approach is proposed to detect regional morphological alterations in subcortical structures between two study groups, e.g., healthy and pathological subjects. The proposed scheme extracts smoothed triangulated surface meshes from segmented binary maps, and establishes reliable point-to-point correspondences among the population of surfaces using a spectral matching method. Mean curvature features are incorporated in the matching process, in order to increase the accuracy of the established surface correspondence. The mean shapes are created as the geometric mean of all surfaces in each group, and a distance map between these shapes is used to characterize the morphological changes between the two study groups. The resulting distance map is further analyzed to check for statistically significant differences between two populations. The performance of the proposed framework is evaluated on two separate subcortical structures (hippocampus and putamen). Furthermore, the proposed methodology is validated in a clinical application for detecting abnormal subcortical shape variations in Alzheimer's disease. Experimental results show that the proposed method is comparable to state-of-the-art algorithms, has less computational cost, and is more sensitive to small morphological variations in patients with neuropathologies.},
annote = {Very similar to what we are doing, at least the pipeline is really really similar},
author = {Shakeri, Mahsa and Lombaert, Herve and Datta, Alexandre N and Oser, Nadine and L{\'{e}}tourneau-Guillon, Laurent and Lapointe, Laurence Vincent and Martin, Florence and Malfait, Domitille and Tucholka, Alan and Lipp{\'{e}}, Sarah and Kadoury, Samuel},
doi = {10.1016/j.compmedimag.2016.03.001},
isbn = {1879-0771; 0895-6111},
issn = {18790771},
journal = {Comput. Med. Imaging Graph.},
keywords = {Alzheimer's disease,Groupwise shape analysis,Spectral matching,Subcortical morphology},
mendeley-groups = {PhDThesis/Hippo},
pages = {58--71},
pmid = {27025904},
publisher = {Pergamon},
title = {{Statistical shape analysis of subcortical structures using spectral matching}},
volume = {52},
year = {2016}
}
@article{Wang2011a,
abstract = {Computational anatomy methods are now widely used in clinical neuroimaging to map the profile of disease effects on the brain and its clinical correlates. In Alzheimer's disease (AD), many research groups have modeled localized changes in hippocampal and lateral ventricular surfaces, to provide candidate biomarkers of disease progression for drug trials. We combined the power of parametric surface modeling and tensor-based morphometry to study hippocampal differences associated with AD and mild cognitive impairment (MCI) in 490 subjects (97 AD, 245 MCI, 148 controls) and ventricular differences in 804 subjects scanned as part of the Alzheimer's Disease Neuroimaging Initiative (ADNI; 184 AD, 391 MCI, 229 controls). We aimed to show that a new multivariate surface statistic based on multivariate tensor-based morphometry (mTBM) and radial distance provides a more powerful way to detect localized anatomical differences than conventional surface-based analysis. In our experiments, we studied correlations between hippocampal atrophy and ventricular enlargement and clinical measures and cerebrospinal fluid biomarkers. The new multivariate statistics gave better effect sizes for detecting morphometric differences, relative to other statistics including radial distance, analysis of the surface tensor and the Jacobian determinant. In empirical tests using false discovery rate curves, smaller sample sizes were needed to detect associations with diagnosis. The analysis pipeline is generic and automated. It may be applied to analyze other brain subcortical structures including the caudate nucleus and putamen. This publically available software may boost power for morphometric studies of subcortical structures in the brain.},
author = {Wang, Yalin and Song, Yang and Rajagopalan, Priya and An, Tuo and Liu, Krystal and Chou, Yi-Yu and Gutman, Boris and Toga, Arthur W and Thompson, Paul M and {Alzheimer's Disease Neuroimaging Initiative}, the Alzheimer's Disease Neuroimaging},
doi = {10.1016/j.neuroimage.2011.03.040},
issn = {1095-9572},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {4},
pages = {1993--2010},
pmid = {21440071},
publisher = {NIH Public Access},
title = {{Surface-based TBM boosts power to detect disease effects on the brain: an N=804 ADNI study.}},
volume = {56},
year = {2011}
}
@article{Zhang2016,
abstract = {We offer a blazingly brief review of evolution of shape analysis methods in medical imaging. As the representations and the statistical models grew more sophisticated, the problem of shape analysis has been gradually redefined to accept images rather than binary segmentations as a starting point. This transformation enabled shape analysis to take its rightful place in the arsenal of tools for extracting and understanding patterns in large clinical image sets. We speculate on the future developments in shape analysis and potential applications that would bring this mathematically rich area to bear on clinical practice.},
annote = {Important paper on the basics of statistical shape analysis.},
author = {Zhang, Miaomiao and Golland, Polina},
doi = {10.1016/j.media.2016.06.025},
issn = {1361-8423},
journal = {Med. Image Anal.},
keywords = {Diffeomorphisms,Landmarks,Shape variability,Statistical shape analysis},
mendeley-groups = {PhDThesis/Hippo},
pages = {155--158},
pmid = {27377332},
publisher = {NIH Public Access},
title = {{Statistical shape analysis: From landmarks to diffeomorphisms.}},
volume = {33},
year = {2016}
}
@inproceedings{Inlow2016,
abstract = {In this work, we propose a novel and powerful image analysis framework for hippocampal morphometry in early mild cognitive impairment (EMCI), an early prodromal stage of Alzheimer's disease (AD). We create a hippocampal surface atlas with subfield information, model each hippocampus using the SPHARM technique, and register it to the atlas to extract surface deformation signals. We propose a new alternative to standard random field theory (RFT) and permutation image analysis methods, Statistical Parametric Mapping (SPM) Distribution Analysis or SPM-DA, to perform statistical shape analysis and compare its performance with that of RFT methods on both simulated and real hippocampal surface data. The major strengths of our framework are twofold: (a) SPM-DA provides potentially more powerful algorithms than standard RFT methods for detecting weak signals, and (b) the framework embraces the important hippocampal subfield information for improved biological interpretation. We demonstrate the effectiveness of our method via an application to an AD cohort, where an SPM-DA method detects meaningful hippocampal shape differences in EMCI that are undetected by standard RFT methods.},
author = {Inlow, Mark and Cong, Shan and Risacher, Shannon L and West, John and Rizkalla, Maher and Salama, Paul and Saykin, Andrew J and Shen, Li},
booktitle = {Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-43775-0_27},
isbn = {9783319437743},
issn = {16113349},
mendeley-groups = {PhDThesis/Hippo},
pages = {302--310},
publisher = {Springer Verlag},
title = {{A new statistical image analysis approach and its application to Hippocampal morphometry}},
volume = {9805 LNCS},
year = {2016}
}
@article{Nitzken2014,
abstract = {The survey outlines and compares popular computational techniques for quantitative description of shapes of major structural parts of the human brain, including medial axis and skeletal analysis, geodesic distances, Procrustes analysis, deformable models, spherical harmonics, and deformation morphometry, as well as other less widely used techniques. Their advantages, drawbacks, and emerging trends, as well as results of applications, in particular, for computer-aided diagnostics, are discussed. {\textcopyright}2014 IEEE.},
annote = {Review, que podem citar de passada juntament amb d'altres reviews.},
author = {Nitzken, Matthew J and Casanova, Manuel F and Gimel'farb, Georgy and Inanc, Tamer and Zurada, Jacek M and El-Baz, Ayman},
doi = {10.1109/JBHI.2014.2298139},
issn = {21682194},
journal = {IEEE J. Biomed. Heal. Informatics},
keywords = {Brain,diagnostics,shape analysis},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {1337--1354},
title = {{Shape analysis of the human brain: A brief survey}},
volume = {18},
year = {2014}
}
@book{Shen2017a,
abstract = {Statistical shape analysis is a fundamental topic in biomedical image computing, and plays important roles in numerous applications in brain imaging. This chapter describes typical shape analysis methods for modeling and analyzing 3D surface data in brain imaging studies. These studies examine various structures of interest in the brain, and aim to identify morphometric differences associated with a particular condition to aid diagnosis and treatment. We first present classic computational methods for modeling and registering 3D surfaces, and then discuss advanced methods that take into consideration subfield information on the surface. After that, we describe techniques for shape analysis of registered surface models, including traditional general linear models as well as a newly proposed statistical learning model for performing surface-based morphometry. Finally, we provide a real world neuroimaging application to demonstrate the effectiveness of these techniques.},
author = {Shen, Li and Cong, Shan and Inlow, Mark},
booktitle = {Stat. Shape Deform. Anal. Methods, Implement. Appl.},
doi = {10.1016/B978-0-12-810493-4.00016-X},
edition = {1},
isbn = {9780128104941},
keywords = {Distribution analysis,Hippocampal subfield,Hippocampus,Magnetic resonance imaging,Random field theory,Spherical harmonics,Spherical parameterization,Statistical parametric mapping,Surface registration,Surface-based morphometry},
mendeley-groups = {PhDThesis/Hippo},
pages = {351--378},
publisher = {Elsevier Ltd},
title = {{Statistical Shape Analysis for Brain Structures}},
year = {2017}
}
@article{Miller2006,
annote = {Citar perque si, per{\`{o}} no {\'{e}}s gaire rellevant.},
author = {Miller, Michael I and Trouv{\'{e}}, Alain and Younes, Laurent},
doi = {10.1007/s10851-005-3624-0},
journal = {J Math Imaging Vis.},
mendeley-groups = {PhDThesis/Hippo},
number = {2},
pages = {209--228},
title = {{Geodesic Shooting for Computational Anatomy}},
volume = {24},
year = {2006}
}
@article{Durrleman2014,
abstract = {We propose a generic method for the statistical analysis of collections of anatomical shape complexes, namely sets of surfaces that were previously segmented and labeled in a group of subjects. The method estimates an anatomical model, the template complex, that is representative of the population under study. Its shape reflects anatomical invariants within the dataset. In addition, the method automatically places control points near the most variable parts of the template complex. Vectors attached to these points are parameters of deformations of the ambient 3D space. These deformations warp the template to each subject's complex in a way that preserves the organization of the anatomical structures. Multivariate statistical analysis is applied to these deformation parameters to test for group differences. Results of the statistical analysis are then expressed in terms of deformation patterns of the template complex, and can be visualized and interpreted. The user needs only to specify the topology of the template complex and the number of control points. The method then automatically estimates the shape of the template complex, the optimal position of control points and deformation parameters. The proposed approach is completely generic with respect to any type of application and well adapted to efficient use in clinical studies, in that it does not require point correspondence across surfaces and is robust to mesh imperfections such as holes, spikes, inconsistent orientation or irregular meshing.The approach is illustrated with a neuroimaging study of Down syndrome (DS). The results demonstrate that the complex of deep brain structures shows a statistically significant shape difference between control and DS subjects. The deformation-based modelingis able to classify subjects with very high specificity and sensitivity, thus showing important generalization capability even given a low sample size. We show that the results remain significant even if the number of control points, and hence the dimension of variables in the statistical model, are drastically reduced. The analysis may even suggest that parsimonious models have an increased statistical performance.The method has been implemented in the software Deformetrica, which is publicly available at www.deformetrica.org. {\textcopyright}2014 Elsevier Inc.},
author = {Durrleman, Stanley and Prastawa, Marcel and Charon, Nicolas and Korenberg, Julie R and Joshi, Sarang and Gerig, Guido and Trouv{\'{e}}, Alain},
doi = {10.1016/j.neuroimage.2014.06.043},
issn = {10959572},
journal = {Neuroimage},
keywords = {Anatomy,Deformation,Morphometry,Shape,Statistics,Varifold},
mendeley-groups = {PhDThesis/Hippo},
pages = {35--49},
publisher = {Elsevier Inc.},
title = {{Morphometry of anatomical shape complexes with dense deformations and sparse parameters}},
volume = {101},
year = {2014}
}
@article{Qiu2009,
abstract = {Late-onset depression often precedes the onset of dementia associated with the hippocampal degeneration. Using large deformation diffeomorphic metric mapping (LDDMM), we evaluated apolipoprotein E epsilon-4 allele (apoE E4) effects on hippocampal volume and shape in 38 depressed patients without the apoE E4, 14 depressed patients with one apoE E4, and 31 healthy comparison subjects without the apoE E4. The hippocampal volumes were manually assessed. We applied a diffeomorphic template generation procedure for creating the hippocampal templates based on a subset of the population. The LDDMM mappings were used to generate the hippocampal shape of each subject and characterize the surface deformation of each hippocampus relative to the template. Such deformation was modeled as random field characterized by the Laplace-Beltrami basis functions in the template coordinates. Linear regression was used to examine group differences in the hippocampal volume and shape. We found that there were significant hippocampal shape alternations in both depressed groups while the groups of depressed patients and the group of healthy subjects did not differ in the hippocampal volume. The depressed patients with one apoE E4 show more pronounced shape inward-compression in the anterior CA1 than the depressed patients without the apoE E4 when compared with the healthy controls without the apoE E4. Thus, hippocampal shape abnormalities in late-onset depressed patients with one apoE E4 may indicate future conversion of this group to AD at higher risk than depressed patients without the apoE E4. {\textcopyright}2008 Elsevier Inc.},
author = {Qiu, Anqi and Taylor, Warren D and Zhao, Zheen and MacFall, James R and Miller, Michael I and Key, Cynthia R and Payne, Martha E and Steffens, David C and Krishnan, K Ranga R},
doi = {10.1016/j.neuroimage.2008.10.010},
issn = {10538119},
journal = {Neuroimage},
keywords = {APOE,Diffeomorphic mapping,Geriatric depression,Hippocampal shape},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {3},
pages = {620--626},
publisher = {Academic Press},
title = {{APOE related hippocampal shape alteration in geriatric depression}},
volume = {44},
year = {2009}
}
@article{Cury2019a,
abstract = {Brain atrophy as measured from structural MR images, is one of the primary imaging biomarkers used to track neurodegenerative disease progression. In diseases such as frontotemporal dementia or Alzheimer's disease, atrophy can be observed in key brain structures years before any clinical symptoms are present. Atrophy is most commonly captured as volume change of key structures and the shape changes of these structures are typically not analysed despite being potentially more sensitive than summary volume statistics over the entire structure. In this paper we propose a spatiotemporal analysis pipeline based on Large Diffeomorphic Deformation Metric Mapping (LDDMM) to detect shape changes from volumetric MRI scans. We applied our framework to a cohort of individuals with genetic variants of frontotemporal dementia and healthy controls from the Genetic FTD Initiative (GENFI) study. Our method, take full advantage of the LDDMM framework, and relies on the creation of a population specific average spatiotemporal trajectory of a relevant brain structure of interest, the thalamus in our case. The residuals from each patient data to the average spatiotemporal trajectory are then clustered and studied to assess when presymptomatic mutation carriers differ from healthy control subjects. We found statistical differences in shape in the anterior region of the thalamus at least five years before the mutation carrier subjects develop any clinical symptoms. This region of the thalamus has been shown to be predominantly connected to the frontal lobe, consistent with the pattern of cortical atrophy seen in the disease.},
annote = {Longitudinal. Mencionar i ja.

LDDMM paper.},
author = {Cury, Claire and Durrleman, Stanley and Cash, David M and Lorenzi, Marco and Nicholas, Jennifer M and Bocchetta, Martina and van Swieten, John C and Borroni, Barbara and Galimberti, Daniela and Masellis, Mario and Tartaglia, Maria Carmela and Rowe, James B and Graff, Caroline and Tagliavini, Fabrizio and Frisoni, Giovanni B and Laforce, Robert and Finger, Elizabeth and de Mendon{\c{c}}a, Alexandre and Sorbi, Sandro and Ourselin, Sebastien and Rohrer, Jonathan D and Modat, Genetic F T D Initiative GENFI},
doi = {10.1016/j.neuroimage.2018.11.063},
issn = {10959572},
journal = {Neuroimage},
keywords = {Clustering,Computational anatomy,Parallel transport,Shape analysis,Spatiotemporal geodesic regression,Thalamus},
mendeley-groups = {PhDThesis/Hippo},
month = {mar},
pages = {282--290},
pmid = {30529631},
publisher = {Academic Press Inc.},
title = {{Spatiotemporal analysis for detection of pre-symptomatic shape changes in neurodegenerative diseases: Initial application to the GENFI cohort}},
volume = {188},
year = {2019}
}
@article{Cong2015,
abstract = {The hippocampus is widely studied with neuroimaging techniques given its importance in learning and memory and its potential as a biomarker for Alzheimer's disease (AD). Its complex folding anatomy often presents analytical challenges. In particular, the critical subfield information is typically not addressed by the existing hippocampal shape studies. To bridge this gap, we present a computational framework for surface-based morphometric analysis of hippocampal subfields. The major strengths of this framework are as follows: (a) it performs detailed hippocampal shape analysis, (b) it embraces, rather than ignores, the important hippocampal subfield information, and (c) it analyzes regular magnetic resonance imaging scans and is applicable to large scale studies. We demonstrate its effectiveness by applying it to the identification of regional hippocampal subfield atrophy patterns associated with mild cognitive impairment and AD.},
author = {Cong, Shan and Rizkalla, Maher and Salama, Paul and West, John and Risacher, Shannon and Saykin, Andrew and Shen, Li},
doi = {10.1109/MWSCAS.2015.7282173},
isbn = {9781467365574},
issn = {15483746},
journal = {Midwest Symp. Circuits Syst.},
mendeley-groups = {PhDThesis/Hippo},
title = {{Surface-based morphometric analysis of hippocampal subfields in mild cognitive impairment and Alzheimer's disease}},
volume = {2015-Septe},
year = {2015}
}
@article{Kim2015a,
abstract = {Accurately recovering the hippocampal shapes against rough and noisy segmentations is as challenging as achieving good anatomical correspondence between the individual shapes. To address these issues, we propose a mesh-to-volume registration approach, characterized by a progressive model deformation. Our model implements flexible weighting scheme for model rigidity under a multi-level neighborhood for vertex connectivity. This method induces a large-to-small scale deformation of a template surface to build the pairwise correspondence by minimizing geometric distortion while robustly restoring the individuals' shape characteristics. We evaluated the proposed method's 1) accuracy and robustness in smooth surface reconstruction, 2) sensitivity in detecting significant shape differences between healthy control and disease groups (mild cognitive impairment and Alzheimer's disease), 3) robustness in constructing the anatomical correspondence between individual shape models, and 4) applicability in identifying subtle shape changes in relation to cognitive abilities in a healthy population. We compared the performance of the proposed method with other well-known methods - SPHARM-PDM, ShapeWorks and LDDMM volume registration with template injection - using various metrics of shape similarity, surface roughness, volume, and shape deformity. The experimental results showed that the proposed method generated smooth surfaces with less volume differences and better shape similarity to input volumes than others. The statistical analyses with clinical variables also showed that it was sensitive in detecting subtle shape changes of hippocampus.},
annote = {!! Citar.

Paper molt interessant, on fa una comparaci{\'{o}} de m{\`{e}}todes necess{\`{a}}ria, t{\'{e}} una introducci{\'{o}} on ens podem inspirar, i utilitza un meteode que caldria citar. De fet, aquest article potser estaria b{\'{e}} haver-lo llegit ABANS de fer tot. oh well.},
author = {Kim, Jaeil and Valdes-Hernandez, Maria Del C and Royle, Natalie A and Park, Jinah},
doi = {10.1109/TMI.2014.2382581},
issn = {1558254X},
journal = {IEEE Trans. Med. Imaging},
keywords = {Brain,hippocampus,magnetic resonance imaging (MRI),progressive model deformation,shape analysis},
mendeley-groups = {PhDThesis/Hippo},
number = {6},
pages = {1242--1261},
title = {{Hippocampal shape modeling based on a progressive template surface deformation and its verification}},
volume = {34},
year = {2015}
}
@article{Gutierrez2019,
abstract = {This work presents a Bayesian predictive approach to statistical shape analysis. A modeling strategy that starts with a Gaussian distribution on the configuration space, and then removes the effects of location, rotation and scale, is studied. This boils down to an application of the projected normal distribution to model the configurations in the shape space, which together with certain identifiability constraints, facilitates parameter interpretation. Having better control over the parameters allows us to generalize the model to a regression setting where the effect of predictors on shapes can be considered. The methodology is illustrated and tested using both simulated scenarios and a real data set concerning eight anatomical landmarks on a sagittal plane of the corpus callosum in patients with autism and in a group of controls.},
author = {Guti{\'{e}}rrez, Luis and Guti{\'{e}}rrez-Pe{\~{n}}a, Eduardo and Mena, Rams{\'{e}}s H},
doi = {10.1214/18-BA1113},
issn = {19316690},
journal = {Bayesian Anal.},
keywords = {Bookstein coordinates,Identifiability,Medical image,Shape regression},
mendeley-groups = {PhDThesis/Hippo},
number = {2},
pages = {427--447},
title = {{A Bayesian approach to statistical shape analysis via the projected normal distribution}},
volume = {14},
year = {2019}
}
@article{Madan2017,
abstract = {Metrics of brain morphology are increasingly being used to examine inter-individual differences, making it important to evaluate the reliability of these structural measures. Here we used two open-access datasets to assess the intersession reliability of three cortical measures (thickness, gyrification, and fractal dimensionality) and two subcortical measures (volume and fractal dimensionality). Reliability was generally good, particularly with the gyrification and fractal dimensionality measures. One dataset used a sequence previously optimized for brain morphology analyses and had particularly high reliability. Examining the reliability of morphological measures is critical before the measures can be validly used to investigate inter-individual differences.},
annote = {Estic segur que aquest {\'{e}}s un dels meus reviewers.

Que putes merdes vol dir test-retest? La puta primera vegada que ho escolto.

No el poso, per{\`{o}}},
author = {Madan, Christopher R and Kensinger, Elizabeth A},
doi = {10.1007/s40708-016-0060-4},
issn = {21984026},
journal = {Brain Informatics},
keywords = {Cortical structure,Cortical thickness,Fractal dimensionality,Gyrification,Reliability,Structural complexity,Subcortical},
mendeley-groups = {PhDThesis/Hippo},
month = {jun},
number = {2},
pages = {107--121},
publisher = {Springer Berlin Heidelberg},
title = {{Test–retest reliability of brain morphology estimates}},
volume = {4},
year = {2017}
}
@article{Bouix2005,
abstract = {In magnetic resonance imaging (MRI) research, significant attention has been paid to the analysis of the hippocampus (HC) within the medial temporal lobe because of its importance in memory and learning, and its role in neurodegenerative diseases. Manual segmentation protocols have established a volume decline in the HC in conjunction with Alzheimer's disease, epilepsy, post-traumatic stress disorder, and depression. Furthermore, recent studies have investigated age-related changes of HC volume which show an interaction with gender; in early adulthood, volume reduction of the HC is found in men but not in women. In this paper, we investigated gender differences in normal subjects in young adulthood by employing a shape analysis of the HC using medial surfaces. For each subject, the most prominent medial manifold of the HC was extracted and flattened. The flattened sheets were then registered using both a rigid and a non-rigid alignment technique, and the medial surface radius was expressed as a height function over them. This allowed for an investigation of the association between subject variables and the local width of the HC. With regard to the effects of age and gender, it could be shown that the previously observed gender differences were mostly due to volume loss in males in the lateral areas of the HC head and tail. We suggest that the analysis of HC shape using medial surfaces might thus serve as a complimentary technique to investigate group differences to the established segmentation protocols for volume quantification in MRI. {\textcopyright}2004 Elsevier Inc. All rights reserved.},
author = {Bouix, Sylvain and Pruessner, Jens C and Collins, D Louis and Siddiqi, Kaleem},
doi = {10.1016/j.neuroimage.2004.12.051},
issn = {10538119},
journal = {Neuroimage},
keywords = {Hippocampus,MRI,Medial surfaces,Medial temporal lobe,Shape analysis,Structural analysis},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {1077--1089},
pmid = {15850726},
publisher = {Academic Press},
title = {{Hippocampal shape analysis using medial surfaces}},
volume = {25},
year = {2005}
}
@article{Zhao2008,
abstract = {Major depression in the elderly is associated with brain structural changes and vascular lesions. Changes in the subcortical regions of the limbic system have also been noted. Studies examining hippocampus volumetric differences in depression have shown variable results, possibly due to any volume differences being secondary to local shape changes rather than differences in the overall volume. Shape analysis offers the potential to detect such changes. The present study applied spherical harmonic (SPHARM) shape analysis to the left and right hippocampi of 61 elderly subjects with major depression an 43 non-depressed elderly subjects. Statistical models controlling for age, sex, and total cerebral volume showed a significant reduction in depressed compared with control subjects in the left hippocampus (F1.103=5.26; p=0.0240) but not right hippocampus volume (F1.103=0.5213). Shape analysis showed significant differences in the mid-body of the left (but not the right hippocampus between depressed and controls. When the depressed group was dichotomozed into those whose depression was remitted at time of imaging and those who were unremitted, the shape comparison showed remitted subjects to be indistinguishable from controls (both sides) while the unremitted subjects different in the midbody and the lateral side near the head. Hippocampal volume showed no difference between controls and remitted subjects but nonremitted subjects had significantly smaller left hippocampal volumes with no significant group differences in the right hippocampus. These findings may provide support to other reports of neurogenic effects of antidepressants and their relation to successful treatment for depressive symptoms. {\textcopyright}2008 Zhao et al.},
author = {Zhao, Zheen and Taylor, Warren D and Styner, Martin and Steffens, David C and Krishnan, K Ranga R and MacFall, James R},
doi = {10.1371/journal.pone.0001837},
editor = {Baune, Bernhard},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Hippo},
month = {mar},
number = {3},
pages = {e1837},
publisher = {Public Library of Science},
title = {{Hippocampus shape analysis and late-life depression}},
volume = {3},
year = {2008}
}
@article{Singh2014,
abstract = {Abstract We develop a multivariate analysis of brain anatomy to identify the relevant shape deformation patterns and quantify the shape changes that explain corresponding variations in clinical neuropsychological measures. We use kernel Partial Least Squares (PLS) and formulate a regression model in the tangent space of the manifold of diffeomorphisms characterized by deformation momenta. The scalar deformation momenta completely encode the diffeomorphic changes in anatomical shape. In this model, the clinical measures are the response variables, while the anatomical variability is treated as the independent variable. To better understand the “shape—clinical response” relationship, we also control for demographic confounders, such as age, gender, and years of education in our regression model. We evaluate the proposed methodology on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database using baseline structural MR imaging data and neuropsychological evaluation test scores. We demonstrate the ability of our model to quantify the anatomical deformations in units of clinical response. Our results also demonstrate that the proposed method is generic and generates reliable shape deformations both in terms of the extracted patterns and the amount of shape changes. We found that while the hippocampus and amygdala emerge as mainly responsible for changes in test scores for global measures of dementia and memory function, they are not a determinant factor for executive function. Another critical finding was the appearance of thalamus and putamen as most important regions that relate to executive function. These resulting anatomical regions were consistent with very high confidence irrespective of the size of the population used in the study. This data-driven global analysis of brain anatomy was able to reach similar conclusions as other studies in Alzheimer's disease based on predefined ROIs, together with the identification of other new patterns of deformation. The proposed methodology thus holds promise for discovering new patterns of shape changes in the human brain that could add to our understanding of disease progression in neurological disorders.},
author = {Singh, Nikhil and {Thomas Fletcher}, P and {Samuel Preston}, J and King, Richard D and Marron, J S and Weiner, Michael W and Joshi, Sarang},
doi = {https://doi.org/10.1016/j.media.2014.01.001},
issn = {1361-8415},
journal = {Med. Image Anal.},
keywords = {Alzheimer's disease,Computational anatomy,Deformation momenta,Kernel Partial Least Squares (PLS),Prediction},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {616--633},
title = {{Quantifying anatomical shape variations in neurological disorders}},
volume = {18},
year = {2014}
}
@article{Tang2016,
abstract = {We analyzed, in an integrative fashion, the morphometry and structural integrity of the bilateral hippocampi and amygdalas in Alzheimer's disease (AD) using T1-weighted images and diffusion tensor images (DTIs). We detected significant hippocampal and amygdalar volumetric atrophies in AD relative to healthy controls (HCs). Shape analysis revealed significant region-specific atrophies with the hippocampal atrophy mainly being concentrated on the CA1 and CA2 while the amygdalar atrophy was concentrated on the basolateral and basomedial. In all structures, the structural integrity displayed a significantly decreased mean fractional anisotropy (FA) value and an increased mean trace value in AD. In addition to the inter-group comparisons, we systematically evaluated the discriminative power of our three types of features (volume, shape, and DTI), both individually and in their possible combinations, when differentiating between AD and HCs. We found the volume features to be redundant when the more sophisticated shape features were available. A combination of the shape and DTI features of the right hippocampus, with classification automatically performed by support vector machine, yielded the strongest classification result (overall accuracy, 94.6{\%}; sensitivity, 95.5{\%}; specificity, 93.3{\%}).},
author = {Tang, Xiaoying and Qin, Yuanyuan and Wu, Jiong and Zhang, Min and Zhu, Wenzhen and Miller, Michael I},
doi = {10.1016/j.mri.2016.05.001},
issn = {18735894},
journal = {Magn. Reson. Imaging},
keywords = {Amygdala,Diffusion tensor imaging,Hippocampus,Linear discriminant analysis,Shape,Support vector machine},
mendeley-groups = {PhDThesis/Hippo},
number = {8},
pages = {1087--1099},
publisher = {Elsevier B.V.},
title = {{Shape and diffusion tensor imaging based integrative analysis of the hippocampus and the amygdala in Alzheimer's disease}},
volume = {34},
year = {2016}
}
@article{Chung2010,
abstract = {Although there are many imaging studies on traditional ROI-based amygdala volumetry, there are very few studies on modeling amygdala shape variations. This paper presents a unified computational and statistical framework for modeling amygdala shape variations in a clinical population. The weighted spherical harmonic representation is used to parameterize, smooth out, and normalize amygdala surfaces. The representation is subsequently used as an input for multivariate linear models accounting for nuisance covariates such as age and brain size difference using the SurfStat package that completely avoids the complexity of specifying design matrices. The methodology has been applied for quantifying abnormal local amygdala shape variations in 22 high functioning autistic subjects. {\textcopyright}2010 Elsevier Inc.},
annote = {Paper que fa servir Surfstat. Crec que {\'{e}}s el paper de l'exemple que hi ha a la web. Citar.},
author = {Chung, Moo K and Worsley, Keith J and Nacewicz, Brendon M and Dalton, Kim M and Davidson, Richard J},
doi = {10.1016/j.neuroimage.2010.06.032},
issn = {10538119},
journal = {Neuroimage},
keywords = {Amygdala,Fourier analysis,Multivariate linear model,Spherical harmonics,SurfStat,Surface flattening},
mendeley-groups = {PhDThesis/Hippo},
number = {2},
pages = {491--505},
pmid = {20620211},
publisher = {NIH Public Access},
title = {{General multivariate linear modeling of surface shapes using SurfStat}},
volume = {53},
year = {2010}
}
@article{Apostolova2010,
abstract = {We used a previously validated automated machine learning algorithm based on adaptive boosting to segment the hippocampi in baseline and 12-month follow-up 3D T1-weighted brain MRIs of 150 cognitively normal elderly (NC), 245 mild cognitive impairment (MCI) and 97 Dementia of the Alzheimer's type (DAT) ADNI subjects. Using the radial distance mapping technique, we examined the hippocampal correlates of delayed recall performance on three well-established verbal memory tests-ADAScog delayed recall (ADAScog-DR), the Rey Auditory Verbal Learning Test -DR (AVLT-DR) and Wechsler Logical Memory II-DR (LM II-DR). We observed no significant correlations between delayed recall performance and hippocampal radial distance on any of the three verbal memory measures in NC. All three measures were associated with hippocampal volumes and radial distance in the full sample and in the MCI group at baseline and at follow-up. In DAT we observed stronger left-sided associations between hippocampal radial distance, LM II-DR and ADAScog-DR both at baseline and at follow-up. The strongest linkage between memory performance and hippocampal atrophy in the MCI sample was observed with the most challenging verbal memory test-the AVLT-DR, as opposed to the DAT sample where the least challenging test the ADAScog-DR showed strongest associations with the hippocampal structure. After controlling for baseline hippocampal atrophy, memory performance showed regionally specific associations with hippocampal radial distance in predominantly CA1 but also in subicular distribution. {\textcopyright}2009 Elsevier Inc.},
author = {Apostolova, Liana G and Morra, Jonathan H and Green, Amity E and Hwang, Kristy S and Avedissian, Christina and Woo, Ellen and Cummings, Jeffrey L and Toga, Arthur W and Jack, Clifford R and Weiner, Michael W and Thompson, Paul M},
doi = {10.1016/j.neuroimage.2009.12.125},
issn = {10538119},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pages = {488--499},
publisher = {Academic Press},
title = {{Automated 3D mapping of baseline and 12-month associations between three verbal memory measures and hippocampal atrophy in 490 ADNI subjects}},
volume = {51},
year = {2010}
}
@article{Younes2014,
abstract = {This paper uses diffeomorphometry methods to quantify the order in which statistically significant morphometric change occurs in three medial temporal lobe regions, the amygdala, entorhinal cortex (ERC), and hippocampus among subjects with symptomatic and preclinical Alzheimer's disease (AD). Magnetic resonance imaging scans were examined in subjects who were cognitively normal at baseline, some of whom subsequently developed clinical symptoms of AD. The images were mapped to a common template, using shape-based diffeomorphometry. The multidimensional shape markers indexed through the temporal lobe structures were modeled using a changepoint model with explicit parameters, specifying the number of years preceding clinical symptom onset. Our model assumes that the atrophy rate of a considered brain structure increases years before detectable symptoms. The results demonstrate that the atrophy changepoint in the ERC occurs first, indicating significant change 8-10 years prior to onset, followed by the hippocampus, 2-4 years prior to onset, followed by the amygdala, 3 years prior to onset. The ERC is significant bilaterally, in both our local and global measures, with estimates of ERC surface area loss of 2.4{\%} (left side) and 1.6{\%} (right side) annually. The same changepoint model for ERC volume gives 3.0{\%} and 2.7{\%} on the left and right sides, respectively. Understanding the order in which changes in the brain occur during preclinical AD may assist in the design of intervention trials aimed at slowing the evolution of the disease.{\textcopyright}2014 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license.},
author = {Younes, Laurent and Albert, Marilyn and Miller, Michael I},
doi = {10.1016/j.nicl.2014.04.009},
issn = {22131582},
journal = {NeuroImage Clin.},
keywords = {AD,Abbreviations,Alzheimer's disease,CDR,Clinical Center of the National Institutes of Heal,ERC,FWER,GPB,Geriatric Psychiatry Branch,MCI,MMSE,NIA,NIH,NIMH,National Institute for Mental Health,National Institute on Aging,ROI-LDDMM,RSS,SPGR,clinical dementia rating,diffeomorphometry,entorhinal cortex,family-wise error rate,mild cognitive impairment,mini-mental state exam,region-of-interest large deformation diffeomorphic,residual sum of squares,spoiled gradient echo,study of shape using a metric on the diffeomorphic},
mendeley-groups = {PhDThesis/Hippo},
pages = {178--187},
publisher = {Elsevier},
title = {{Inferring changepoint times of medial temporal lobe morphometric change in preclinical Alzheimer's disease}},
volume = {5},
year = {2014}
}
@article{Kim2015,
abstract = {The purposes of the present study were to explore whether hippocampal atrophy exists in pure subcortical vascular dementia (SVaD) as defined by negative 11C-Pittsburg compound-B (PiB-) positron emission tomography and to compare hippocampal volume and shape between PiB- SVaD and PiB positive (PiB+) Alzheimer's disease (AD) dementia. Hippocampal volume and shape were compared among 40 patients with PiB- SVaD, 34 with PiB+ AD, and 21 elderly with normal cognitive function (NC). The normalized hippocampal volume of PiB- SVaD was significantly smaller than NC but larger than that of PiB+ AD (NC {\textgreater}PiB- SVaD {\textgreater}PiB+ AD). Both PiB- SVaD and PiB+ AD patients had deflated shape changes in the cornus ammonis (CA) 1 and subiculum compared with NC. However, direct comparison between PiB- SVaD and PiB+ AD demonstrated more inward deformity in the subiculum of the left hippocampus in PiB+ AD. PiB- SVaD patients did have smaller hippocampal volumes and inward shape change on CA 1 and subiculum compared with NC, suggesting that cumulative ischemia without amyloid pathology could lead to hippocampal atrophy and shape changes.},
annote = {Molt cl{\'{i}}nic, crec que no faria falta posar-lo},
author = {Kim, Geon Ha and Lee, Jae Hong and Seo, Sang Won and Kim, Jeong Hun and Seong, Joon Kyung and Ye, Byoung Seok and Cho, Hanna and Noh, Young and Kim, Hee Jin and Yoon, Cindy W and Oh, Seung Jun and Kim, Jae Seung and Choe, Yearn Seong and Lee, Kyung Han and Kim, Sung Tae and Hwang, Jung Won and Jeong, Jee Hyang and Na, Duk L},
doi = {10.1016/j.neurobiolaging.2014.08.009},
issn = {15581497},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Hippocampus,PiB-PET,Vascular dementia},
mendeley-groups = {PhDThesis/Hippo},
number = {1},
pages = {485--491},
publisher = {Elsevier Ltd},
title = {{Hippocampal volume and shape in pure subcortical vascular dementia}},
volume = {36},
year = {2015}
}
@article{Shi2007,
abstract = {We propose in this paper a new method for the mapping of hippocampal (HC) surfaces to establish correspondences between points on HC surfaces and enable localized HC shape analysis. A novel geometric feature, the intrinsic shape context, is defined to capture the global characteristics of the HC shapes. Based on this intrinsic feature, an automatic algorithm is developed to detect a set of landmark curves that are stable across population. The direct map between a source and target HC surface is then solved as the minimizer of a harmonic energy function defined on the source surface with landmark constraints. For numerical solutions, we compute the map with the approach of solving partial differential equations on implicit surfaces. The direct mapping method has the following properties: (1) it has the advantage of being automatic; (2) it is invariant to the pose of HC shapes. In our experiments, we apply the direct mapping method to study temporal changes of HC asymmetry in Alzheimer's disease (AD) using HC surfaces from 12 AD patients and 14 normal controls. Our results show that the AD group has a different trend in temporal changes of HC asymmetry than the group of normal controls. We also demonstrate the flexibility of the direct mapping method by applying it to construct spherical maps of HC surfaces. Spherical harmonics (SPHARM) analysis is then applied and it confirms our results on temporal changes of HC asymmetry in AD. {\textcopyright}2007 Elsevier Inc. All rights reserved.},
author = {Shi, Yonggang and Thompson, Paul M and de Zubicaray, Greig I and Rose, Stephen E and Tu, Zhuowen and Dinov, Ivo and Toga, Arthur W},
doi = {10.1016/j.neuroimage.2007.05.016},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Asymmetry,Direct mapping,Hippocampal surface,Implicit representation,Intrinsic shape context,Level set,Shape analysis,Temporal changes},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {792--807},
publisher = {Academic Press},
title = {{Direct mapping of hippocampal surfaces with intrinsic shape context}},
volume = {37},
year = {2007}
}


@article{Hochreiter1998,
abstract = {Recurrent nets are in principle capable to store past inputs to produce the currently desired output. Because of this property recurrent nets are used in time series prediction and process control. Practical applications involve temporal dependencies spanning many time steps, e.g. between relevant inputs and desired outputs. In this case, however, gradient based learning methods take too much time. The extremely increased learning time arises because the error vanishes as it gets propagated back. In this article the decaying error flow is theoretically analyzed. Then methods trying to overcome vanishing gradients are briefly discussed. Finally, experiments comparing conventional algorithms and alternative methods are presented. With advanced methods long time lag problems can be solved in reasonable time.},
author = {Hochreiter, Sepp},
doi = {10.1142/S0218488598000094},
issn = {02184885},
journal = {Int. J. Uncertainty, Fuzziness Knowlege-Based Syst.},
keywords = {Long Short-Term Memory,Long-term dependencies,Recurrent neural nets,Vanishing gradient},
mendeley-groups = {PhDThesis/VAE},
month = {nov},
number = {2},
pages = {107--116},
publisher = {World Scientific Publishing Co. Pte Ltd},
title = {{The vanishing gradient problem during learning recurrent neural nets and problem solutions}},
volume = {6},
year = {1998}
}


@article{Miller2015,
abstract = {This paper examines MRI analysis of neurodegeneration in Alzheimer's Disease (AD) in a network of structures within the medial temporal lobe using diffeomorphometry methods coupled with high-field atlasing in which the entorhinal cortex is partitioned into eight subareas. The morphometry markers for three groups of subjects (controls, preclinical AD, and symptomatic AD) are indexed to template coordinates measured with respect to these eight subareas. The location and timing of changes are examined within the subareas as it pertains to the classic Braak and Braak staging by comparing the three groups. We demonstrate that the earliest preclinical changes in the population occur in the lateral most sulcal extent in the entorhinal cortex (alluded to as transentorhinal cortex by Braak and Braak), and then proceeds medially which is consistent with the Braak and Braak staging. We use high-field 11T atlasing to demonstrate that the network changes are occurring at the junctures of the substructures in this medial temporal lobe network. Temporal progression of the disease through the network is also examined via changepoint analysis, demonstrating earliest changes in entorhinal cortex. The differential expression of rate of atrophy with progression signaling the changepoint time across the network is demonstrated to be signaling in the intermediate caudal subarea of the entorhinal cortex, which has been noted to be proximal to the hippocampus. This coupled to the findings of the nearby basolateral involvement in amygdala demonstrates the selectivity of neurodegeneration in early AD.},
author = {Miller, Michael I and Ratnanather, J Tilak and Tward, Daniel J and Brown, Timothy and Lee, David S and Ketcha, Michael and Mori, Kanami and Wang, Mei Cheng and Mori, Susumu and Albert, Marilyn S and Younes, Laurent and {BIOCARD Research Team}},
doi = {10.3389/fbioe.2015.00054},
issn = {22964185},
journal = {Front. Bioeng. Biotechnol.},
keywords = {Cell-cell hypothesis,Diffeomorphometry,Entorhinal cortex,Preclinical Alzheimer's disease,Shape},
mendeley-groups = {PhDThesis/Hippo},
number = {MAY},
pages = {54},
publisher = {Frontiers Media S.A.},
title = {{Network neurodegeneration in Alzheimer's disease via MRI based shape diffeomorphometry and high-field atlasing}},
volume = {3},
year = {2015}
}
@article{Cury2018,
abstract = {In this paper, we propose an approach for template-based shape analysis of large datasets, using diffeomorphic centroids as atlas shapes. Diffeomorphic centroid methods fit in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework and use kernel metrics on currents to quantify surface dissimilarities. The statistical analysis is based on a Kernel Principal Component Analysis (Kernel PCA) performed on the set of initial momentum vectors which parametrize the deformations. We tested the approach on different datasets of hippocampal shapes extracted from brain magnetic resonance imaging (MRI), compared three different centroid methods and a variational template estimation. The largest dataset is composed of 1,000 surfaces, and we are able to analyse this dataset in 26 h using a diffeomorphic centroid. Our experiments demonstrate that computing diffeomorphic centroids in place of standard variational templates leads to similar shape analysis results and saves around 70{\%} of computation time. Furthermore, the approach is able to adequately capture the variability of hippocampal shapes with a reasonable number of dimensions, and to predict anatomical features of the hippocampus, only present in 17{\%} of the population, in healthy subjects.},
author = {Cury, Claire and Glaun{\`{e}}s, Joan A and Toro, Roberto and Chupin, Marie and Schumann, Gunter and Frouin, Vincent and Poline, Jean-Baptiste and Colliot, Olivier},
doi = {10.3389/fnins.2018.00803},
issn = {1662-453X},
journal = {Front. Neurosci.},
keywords = {Atlas,Computational anatomy,Hippocampus,IHI,LDDMM,Morphometry,Riemannian barycentres,Shape analysis},
mendeley-groups = {PhDThesis/Hippo},
month = {nov},
number = {NOV},
pages = {803},
publisher = {Frontiers Media S.A.},
title = {{Statistical Shape Analysis of Large Datasets Based on Diffeomorphic Iterative Centroids}},
volume = {12},
year = {2018}
}
@article{Vaillant2007,
abstract = {This paper describes the application of large deformation diffeomorphic metric mapping to cortical surfaces based on the shape and geometric properties of subregions of the superior temporal gyrus in the human brain. The anatomical surfaces of the cortex are represented as triangulated meshes. The diffeomorphic matching algorithm is implemented by defining a norm between the triangulated meshes, based on the algorithms of Vaillant and Glaun{\`{e}}s. The diffeomorphic correspondence is defined as a flow of the extrinsic three dimensional coordinates containing the cortical surface that registers the initial and target geometry by minimizing the norm. The methods are demonstrated in 40 high-resolution MRI cortical surfaces of planum temporale (PT) constructed from subsets of the superior temporal gyrus (STG). The effectiveness of the algorithm is demonstrated via the Euclidean positional distance, distance of normal vectors, and curvature before and after the surface matching as well as the comparison with a landmark matching algorithm. The results demonstrate that both the positional and shape variability of the anatomical configurations are being represented by the diffeomorphic maps. {\textcopyright}2006 Elsevier Inc. All rights reserved.},
author = {Vaillant, Marc and Qiu, Anqi and Glaun{\`{e}}s, Joan and Miller, Michael I},
doi = {10.1016/j.neuroimage.2006.08.053},
issn = {10538119},
journal = {Neuroimage},
keywords = {Diffeomorphics,Large deformation,Normal vector,Surface matching},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {3},
pages = {1149--1159},
publisher = {Academic Press},
title = {{Diffeomorphic metric surface mapping in subregion of the superior temporal gyrus}},
volume = {34},
year = {2007}
}
@inproceedings{Bone2018a,
author = {B{\^{o}}ne, Alexandre and Louis, Maxime and Martin, Beno{\^{i}}t and Durrleman, Stanley},
booktitle = {ShapeMI, Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-030-04747-4},
isbn = {978-3-030-04746-7},
keywords = {computational anatomy,large deformation diffeomorphic metric,mapping,open-source software,statistical shape analysis},
mendeley-groups = {PhDThesis/Hippo},
pages = {3--13},
title = {{Deformetrica 4: An Open-Source Software for Statistical Shape Analysis}},
volume = {11167},
year = {2018}
}
@article{Parker2019,
abstract = {The most common presentation of early onset Alzheimer's disease (EOAD – defined as symptom onset {\textless}65 years) is with progressive episodic memory impairment – amnestic or typical Alzheimer's disease (tAD). However, EOAD is notable for its phenotypic heterogeneity, with posterior cortical atrophy (PCA) – characterised by prominent higher-order visual processing deficits and relative sparing of episodic memory – the second most common canonical phenotype. The hippocampus, which comprises a number of interconnected anatomically and functionally distinct subfields, is centrally involved in Alzheimer's disease and is a crucial mediator of episodic memory. The extent to which volumes of individual hippocampal subfields differ between different phenotypes in EOAD is unclear. The aim of this analysis was to investigate the hypothesis that patients with a PCA phenotype will exhibit differences in specific hippocampal subfield volumes compared to tAD. We studied 63 participants with volumetric T1-weighted MRI performed on the same 3T scanner: 39 EOAD patients [27 with tAD and 12 with PCA] and 24 age-matched controls. Volumetric estimates of the following hippocampal subfields for each participant were obtained using Freesurfer version 6.0: CA1, CA2/3, CA4, presubiculum, subiculum, hippocampal tail, parasubiculum, the molecular and granule cell layers of the dentate gryus (GCMLDG), the molecular layer, and the hippocampal amygdala transition area (HATA). Linear regression analyses comparing mean hippocampal subfield volumes between groups, adjusting for age, sex and head size, were performed. Using a Bonferonni-corrected p-value of p {\textless}0.0025, compared to controls, tAD was associated with atrophy in all hippocampal regions, except the parasubiculum. In PCA patients compared to controls, the strongest evidence for volume loss was in the left presubiclum, right subiculum, right GCMLDG, right molecular layer and the right HATA. Compared to PCA, patients with tAD had strong evidence for smaller volumes in left CA1 and left hippocampal tail. In conclusion, these data provide evidence that hippocampal subfield volumes differ in different phenotypes of EOAD.},
author = {Parker, Thomas D and Slattery, Catherine F and Yong, Keir X X and Nicholas, Jennifer M and Paterson, Ross W and Foulkes, Alexander J M and Malone, Ian B and Thomas, David L and Cash, David M and Crutch, Sebastian J and Fox, Nick C and Schott, Jonathan M},
doi = {10.1016/j.nicl.2018.101632},
issn = {22131582},
journal = {NeuroImage Clin.},
keywords = {Atypical Alzheimer's disease,CA1,Early-onset Alzheimer's disease,Hippocampal subfields,Posterior cortical atrophy,Presubiculum},
mendeley-groups = {PhDThesis/Hippo},
pages = {101632},
publisher = {Elsevier Inc.},
title = {{Differences in hippocampal subfield volume are seen in phenotypic variants of early onset Alzheimer's disease}},
volume = {21},
year = {2019}
}
@article{Gao2014,
abstract = {In the last two decades, the statistical analysis of shape has become an actively studied field and finds applications in a wide range of areas. In addition to algorithmic development, many researchers have distributed end-user orientated toolboxes, which further enable the utilization of the algorithms in an "off the shelf" fashion. However, there is little work on the evaluation and validation of these techniques, which poses a rather serious challenge when interpreting their results. To address this lack of validation, we design a validation framework and then use it to test some of the most widely used toolboxes. Our initial results show inconsistencies and disagreement among four different methods. We believe this type of analysis to be critical not only for the community of algorithm designers but also perhaps more importantly to researchers who use these tools without knowing the algorithm details and seek objective criteria for tool selection.},
annote = {Semblant a Goparaju et al.},
author = {Gao, Yi and Riklin-Raviv, Tammy and Bouix, Sylvain},
doi = {10.1002/hbm.22525},
issn = {10970193},
journal = {Hum. Brain Mapp.},
keywords = {Algorithm evaluation,Reproducibility,Statistical shape analysis},
mendeley-groups = {PhDThesis/Hippo},
month = {oct},
number = {10},
pages = {4965--4978},
publisher = {John Wiley and Sons Inc.},
title = {{Shape analysis, a field in need of careful validation}},
volume = {35},
year = {2014}
}
@inproceedings{Goparaju2018,
abstract = {Statistical shape modeling (SSM) has proven useful in many areas of biology and medicine as a new generation of morphometric approaches for the quantitative analysis of anatomical shapes. Recently, the increased availability of high-resolution in vivo images of anatomy has led to the development and distribution of open-source computational tools to model anatomical shapes and their variability within populations with unprecedented detail and statistical power. Nonetheless, there is little work on the evaluation and validation of such tools as related to clinical applications that rely on morphometric quantifications for treatment planning. To address this lack of validation, we systematically assess the outcome of widely used off-the-shelf SSM tools, namely ShapeWorks, SPHARM-PDM, and Deformetrica, in the context of designing closure devices for left atrium appendage (LAA) in atrial fibrillation (AF) patients to prevent stroke, where an incomplete LAA closure may be worse than no closure. This study is motivated by the potential role of SSM in the geometric design of closure devices, which could be informed by population-level statistics, and patient-specific device selection, which is driven by anatomical measurements that could be automated by relating patient-level anatomy to population-level morphometrics. Hence, understanding the consequences of different SSM tools for the final analysis is critical for the careful choice of the tool to be deployed in real clinical scenarios. Results demonstrate that estimated measurements from ShapeWorks model are more consistent compared to models from Deformetrica and SPHARM-PDM. Furthermore, ShapeWorks and Deformetrica shape models capture clinically relevant population-level variability compared to SPHARM-PDM models.},
annote = {{\'{E}}s un paper de comparaci{\'{o}} de shapes tools i models.

Pot ser interessant les referencies. La majoria ja les tinc.},
archivePrefix = {arXiv},
arxivId = {1810.03987},
author = {Goparaju, Anupama and Csecs, Ibolya and Morris, Alan and Kholmovski, Evgueni and Marrouche, Nassir and Whitaker, Ross and Elhabian, Shireen},
booktitle = {ShapeMI, Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-030-04747-4_2},
eprint = {1810.03987},
isbn = {9783030047467},
issn = {16113349},
keywords = {Correspondence optimization,Evaluation,Statistical shape models,Surface parameterization},
mendeley-groups = {PhDThesis/Hippo},
pages = {14--27},
publisher = {Springer Verlag},
title = {{On the Evaluation and Validation of Off-the-Shelf Statistical Shape Modeling Tools: A Clinical Application}},
volume = {11167},
year = {2018}
}
@article{Shakeri2016a,
abstract = {Studying morphological changes of subcortical structures often predicate neurodevelopmental and neurodegenerative diseases, such as Alzheimer's disease and schizophrenia. Hence, methods for quantifying morphological variations in the brain anatomy, including groupwise shape analyses, are becoming increasingly important for studying neurological disorders. In this paper, a novel groupwise shape analysis approach is proposed to detect regional morphological alterations in subcortical structures between two study groups, e.g., healthy and pathological subjects. The proposed scheme extracts smoothed triangulated surface meshes from segmented binary maps, and establishes reliable point-to-point correspondences among the population of surfaces using a spectral matching method. Mean curvature features are incorporated in the matching process, in order to increase the accuracy of the established surface correspondence. The mean shapes are created as the geometric mean of all surfaces in each group, and a distance map between these shapes is used to characterize the morphological changes between the two study groups. The resulting distance map is further analyzed to check for statistically significant differences between two populations. The performance of the proposed framework is evaluated on two separate subcortical structures (hippocampus and putamen). Furthermore, the proposed methodology is validated in a clinical application for detecting abnormal subcortical shape variations in Alzheimer's disease. Experimental results show that the proposed method is comparable to state-of-the-art algorithms, has less computational cost, and is more sensitive to small morphological variations in patients with neuropathologies.},
author = {Shakeri, Mahsa and Lombaert, Herve and Datta, Alexandre N and Oser, Nadine and L{\'{e}}tourneau-Guillon, Laurent and Lapointe, Laurence Vincent and Martin, Florence and Malfait, Domitille and Tucholka, Alan and Lipp{\'{e}}, Sarah and Kadoury, Samuel},
doi = {10.1016/j.compmedimag.2016.03.001},
issn = {18790771},
journal = {Comput. Med. Imaging Graph.},
keywords = {Alzheimer's disease,Groupwise shape analysis,Spectral matching,Subcortical morphology},
mendeley-groups = {PhDThesis/Hippo},
pages = {58--71},
title = {{Statistical shape analysis of subcortical structures using spectral matching}},
volume = {52},
year = {2016}
}
@article{Styner2006,
abstract = {Shape analysis has become of increasing interest to the neuroimaging community due to its potential to precisely locate morphological changes between healthy and pathological structures. This manuscript presents a comprehensive set of tools for the computation of 3D structural statistical shape analysis. It has been applied in several studies on brain morphometry, but can potentially be employed in other 3D shape problems. Its main limitations is the necessity of spherical topology.The input of the proposed shape analysis is a set of binary segmentation of a single brain structure, such as the hippocampus or caudate. These segmentations are converted into a corresponding spherical harmonic description (SPHARM), which is then sampled into a triangulated surfaces (SPHARM-PDM). After alignment, differences between groups of surfaces are computed using the Hotelling T(2) two sample metric. Statistical p-values, both raw and corrected for multiple comparisons, result in significance maps. Additional visualization of the group tests are provided via mean difference magnitude and vector maps, as well as maps of the group covariance information.The correction for multiple comparisons is performed via two separate methods that each have a distinct view of the problem. The first one aims to control the family-wise error rate (FWER) or false-positives via the extrema histogram of non-parametric permutations. The second method controls the false discovery rate and results in a less conservative estimate of the false-negatives.},
annote = {Base paper de SPHARM PDM. Citar i explicar breument, {\'{e}}s important.

Molt semblant al que fem.},
author = {Styner, Martin and Oguz, Ipek and Xu, Shun and Brechb{\"{u}}hler, Christian and Pantazis, Dimitrios and Levitt, James J and Shenton, Martha E and Gerig, Guido},
issn = {2327-770X},
journal = {Insight J.},
mendeley-groups = {PhDThesis/Hippo},
issue = {1071},
pages = {242--250},
pmid = {21941375},
publisher = {NIH Public Access},
title = {{Framework for the Statistical Shape Analysis of Brain Structures using SPHARM-PDM.}},
year = {2006}
}

@article{LeCun2015,
abstract = {Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.},
archivePrefix = {arXiv},
arxivId = {arXiv:1312.6184v5},
author = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},
doi = {10.1038/nature14539},
eprint = {arXiv:1312.6184v5},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/LeCun et al. - 2015 - Deep learning.pdf:pdf},
isbn = {3135786504},
issn = {0028-0836},
journal = {Nature},
mendeley-groups = {PHD/Reviews,PhDThesis/Introduction},
number = {7553},
pages = {436--444},
pmid = {26017442},
title = {{Deep learning}},
volume = {521},
year = {2015}
}



@article{Joshi2016,
abstract = {Shape morphometry of subcortical surfaces plays an important role in analyzing normal developmental changes as well as in quantifying disease-related effects in the human brain. We present a geometric approach for joint registration, deformation, and statistical analysis of shapes of subcortical surfaces. Here, subcortical surfaces are mathematically represented by vector-fields, termed square-root normal vector fields (SRNFs), on the spherical domain. The SRNF representation allows modeling of the action of the re-parameterization group to by isometries under the standard Hilbert norm, and thus enables an elastic shape analysis. This elastic analysis results in optimal deformations between shapes and helps to quantify shape differences using geodesic lengths. Importantly, the joint registration of observed shapes in a shape class removes nuisance variability due to mis-registration in the shape data and results in parsimonious statistical shape models with improved inferences for characterizing population-based subcortical structural variability. We demonstrate the ideas for shape matching and statistical analysis of hippocampal shapes for (N=120) subjects from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset. Specifically, we present results for assessing group differences both by using global descriptors such as principal components and local descriptors such as deformations induced by the tangent vectors from the mean shapes to the individuals.},
author = {Joshi, Shantanu H and Xie, Qian and Kurtek, Sebastian and Srivastava, Anuj and Laga, Hamid},
doi = {10.1109/DICTA.2016.7797087},
isbn = {9781509028962},
journal = {2016 Int. Conf. Digit. Image Comput. Tech. Appl. DICTA 2016},
mendeley-groups = {PhDThesis/Hippo},
title = {{Surface Shape Morphometry for Hippocampal Modeling in Alzheimer's Disease}},
year = {2016}
}
@article{Beg2005,
abstract = {This paper examine the Euler-Lagrange equations for the solution of the large deformation diffeomorphic metric mapping problem studied in Dupuis et al. (1998) and Trouv{\'{e}} (1995) in which two images I0, I1 are given and connected via the diffeomorphic change of coordinates I 0 o $\phi$-1 = I1 where $\phi$ = $\phi$1 is the end point at t = 1 of curve $\phi$t, t ∈ [0, 1] satisfying $\phi$t, = vt($\phi$t), t ∈ [0, 1] with $\phi$0 = id. The variational problem takes the form argmin $\nu$: $\phi$̇t=$\nu$1($\phi$1) (∫01 ∥$\nu$t∥V2dt + ∥I0o $\phi$1-1 - I 1∥L22 where ∥$\nu$t∥V is an appropriate Sobolev norm on the velocity field $\nu$t({\textperiodcentered}), and the second term enforces matching of the images with ∥{\textperiodcentered}∥L2 representing the squared-error norm. In this paper we derive the Euler-Lagrange equations characterizing the minimizing vector fields $\nu$t, t ∈ [0, 1] assuming sufficient smoothness of the norm to guarantee existence of solutions in the space of diffeomorphisms. We describe the implementation of the Euler equations using semi-lagrangian method of computing particle flows and show the solutions for various examples. As well, we compute the metric distance on several anatomical configurations as measured by ∫01 ∥$\nu$t∥V dt on the geodesic shortest paths.},
author = {Beg, M Faisal and Miller, Michael I and Trouv{\'{e}}, Alain and Younes, Laurent},
doi = {10.1023/B:VISI.0000043755.93987.aa},
issn = {09205691},
journal = {Int. J. Comput. Vis.},
keywords = {Computational anatomy,Deformable template,Euler-lagrange equation,Metrics,Variational optimization},
mendeley-groups = {PhDThesis/Hippo},
number = {2},
pages = {139--157},
title = {{Computing large deformation metric mappings via geodesic flows of diffeomorphisms}},
volume = {61},
year = {2005}
}
@article{Shen2003,
abstract = {Surface-based representation and classification techniques are studied for hippocampal shape analysis. The goal is twofold: (1) develop a new framework of salient feature extraction and accurate classification for 3D shape data: (2) detect hippocampal abnormalities in schizophrenia using this technique. A fine-scale spherical harmonic expansion is employed to describe a closed 3D surface object. The expansion can then easily be transformed to extract only shape information (i.e., excluding translation, rotation, and scaling) and create a shape descriptor comparable across different individuals. This representation captures shape features and is flexible enough to do shape modeling, identify statistical group differences, and generate similar synthetic shapes. Principal component analysis is used to extract a small number of independent features from high dimensional shape descriptors, and Fisher's linear discriminant is applied for pattern classification. This framework is shown to be able to perform well in distinguishing clear group differences as well as small and noisy group differences using simulated shape data. In addition, the application of this technique to real data indicates that group shape differences exist in hippocampi between healthy controls and schizophrenic patients.},
author = {Shen, Li and Ford, James and Makedon, Fillia and Saykin, Andrew},
doi = {10.1117/12.480851},
issn = {0277786X},
journal = {Proc. SPIE 5032, Med. Imaging 2003 Image Process},
keywords = {classification,hippocampus,mri,shape analysis,surface modeling},
mendeley-groups = {PhDThesis/Hippo},
pages = {253},
title = {{Hippocampal shape analysis: surface-based representation and classification}},
year = {2003}
}
@article{Heimann2009,
abstract = {Statistical shape models (SSMs) have by now been firmly established as a robust tool for segmentation of medical images. While 2D models have been in use since the early 1990s, wide-spread utilization of three-dimensional models appeared only in recent years, primarily made possible by breakthroughs in automatic detection of shape correspondences. In this article, we review the techniques required to create and employ these 3D SSMs. While we concentrate on landmark-based shape representations and thoroughly examine the most popular variants of Active Shape and Active Appearance models, we also describe several alternative approaches to statistical shape modeling. Structured into the topics of shape representation, model construction, shape correspondence, local appearance models and search algorithms, we present an overview of the current state of the art in the field. We conclude with a survey of applications in the medical field and a discussion of future developments. {\textcopyright}2009 Elsevier B.V. All rights reserved.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Heimann, Tobias and Meinzer, Hans Peter},
doi = {10.1016/j.media.2009.05.004},
eprint = {NIHMS150003},
isbn = {1361-8415},
issn = {13618415},
journal = {Med. Image Anal.},
keywords = {Active Appearance model,Active Shape model,Deformable surface,Statistical shape model},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {543--563},
pmid = {19525140},
publisher = {Elsevier},
title = {{Statistical shape models for 3D medical image segmentation: A review}},
volume = {13},
year = {2009}
}
@article{Cacciaglia2019,
author = {Cacciaglia, Raffaele and Molinuevo, Jos{\'{e}} Luis and Falc{\'{o}}n, Carles and S{\'{a}}nchez-Benavides, Gonzalo and Gramunt, Nina and Brugulat-Serrat, Anna and Esteller, Manel and Mor{\'{a}}n, Sebasti{\'{a}}n and Fauria, Karine and Gispert, Juan Domingo},
doi = {10.1016/j.nicl.2019.101818},
issn = {22131582},
journal = {NeuroImage Clin.},
keywords = {APOE-$\epsilon$4,Alzheimer's disease,Cognitive performance,Healthy participants,Voxel-based morphometry},
mendeley-groups = {PhDThesis/Hippo},
number = {April},
pages = {101818},
publisher = {Elsevier},
title = {{APOE-$\epsilon$4 risk variant for Alzheimer's disease modifies the association between cognitive performance and cerebral morphology in healthy middle-aged individuals}},
volume = {23},
year = {2019}
}
@article{Cacciaglia2018,
abstract = {Introduction: Apolipoprotein E (APOE)-e4 is the major genetic risk factor for Alzheimer's disease. However, the dose-dependent impact of this allele on brain morphology of healthy individuals remains unclear. Methods: We analyzed gray matter volumes (GMvs) in a sample of 533 healthy middle-aged individuals with a substantial representation of e4-carriers (207 heterozygotes and 65 homozygotes). Results: We found APOE-e4 additive GMv reductions in the right hippocampus, caudate, precentral gyrus, and cerebellar crus. In these regions, the APOE genotype interacted with age, with homozygotes displaying lower GMv after the fifth decade of life. APOE-e4 was also associated to greater GMv in the right thalamus, left occipital gyrus, and right frontal cortex. Discussion: Our data indicate that APOE-e4 exerts additive effects on GMv in regions relevant for Alzheimer's disease pathophysiology already in healthy individuals. These findings elucidate the mechanisms underlying the increased Alzheimer's disease risk in e4-carriers, suggesting a dose-dependent disease vulnerability on the brain structure level.},
annote = {Paper important, important entendre tots els conceptes que es relaten aqu{\'{i}}. Interessant estudiar totes les estad{\'{i}}stiques descrites.},
author = {Cacciaglia, Raffaele and Molinuevo, Jos{\'{e}} Luis and Falc{\'{o}}n, Carles and Brugulat-Serrat, Anna and S{\'{a}}nchez-Benavides, Gonzalo and Gramunt, Nina and Esteller, Manel and Mor{\'{a}}ne, Seb{\'{a}}stian and Minguill{\'{o}}na, Carolina and Fauriaa, Karine and Gispert, Juan Domingo},
doi = {10.1016/j.jalz.2018.01.016},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {APOE-e4,Aging,Alzheimer's disease,Gray matter volumes,Healthy individuals,Voxel-based morphometry},
mendeley-groups = {PhDThesis/Hippo},
month = {jul},
number = {7},
pages = {902--912},
pmid = {29605385},
publisher = {Elsevier},
title = {{Effects of APOE-$\epsilon$4 allele load on brain morphology in a cohort of middle-aged healthy individuals with enriched genetic risk for Alzheimer's disease}},
volume = {14},
year = {2018}
}
@article{Coupe2017,
author = {Coup{\'{e}}, Pierrick and Catheline, Gwenaelle and Lanuza, Enrique and Manj{\'{o}}n, Jos{\'{e}} Vicente},
doi = {10.1002/hbm.23743},
issn = {10659471},
journal = {Hum. Brain Mapp.},
keywords = {MRI segmentation,aging,brain trajectory,lifespan,maturation,patch‐based processing},
mendeley-groups = {PhDThesis/Hippo},
month = {nov},
number = {11},
pages = {5501--5518},
publisher = {Wiley-Blackwell},
title = {{Towards a unified analysis of brain maturation and aging across the entire lifespan: A MRI analysis}},
volume = {38},
year = {2017}
}
@article{Styner2004,
abstract = {Statistical shape analysis has become of increasing interest to the neuroimaging community due to its potential to precisely locate morphological changes and thus potentially discriminate between healthy and pathological structures. This paper describes a combined boundary and medial shape analysis based on two different shape descriptions applied to a study of the hippocampus shape abnormalities in schizophrenia. The first shape description is the sampled boundary implied by the spherical harmonic SPHARM description. The second one is the medial shape description called M-rep. Both descriptions are sampled descriptions with inherent point correspondence. Their shape analysis is based on computing differences from an average template structure analyzed using standard group mean difference tests. The results of the global and local shape analysis in the presented hippocampus study exhibit the same patterns for the boundary and the medial analysis. The results strongly suggest that the normalized hippocampal shape of the schizophrenic group is different from the control group, most significantly as a deformation difference in the tail region. {\textcopyright}2004 Elsevier B.V. All rights reserved.},
author = {Styner, Martin and Lieberman, Jeffrey A and Pantazis, Dimitrios and Gerig, Guido},
doi = {10.1016/j.media.2004.06.004},
issn = {13618415},
journal = {Med. Image Anal.},
keywords = {Brain morphometry,Medial shape description,Medical image analysis,Schizophrenia,Shape analysis},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {197--203},
publisher = {Elsevier},
title = {{Boundary and medial shape analysis of the hippocampus in schizophrenia}},
volume = {8},
year = {2004}
}
@article{Adler2018,
abstract = {There has been increasing interest in hippocampal subfield morphometry in aging and disease using in vivo MRI. However, research on in vivo morphometry is hampered by the lack of a definitive reference model describing regional effects of aging and disease pathology on the hippocampus. To address this limitation, we built a 3D probabilistic atlas of the hippocampus combining postmortem MRI with histology, allowing us to investigate Alzheimer's disease (AD)-related effects on hippocampal subfield morphometry, derived from histology. Our results support the hypothesis of differential involvement of hippocampal subfields in AD, providing further impetus for more granular study of the hippocampus in aging and disease during life. Furthermore, this atlas provides an important anatomical reference for hippocampal subfield research. Although the hippocampus is one of the most studied structures in the human brain, limited quantitative data exist on its 3D organization, anatomical variability, and effects of disease on its subregions. Histological studies provide restricted reference information due to their 2D nature. In this paper, high-resolution (∼200 × 200 × 200 $\mu$m3) ex vivo MRI scans of 31 human hippocampal specimens are combined using a groupwise diffeomorphic registration approach into a 3D probabilistic atlas that captures average anatomy and anatomic variability of hippocampal subfields. Serial histological imaging in 9 of the 31 specimens was used to label hippocampal subfields in the atlas based on cytoarchitecture. Specimens were obtained from autopsies in patients with a clinical diagnosis of Alzheimer's disease (AD; 9 subjects, 13 hemispheres), of other dementia (nine subjects, nine hemispheres), and in subjects without dementia (seven subjects, nine hemispheres), and morphometric analysis was performed in atlas space to measure effects of age and AD on hippocampal subfields. Disproportional involvement of the cornu ammonis (CA) 1 subfield and stratum radiatum lacunosum moleculare was found in AD, with lesser involvement of the dentate gyrus and CA2/3 subfields. An association with age was found for the dentate gyrus and, to a lesser extent, for CA1. Three-dimensional patterns of variability and disease and aging effects discovered via the ex vivo hippocampus atlas provide information highly relevant to the active field of in vivo hippocampal subfield imaging.},
author = {Adler, Daniel H and Wisse, Laura E M and Ittyerah, Ranjit and Pluta, John B and Ding, Song-Lin and Xie, Long and Wang, Jiancong and Kadivar, Salmon and Robinson, John L and Schuck, Theresa and Trojanowski, John Q and Grossman, Murray and Detre, John A and Elliott, Mark A and Toledo, Jon B and Liu, Weixia and Pickup, Stephen and Miller, Michael I and Das, Sandhitsu R and Wolk, David A and Yushkevich, Paul A},
doi = {10.1073/pnas.1801093115},
issn = {0027-8424},
journal = {Proc. Natl. Acad. Sci.},
mendeley-groups = {PhDThesis/Hippo},
number = {17},
pages = {201801093},
pmid = {29592955},
title = {{Characterizing the human hippocampus in aging and Alzheimer's disease using a computational atlas derived from ex vivo MRI and histology}},
year = {2018}
}
@article{Shi2014,
abstract = {The apolipoprotein E (APOE) e4 allele is the most prevalent genetic risk factor for Alzheimer's disease (AD). Hippocampal volumes are generally smaller in AD patients carrying the e4 allele compared to e4 non-carriers. Here we examined the effect of APOE e4 on hippocampal morphometry in a large imaging database – the Alzheimer's Disease Neuroimaging Initiative (ADNI). We automatically segmented and constructed hippocampal surfaces from the baseline MR images of 725 subjects with known APOE genotype information including 167 with AD, 354 with mild cognitive impairment (MCI), and 204 normal controls. High-order correspondences between hippocampal surfaces were enforced across subjects with a novel inverse consistent surface fluid registration method. Multivariate statistics consisting of multivariate tensor-based morphometry (mTBM) and radial distance were computed for surface deformation analysis. Using Hotelling's T2 test, we found significant morphological deformation in APOE e4 carriers relative to non-carriers in the entire cohort as well as in the non-demented (pooled MCI and control) subjects, affecting the left hippocampus more than the right, and this effect was more pronounced in e4 homozygotes than heterozygotes. Our findings are consistent with previous studies that showed e4 carriers exhibit accelerated hippocampal atrophy; we extend these findings to a novel measure of hippocampal morphometry. Hippocampal morphometry has significant potential as an imaging biomarker of early stage AD.},
author = {Shi, Jie and Lepor{\'{e}}, Natasha and Gutman, Boris A and Thompson, Paul M and Baxter, Leslie C and Caselli, Richard L and Wang, Yaling},
doi = {10.1002/hbm.22447},
journal = {Hum. Brain Mapp.},
keywords = {APOE e4,Alzheimer's disease,MRI,hippocampus,multivariate tensor-based morphometry (mTBM)},
mendeley-groups = {PhDThesis/Hippo},
number = {8},
pages = {3903--3918},
title = {{Genetic influence of APOE4 genotype on hippocampal morphometry - an N=725 surface-based ADNI study}},
volume = {35},
year = {2014}
}
@article{Wang2013,
abstract = {Groupwise segmentation that simultaneously segments a set of images and ensures that the segmentations for the same structure of interest from different images are consistent usually can achieve better performance than segmenting each image independently. Our main contribution is that we adopt the groupwise segmentation framework to improve the performance of multi-atlas label fusion. We develop a novel statistical model to allow this extension. Comparing to previous atlas propagation and groupwise segmentation work, one key novelty of our method is that the error produced during label propagation is explicitly addressed in the joint label fusion framework. Experiments on hippocampus segmentation in magnetic resonance images show the effectiveness of the new groupwise segmentation technique.},
author = {Wang, Hongzhi and Yushkevich, Paul A},
doi = {10.3389/fninf.2013.00027},
issn = {1662-5196},
journal = {Front. Neuroinform.},
keywords = {Insight-Toolkit,corrective learning,joint label fusion,multi-atlas label fusion,open source implementation},
mendeley-groups = {PhDThesis/Hippo},
pages = {27},
pmid = {24319427},
publisher = {Frontiers Media SA},
title = {{Multi-atlas segmentation with joint label fusion and corrective learning—an open source implementation}},
volume = {7},
year = {2013}
}
@article{Hotelling2007,
abstract = {confidence},
author = {Hotelling, Harold},
doi = {10.1214/aoms/1177732979},
issn = {0003-4851},
journal = {Ann. Math. Stat.},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
pages = {360--378},
publisher = {Springer, New York, NY},
title = {{The Generalization of Student's Ratio}},
volume = {2},
year = {1931}
}
@article{Frisoni2008,
abstract = {Histological studies have suggested differing involvement of the hippocampal subfields in ageing and in Alzheimer's disease. The aim of this study was to assess in vivo local hippocampal changes in ageing and Alzheimer's disease based on high resolution MRI at 3 Tesla. T(1)-weighted images were acquired from 19 Alzheimer's disease patients [age 76 +/- 6 years, three males, Mini-Mental State Examination 13 +/- 4] and 19 controls (age 74 +/- 5 years, 11 males, Mini-Mental State Examination 29 +/- 1). The hippocampal formation was isolated by manual tracing. Radial atrophy mapping was used to assess group differences and correlations by averaging hippocampal shapes across subjects using 3D parametric surface mesh models. Percentage difference, Pearson's r, and significance maps were produced. Hippocampal volumes were inversely correlated with age in older healthy controls (r = 0.56 and 0.6 to the right and left, respectively, P {\textless}0.05, corresponding to 14{\%} lower volume for every 10 years of older age from ages 65 to 85 years). Ageing-associated atrophy mapped to medial and lateral areas of the tail and body corresponding to the CA1 subfield and ventral areas of the head corresponding to the presubiculum. Significantly increased volume with older age mapped to a few small spots mainly located to the CA1 sector of the right hippocampus. Volumes were 35{\%} and 30{\%} smaller in Alzheimer's disease patients to the right and left (P {\textless}0.0005). Alzheimer's disease-associated atrophy mapped not only to CA1 areas of the body and tail corresponding to those also associated with age, but also to dorsal CA1 areas of the head unaffected by age. Regions corresponding to the CA2-3 fields were relatively spared in both ageing and Alzheimer's disease. Hippocampal atrophy in Alzheimer's disease maps to areas in the body and tail that partly overlap those affected by normal ageing. Specific areas in the anterior and dorsal CA1 subfield involved in Alzheimer's disease were not in normal ageing. These patterns might relate to differential neural systems involved in Alzheimer's disease and ageing.},
author = {Frisoni, Giovanni B and Ganzola, Rossana and Canu, Elisa and R{\"{u}}b, Udo and Pizzini, Francesca B and Alessandrini, Franco and Zoccatelli, Giada and Beltramello, Alberto and Caltagirone, Carlo and Thompson, Paul M},
doi = {10.1093/brain/awn280},
issn = {00068950},
journal = {Brain},
keywords = {3D-shape,Ageing,Alzheimer's disease,Hippocampus,Magnetic resonance},
mendeley-groups = {PhDThesis/Hippo},
number = {12},
pages = {3266--3276},
publisher = {Narnia},
title = {{Mapping local hippocampal changes in Alzheimer's disease and normal ageing with MRI at 3 Tesla}},
volume = {131},
year = {2008}
}
@article{Lorensen1987,
abstract = {We present a new algorithm, called marching cubes, that creates triangle models of constant density surfaces from 3D medical data. Using a divide-and-conquer approach to generate inter-slice connectivity, we create a case table that defines triangle topology. The algorithm processes the 3D medical data in scan-line order and calculates triangle vertices using linear interpolation. We find the gradient of the original data, normalize it, and use it as a basis for shading the models. The detail in images produced from the generated surface models is the result of maintaining the inter-slice connectivity, surface data, and gradient information present in the original 3D data. Results from computed tomography (CT), magnetic resonance (MR), and single-photon emission computed tomography (SPECT) illustrate the quality and functionality of marching cubes. We also discuss improvements that decrease processing time and add solid modeling capabilities.},
address = {New York, New York, USA},
author = {Lorensen, William E and Cline, Harvey E},
doi = {10.1145/37402.37422},
isbn = {0897912276},
issn = {00978930},
journal = {ACM SIGGRAPH Comput. Graph.},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {163--169},
publisher = {ACM Press},
title = {{Marching cubes: A high resolution 3D surface construction algorithm}},
volume = {21},
year = {1987}
}
@article{Fox1996,
author = {Fox, N C and Warrington, E K and Freeborough, P A and Hartikainen, P and Kennedy, A M and Stevens, J M and Rossor, M N},
doi = {10.1093/brain/119.6.2001},
issn = {0006-8950},
journal = {Brain},
keywords = {hippocampal formation,visual memory},
mendeley-groups = {PhDThesis/Hippo},
number = {6},
pages = {2001--2007},
publisher = {Narnia},
title = {{Presymptomatic hippocampal atrophy in Alzheimer's disease}},
volume = {119},
year = {1996}
}
@article{Gispert2015,
abstract = {The progression of Alzheimer's disease (AD) is characterized by complex trajectories of cerebral atrophy that are affected by interactions with age and apolipoprotein E allele $\epsilon$4 (APOE4) status. In this article, we report the nonlinear volumetric changes in gray matter across the full biological spectrum of the disease, represented by the AD-cerebrospinal fluid (CSF) index. This index reflects the subject's level of pathology and position along the AD continuum. We also evaluated the associated impact of the APOE4 genotype. The atrophy pattern associated with the AD-CSF index was highly symmetrical and corresponded with the typical AD signature. Medial temporal structures showed different atrophy dynamics along the progression of the disease. The bilateral parahippocampal cortices and a parietotemporal region extending from the middle temporal to the supramarginal gyrus presented an initial increase in volume which later reverted. Similarly, a portion of the precuneus presented a rather linear inverse association with the AD-CSF index whereas some other clusters did not show significant atrophy until index values corresponded to positive CSF tau values. APOE4 carriers showed steeper hippocampal volume reductions with AD progression. Overall, the reported atrophy patterns are in close agreement with those mentioned in previous findings. However, the detected nonlinearities suggest that there may be different pathological processes taking place at specific moments during AD progression and reveal the impact of the APOE4 allele.},
author = {Gispert, J D and Rami, L and S{\'{a}}nchez-Benavides, G and Falcon, C and Tucholka, A and Rojas, S and Molinuevo, J L},
doi = {10.1016/j.neurobiolaging.2015.06.027},
isbn = {0197-4580},
issn = {15581497},
journal = {Neurobiol. Aging},
keywords = {Amyloid,Biomarkers,Brain,MRI,Neuroinflammation,Tau,VBM},
mendeley-groups = {PhDThesis/Hippo},
month = {oct},
number = {10},
pages = {2687--2701},
pmid = {26239178},
publisher = {Elsevier},
title = {{Nonlinear cerebral atrophy patterns across the Alzheimer's disease continuum: Impact of APOE4 genotype}},
volume = {36},
year = {2015}
}
@article{Gori2017,
abstract = {We present a Bayesian framework for atlas construction of multi-object shape complexes comprised of both surface and curve meshes. It is general and can be applied to any parametric deformation framework and to all shape models with which it is possible to define probability density functions (PDF). Here, both curve and surface meshes are modelled as Gaussian random varifolds, using a finite-dimensional approximation space on which PDFs can be defined. Using this framework, we can automatically estimate the parameters balancing data-terms and deformation regularity, which previously required user tuning. Moreover, it is also possible to estimate a well-conditioned covariance matrix of the deformation parameters. We also extend the proposed framework to data-sets with multiple group labels. Groups share the same template and their deformation parameters are modelled with different distributions. We can statistically compare the groups'distributions since they are defined on the same space. We test our algorithm on 20 Gilles de la Tourette patients and 20 control subjects, using three sub-cortical regions and their incident white matter fiber bundles. We compare their morphological characteristics and variations using a single diffeomorphism in the ambient space. The proposed method will be integrated with the Deformetrica software package, publicly available at www.deformetrica.org.},
annote = {Bayesian methods per construir tlas de shapes. Integrat a Deformetrica.},
author = {Gori, Pietro and Colliot, Olivier and Marrakchi-Kacem, Linda and Worbe, Yulia and Poupon, Cyril and Hartmann, Andreas and Ayache, Nicholas and Durrleman, Stanley},
doi = {10.1016/j.media.2016.08.011},
issn = {13618423},
journal = {Med. Image Anal.},
keywords = {Atlas,Bayesian,Complex,Fiber bundle,Morphometry,Multi-object,Shape,Varifolds},
mendeley-groups = {PhDThesis/Hippo},
pages = {458--474},
publisher = {Elsevier B.V.},
title = {{A Bayesian framework for joint morphometry of surface and curve meshes in multi-object complexes}},
volume = {35},
year = {2017}
}
@phdthesis{Valero2017,
author = {Valero, Alicia},
mendeley-groups = {PhDThesis/Hippo},
number = {July},
school = {Universitat Pompeu Fabra},
title = {{Characterizing hippocampal morphology as a function of ApoE4 allele load in healthy middle-aged individuals}},
year = {2017}
}
@article{Li2017f,
abstract = {In this paper, by utilizing surface diffeomorphic deformations, we constructed and analyzed subcortical shape morphometric networks in 210 healthy control (HC) subjects and 175 subjects with Alzheimer's disease (AD), aiming to identify AD-induced abnormalities in the subcortical shape network. We quantitatively analyzed pertinent network attributes of the entire network and each node. Further to this, hierarchical analyses were performed; group comparisons were conducted at the structure level first and then the sub-region level. The bilateral amygdalae, hippocampi, as well as the thalamus were all divided into multiple functionally distinct sub-regions. From the structure level analysis, we found significant HC-vs-AD group differences in the average local efficiency and average global efficiency. In addition, the local nodal efficiencies between the right thalamus and all three of the right hippocampus, right amygdala, and left thalamus, as well as that between the left amygdala and left hippocampus, decreased significantly in AD. According to the sub-regional network analyses, we observed significant AD-induced local efficiency decreases between different sub-regions within the right hippocampus itself and between the subiculum of the right hippocampus and the sub-region of the right thalamus connecting to the temporal lobe, indicating a degradation of circuit between the hippocampus, thalamus, and temporal lobe. Statistical comparisons were performed using 40,000 non-parametric permutation tests, with false discovery rate correction employed for multiple comparison correction.},
annote = {Aqui potser mirar el tema de citacions?, nah tinc les que tinc},
author = {Li, Jingyuan and Gong, Yujing and Tang, Xiaoying},
doi = {10.1016/j.neuroscience.2017.10.011},
issn = {18737544},
journal = {Neuroscience},
keywords = {Alzheimer's disease,brain morphology network,shape network,sub-region,subcortical structures,surface deformation},
mendeley-groups = {PhDThesis/Hippo},
number = {October},
pages = {70--83},
publisher = {IBRO},
title = {{Hierarchical subcortical sub-regional shape network analysis in Alzheimer's disease}},
volume = {366},
year = {2017}
}
@article{Li2016,
abstract = {The apolipoprotein E (APOE) e4 genotype is a powerful risk factor for late-onset Alzheimer's disease (AD). In the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, we previously reported significant baseline structural differences in APOE e4 carriers relative to non-carriers, involving the left hippocampus more than the right-a difference more pronounced in e4 homozygotes than heterozygotes. We now examine the longitudinal effects of APOE genotype on hippocampal morphometry at 6-, 12- and 24-months, in the ADNI cohort. We employed a new automated surface registration system based on conformal geometry and tensor-based morphometry. Among different hippocampal surfaces, we computed high-order correspondences, using a novel inverse-consistent surface-based fluid registration method and multivariate statistics consisting of multivariate tensor-based morphometry (mTBM) and radial distance. At each time point, using Hotelling's T2 test, we found significant morphological deformation in APOE e4 carriers relative to non-carriers in the full cohort as well as in the non-demented (pooled MCI and control) subjects at each follow-up interval. In the complete ADNI cohort, we found greater atrophy of the left hippocampus than the right, and this asymmetry was more pronounced in e4 homozygotes than heterozygotes. These findings, combined with our earlier investigations, demonstrate an e4 dose effect on accelerated hippocampal atrophy, and support the enrichment of prevention trial cohorts with e4 carriers.},
author = {Li, Bolun and Shi, Jie and Gutman, Boris A and Baxter, Leslie C and Thompson, Paul M and Caselli, Richard J and Wang, Yalin},
doi = {10.1371/journal.pone.0152901},
isbn = {1932-6203},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Hippo},
number = {4},
pages = {1--26},
pmid = {27065111},
title = {{Influence of APOE genotype on hippocampal atrophy over time - An N=1925 surface-based ADNI study}},
volume = {11},
year = {2016}
}

@inproceedings{Rodrigues2014,
abstract = {The majority of existing computer-aided diagnosis (CAD) schemes for Alzheimer's disease (AD) rely on the analysis of biomarkers at a single time-point, ignoring the progressive nature of the disorder. Recently, a method was proposed by Gray et al. [1] for the multi-region analysis of longitudinal fluorodeoxyglucose positron emission tomography (FDG-PET) images which reported classification improvements by using regional signal intensities combined with regional change over a 12 month period. In this paper we extend the approach proposed in [1] to the analysis of the entire brain pattern. Compared to [1], our method uses voxel-wise differences and avoids segmentation of the images into regions of interest. For our study, FDG-PET scans at the baseline and at 12-month follow-up of cognitively normal (CN), mild cognitive impairment (MCI) and AD subjects were retrieved from the Alzheimer's disease neuroimaging initiative (ADNI) database. For both AD and MCI identification, the best classification results were achieved by combining cross-sectional and longitudinal information rather than using only the cross-sectional data. Furthermore, the longitudinal voxel-based analysis outperformed multi-region analysis.},
author = {Rodrigues, Filipa and Silveira, Margarida},
doi = {10.1109/EMBC.2014.6943992},
issn = {1557-170X (Print)},
journal = {Annu. Int. Conf. IEEE Eng. Med. Biol. Soc.},
keywords = { 80 and over, Computer-Assisted, Factual,Aged,Algorithms,Alzheimer Disease,Biomarkers,Brain,Cognitive Dysfunction,Cross-Sectional Studies,Data Collection,Databases,Diagnosis,Female,Fluorodeoxyglucose F18,Humans,Image Processing,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neuroimaging,Positron-Emission Tomography,Reproducibility of Results,chemistry,classification,diagnosis,diagnostic imaging,methods},
mendeley-groups = {PhDThesis/Review},
pages = {1941--1944},
pmid = {25570360},
title = {{Longitudinal FDG-PET features for the classification of Alzheimer's disease.}},
volume = {2014},
year = {2014}
}
@article{Sabuncu2011,
abstract = {OBJECTIVE To characterize rates of regional Alzheimer disease (AD)-specific brain atrophy across the presymptomatic, mild cognitive impairment, and dementia stages. DESIGN Multicenter case-control study of neuroimaging, cerebrospinal fluid, and cognitive test score data from the Alzheimer's Disease Neuroimaging Initiative. SETTING Research centers across the United States and Canada. PATIENTS We examined a total of 317 participants with baseline cerebrospinal fluid biomarker measurements and 3 T1-weighted magnetic resonance images obtained within 1 year. MAIN OUTCOME MEASURES We used automated tools to compute annual longitudinal atrophy in the hippocampus and cortical regions targeted in AD. We used Mini-Mental State Examination scores as a measure of cognitive performance. We performed a cross-subject analysis of atrophy rates and acceleration on individuals with an AD-like cerebrospinal fluid molecular profile. RESULTS In presymptomatic individuals harboring indicators of AD, baseline thickness in AD-vulnerable cortical regions was significantly reduced compared with that of healthy control individuals, but baseline hippocampal volume was not. Across the clinical spectrum, rates of AD-specific cortical thinning increased with decreasing cognitive performance before peaking at approximately the Mini-Mental State Examination score of 21, beyond which rates of thinning started to decline. Annual rates of hippocampal volume loss showed a continuously increasing pattern with decreasing cognitive performance as low as the Mini-Mental State Examination score of 15. Analysis of the second derivative of imaging measurements revealed that AD-specific cortical thinning exhibited early acceleration followed by deceleration. Conversely, hippocampal volume loss exhibited positive acceleration across all study participants. CONCLUSIONS Alzheimer disease-specific cortical thinning and hippocampal volume loss are consistent with a sigmoidal pattern, with an acceleration phase during the early stages of the disease. Clinical trials should carefully consider the nonlinear behavior of these AD biomarkers.},
annote = {Longitudinal statistical analysis. If mentioned, needs to be in statistical folder.},
author = {Sabuncu, Mert R and Desikan, Rahul S and Sepulcre, Jorge and Yeo, Boon Thye T and Liu, Hesheng and Schmansky, Nicholas J and Reuter, Martin and Weiner, Michael W and Buckner, Randy L and Sperling, Reisa A and Fischl, Bruce},
doi = {10.1001/archneurol.2011.167},
isbn = {1538-3687 (Electronic)$\backslash$r0003-9942 (Linking)},
issn = {00039942},
journal = {Arch. Neurol.},
mendeley-groups = {PhDThesis/Review},
number = {8},
pages = {1040--1048},
pmid = {21825241},
publisher = {NIH Public Access},
title = {{The dynamics of cortical and hippocampal atrophy in Alzheimer disease}},
volume = {68},
year = {2011}
}
@article{Schiratti2015,
abstract = {Mixed-effects models provide a rich theoretical framework for the analysis of longitudinal data. However, when used to analyze or predict the progression of a neurodegenerative disease such as Alzheimer's disease, these models usually do not take into account the fact that subjects may be at different stages of disease progression and the interpretation of the model may depend on some implicit reference time. In this paper, we propose a generative statistical model for longitudinal data, described in a univariate Riemannian manifold setting, which estimates an average disease progression model, subject-specific time shifts and acceleration factors. The time shifts account for variability in age at disease-onset time. The acceleration factors account for variability in speed of disease progression. For a given individual, the estimated time shift and acceleration factor define an affine reparametrization of the average disease progression model. This statistical model has been used to analyze neuropsychological assessments scores and cortical thickness measurements from the Alzheimer's Disease Neuroimaging Initiative database. The numerical results showed that we can distinguish between slow versus fast progressing and early versus late-onset individuals.},
author = {Schiratti, J B and Allassonniere, S and Routier, A and Durrleman, S},
issn = {1011-2499 (Print)},
journal = {Inf. Process. Med. Imaging},
keywords = { Automated, Computer-Assisted, Statistical,Algorithms,Alzheimer Disease,Brain,Computer Simulation,Humans,Image Enhancement,Image Interpretation,Longitudinal Studies,Magnetic Resonance Imaging,Models,Pattern Recognition,Reproducibility of Results,Sensitivity and Specificity,methods,pathology},
mendeley-groups = {PhDThesis/Review},
pages = {564--575},
pmid = {26221703},
title = {{A Mixed-Effects Model with Time Reparametrization for Longitudinal Univariate Manifold-Valued Data.}},
volume = {24},
year = {2015}
}
@article{Schiratti2017,
author = {Schiratti, Jean-baptiste and Colliot, Olivier and Schiratti, Jean-baptiste and Colliot, Olivier and A, Stanley Durrleman},
issn = {15337928},
journal = {J. Mach. Learn. Res.},
keywords = {longitudinal model,riemannian geometry,spatiotemporal analysis,stochas-,tic expectation-maximization algorithm},
mendeley-groups = {PhDThesis/Review},
pages = {1--33},
title = {{A Bayesian mixed-effects model to learn trajectories of changes from repeated manifold-valued observations}},
volume = {18},
year = {2017}
}
@article{Schmidt-Richberg2016,
abstract = {Being able to estimate a patient's progress in the course of Alzheimer's disease and predicting future progression based on a number of observed biomarker values is of great interest for patients, clinicians and researchers alike. In this work, an approach for disease progress estimation is presented. Based on a set of subjects that convert to a more severe disease stage during the study, models that describe typical trajectories of biomarker values in the course of disease are learned using quantile regression. A novel probabilistic method is then derived to estimate the current disease progress as well as the rate of progression of an individual by fitting acquired biomarkers to the models. A particular strength of the method is its ability to naturally handle missing data. This means, it is applicable even if individual biomarker measurements are missing for a subject without requiring a retraining of the model. The functionality of the presented method is demonstrated using synthetic and-employing cognitive scores and image-based biomarkers-real data from the ADNI study. Further, three possible applications for progress estimation are demonstrated to underline the versatility of the approach: classification, construction of a spatio-temporal disease progression atlas and prediction of future disease progression.},
annote = {Longitudinal, robust to missing data.},
author = {Schmidt-Richberg, Alexander and Ledig, Christian and Guerrero, Ricardo and Molina-Abril, Helena and Frangi, Alejandro and Rueckert, Daniel},
doi = {10.1371/journal.pone.0153040},
isbn = {10.1371/journal.pone.0153040},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Review},
number = {4},
pmid = {27096739},
title = {{Learning biomarker models for progression estimation of Alzheimer's disease}},
volume = {11},
year = {2016}
}
@article{Serra2016,
abstract = {This longitudinal study investigates the modifications in structure and function occurring to typical Alzheimer's disease (AD) brains over a 2-year follow-up, from pre-dementia stages of disease, with the aim of identifying biomarkers of prognostic value. Thirty-one patients with amnestic mild cognitive impairment were recruited and followed-up with clinical, neuropsychological, and MRI assessments. Patients were retrospectively classified as AD Converters or Non-Converters, and the data compared between groups. Cross-sectional MRI data at baseline, assessing volume and functional connectivity abnormalities, confirmed previous findings, showing a more severe pattern of regional grey matter atrophy and default-mode network disconnection in Converters than in Non-Converters. Longitudinally, Converters showed more grey matter atrophy in the frontotemporal areas, accompanied by increased connectivity in the precuneus. Discriminant analysis revealed that functional connectivity of the precuneus within the default mode network at baseline is the parameter able to correctly classify patients in Converters and Non-Converters with high sensitivity, specificity, and accuracy.},
annote = {statistical},
author = {Serra, Laura and Cercignani, Mara and Mastropasqua, Chiara and Torso, Mario and Spano, Barbara and Makovac, Elena and Viola, Vanda and Giulietti, Giovanni and Marra, Camillo and Caltagirone, Carlo and Bozzali, Marco},
doi = {10.3233/JAD-150961},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = {Aged,Alzheimer Disease,Atrophy,Brain,Brain Mapping,Cognitive Dysfunction,Computer-Assisted,Cross-Sectional Studies,Discriminant Analysis,Disease Progression,Female,Follow-Up Studies,Gray Matter,Humans,Image Processing,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neural Pathways,Neuropsychological Tests,Prognosis,Rest,diagnostic imaging,physiopathology},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {377--389},
pmid = {26890769},
title = {{Longitudinal Changes in Functional Brain Connectivity Predicts Conversion to Alzheimer's Disease.}},
volume = {51},
year = {2016}
}
@article{Shmueli2010,
abstract = {Statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description. In many disciplines there is near-exclusive use of statistical modeling for causal ex-planation and the assumption that models with high explanatory power are inherently of high predictive power. Conflation between explanation and pre-diction is common, yet the distinction must be understood for progressing scientific knowledge. While this distinction has been recognized in the phi-losophy of science, the statistical literature lacks a thorough discussion of the many differences that arise in the process of modeling for an explanatory ver-sus a predictive goal. The purpose of this article is to clarify the distinction between explanatory and predictive modeling, to discuss its sources, and to reveal the practical implications of the distinction to each step in the model-ing process.},
author = {Shmueli, Galit},
doi = {10.1214/10-STS330},
journal = {Stat. Sci.},
keywords = {Explanatory modeling,causality,data mining,predictive modeling,predictive power,scientific research,statistical strategy},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {289--310},
title = {{To Explain or to Predict?}},
volume = {25},
year = {2010}
}
@article{Silver2012,
abstract = {We present a new method for the detection of gene pathways associated with a multivariate quantitative trait, and use it to identify causal pathways associated with an imaging endophenotype characteristic of longitudinal structural change in the brains of patients with Alzheimer's disease (AD). Our method, known as pathways sparse reduced-rank regression (PsRRR), uses group lasso penalised regression to jointly model the effects of genome-wide single nucleotide polymorphisms (SNPs), grouped into functional pathways using prior knowledge of gene-gene interactions. Pathways are ranked in order of importance using a resampling strategy that exploits finite sample variability. Our application study uses whole genome scans and MR images from 99 probable AD patients and 164 healthy elderly controls in the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. 66,182 SNPs are mapped to 185 gene pathways from the KEGG pathway database. Voxel-wise imaging signatures characteristic of AD are obtained by analysing 3D patterns of structural change at 6, 12 and 24 months relative to baseline. High-ranking, AD endophenotype-associated pathways in our study include those describing insulin signalling, vascular smooth muscle contraction and focal adhesion. All of these have been previously implicated in AD biology. In a secondary analysis, we investigate SNPs and genes that may be driving pathway selection. High ranking genes include a number previously linked in gene expression studies to beta-amyloid plaque formation in the AD brain (PIK3R3,PIK3CG,PRKCAandPRKCB), and to AD related changes in hippocampal gene expression (ADCY2, ACTN1, ACACA, and GNAI1). Other high ranking previously validated AD endophenotype-related genes include CR1, TOMM40 and APOE.},
author = {Silver, Matt and Janousova, Eva and Hua, Xue and Thompson, Paul M and Montana, Giovanni},
doi = {10.1016/j.neuroimage.2012.08.002},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { Single Nucleotide,Aged,Alzheimer Disease,Female,Genetic Predisposition to Disease,Genome-Wide Association Study,Humans,Magnetic Resonance Imaging,Male,Phenotype,Polymorphism,Signal Transduction,genetics,pathology},
mendeley-groups = {PhDThesis/Review},
month = {nov},
number = {3},
pages = {1681--1694},
pmid = {22982105},
title = {{Identification of gene pathways implicated in Alzheimer's disease using longitudinal imaging phenotypes with sparse regression.}},
volume = {63},
year = {2012}
}
@article{Sluimer2009,
abstract = {We investigated progression of atrophy in vivo, in Alzheimer's disease (AD), and mild cognitive impairment (MCI). We included 64 patients with AD, 44 with MCI and 34 controls with serial MRI examinations (interval 1.8 ± 0.7 years). A nonlinear registration algorithm (fluid) was used to calculate atrophy rates in six regions: frontal, medial temporal, temporal (extramedial), parietal, occipital lobes and insular cortex. In MCI, the highest atrophy rate was observed in the medial temporal lobe, comparable with AD. AD patients showed even higher atrophy rates in the extramedial temporal lobe. Additionally, atrophy rates in frontal, parietal and occipital lobes were increased. Cox proportional hazard models showed that all regional atrophy rates predicted conversion to AD. Hazard ratios varied between 2.6 (95{\%} confidence interval (CI) = 1.1-6.2) for occipital atrophy and 15.8 (95{\%} CI = 3.5-71.8) for medial temporal lobe atrophy. In conclusion, atrophy spreads through the brain with development of AD. MCI is marked by temporal lobe atrophy. In AD, atrophy rate in the extramedial temporal lobe was even higher. Moreover, atrophy rates also accelerated in parietal, frontal, insular and occipital lobes. Finally, in nondemented elderly, medial temporal lobe atrophy was most predictive of progression to AD, demonstrating the involvement of this region in the development of AD.},
annote = {Atrophy rates studio using Cox proportional hazard models.},
author = {Sluimer, Jasper D and {Van Der Flier}, Wiesje M and Karas, Giorgos B and {Van Schijndel}, Ronald and Barnes, Josephine and Boyes, Richard G and Cover, Keith S and Olabarriaga, S{\'{i}}lvia D and Fox, Nick C and Scheltens, Philip and Vrenken, Hugo and Barkhof, Frederik},
doi = {10.1007/s00330-009-1512-5},
isbn = {1432-1084 (Electronic)$\backslash$r0938-7994 (Linking)},
issn = {09387994},
journal = {Eur. Radiol.},
keywords = {Alzheimer's disease,Atrophy,Computer-assisted,Image processing,Magnetic resonance imaging},
mendeley-groups = {PhDThesis/Review},
number = {12},
pages = {2826--2833},
pmid = {19618189},
publisher = {Springer},
title = {{Accelerating regional atrophy rates in the progression from normal aging to Alzheimer's disease}},
volume = {19},
year = {2009}
}
@article{Small2007,
abstract = {Preclinical Alzheimer's disease (AD) refers to a period of time prior to diagnosis during which cognitive deficits among individuals who will go on to receive a diagnosis of AD are present. There is great interest in describing the nature of cognitive change during the preclinical period, in terms of whether persons decline in a linear fashion to diagnosis, or exhibit some stability of functioning, followed by rapid losses in performance. In the current study we apply Growth Mixture Modeling to data from The Kungsholmen Project to evaluate whether decline in Mini Mental State Examination (MMSE) scores during the preclinical period of AD follows a linear or quadratic function. At the end of a 7-year follow-up period, some individuals would be diagnosed with AD (n=71), whereas others would remain free of dementia (n=457). The results indicated that a two-group quadratic model of decline provided the best statistical fit measures, as well as the greatest estimates of sensitivity (67{\%}) and specificity (86{\%}). Differences in MMSE scores were apparent at baseline, but the preclinical AD group began to experience precipitous declines three years prior to diagnosis. Finally, persons who were misclassified as preclinical AD had fewer years of education and poorer MMSE scores at baseline.},
author = {Small, Brent J and Backman, Lars},
issn = {0010-9452 (Print)},
journal = {Cortex.},
keywords = { 80 and over, Differential, Theoretical,Aged,Aging,Alzheimer Disease,Cognition Disorders,Dementia,Diagnosis,Disease Progression,Female,Geriatric Assessment,Humans,Linear Models,Longitudinal Studies,Male,Mental Status Schedule,Models,Neuropsychological Tests,Predictive Value of Tests,Risk Factors,diagnosis,methods,physiology,psychology},
mendeley-groups = {PhDThesis/Review},
month = {oct},
number = {7},
pages = {826--834},
pmid = {17941341},
title = {{Longitudinal trajectories of cognitive change in preclinical Alzheimer's disease: a growth mixture modeling analysis.}},
volume = {43},
year = {2007}
}
@article{Spulber2010,
abstract = {For both clinical and research reasons, it is essential to identify which mild cognitive impairment (MCI) subjects subsequently progress to Alzheimer's disease (AD). The prediction may be facilitated by accelerated whole brain atrophy exhibited by AD subjects. Iterative principal component analysis (IPCA) was used to characterize whole brain atrophy rates using sequential MRI scans for 102 MCI subjects from the Kuopio University Hospital. We modelled the likelihood of progression to probable AD, and found that each additional percent of annualized whole brain atrophy rate was associated with a higher odds ratio (OR) of progression (OR. =. 1.30, p=. 0.01, 95{\%} CI. =. 1.05-1.60). Our study demonstrates an association between whole brain atrophy rate and subsequent rate of clinical progression from MCI to AD. These findings suggest that IPCA could be an effective brain-imaging marker of progression to AD and useful tool for the evaluation of disease-modifying treatments. {\textcopyright}2008 Elsevier Inc.},
annote = {statistical},
author = {Spulber, Gabriela and Niskanen, Eini and MacDonald, Stuart and Smilovici, Oded and Chen, Kewei and Reiman, Eric M and Jauhiainen, Anne M and Hallikainen, Merja and Tervo, Susanna and Wahlund, Lars Olof and Vanninen, Ritva and Kivipelto, Miia and Soininen, Hilkka},
doi = {10.1016/j.neurobiolaging.2008.08.018},
isbn = {1558-1497 (Electronic)$\backslash$n0197-4580 (Linking)},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Iterative principal component analysis,MRI,Mild cognitive impairment,Whole brain atrophy},
mendeley-groups = {PhDThesis/Review},
number = {9},
pages = {1601--1605},
pmid = {18829136},
title = {{Whole brain atrophy rate predicts progression from MCI to Alzheimer's disease}},
volume = {31},
year = {2010}
}
@inproceedings{Stuhler2014,
abstract = {We aim at developing new dementia-related features based on longitudinalMRI in order to differentiate various stages of Alzheimer's disease. Current methods for dementia classification rely heavily on the quality of MRI preprocessing, especially on prior registration. We propose to avoid a possibly unsuccessful and always time-consuming non-rigid registration by employing local invariant features which are independent of image scale and orientation, and can be tracked over time in longitudinal studies. We detect and track such keypoints based on scale-space theory in an automatized image processing workflow, and test it on a standardized MRI collection made available by the Alzheimer's Disease Neuroimaging Initiative (ADNI). Our approach is very efficient for processing very large datasets collected from different sites and technical devices, and first results show that characteristic scale and movement of keypoints and their tracks differ significantly between controls and diseased subjects.},
annote = {No s{\'{e}} col{\textperiodcentered}locar-lo... el podem deixar fora, crec jo},
author = {St{\"{u}}hler, Elisabeth and Berthold, Michael R},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-13972-2_6},
isbn = {9783319139715},
issn = {16113349},
keywords = {ADNI,Local-invariant features,Longitudinal MRI,Scale-space extrema,Tracking},
mendeley-groups = {PhDThesis/Review},
pages = {59--70},
title = {{Dementia-related features in longitudinal MRI: Tracking keypoints over time}},
volume = {8848},
year = {2014}
}
@article{Sun2017,
abstract = {Mild Cognitive Impairment (MCI) is an intermediate stage between healthy and Alzheimer's disease (AD). To enable early intervention it is important to identify the MCI subjects that will convert to AD in an early stage. In this paper, we provide a new method to distinguish between MCI patients that either convert to Alzheimer's Disease (MCIc) or remain stable (MCIs), using only longitudinal T1-weighted MRI. Currently, most longitudinal studies focus on volumetric comparison of a few anatomical structures, thereby ignoring more detailed development inside and outside those structures. In this study we propose to exploit the anatomical development within the entire brain, as found by a non-rigid registration approach. Specifically, this anatomical development is represented by the Stationary Velocity Field (SVF) from registration between the baseline and follow-up images. To make the SVFs comparable among subjects, we use the parallel transport method to align them in a common space. The normalized SVF together with derived features are then used to distinguish between MCIc and MCIs subjects. This novel feature space is reduced using a Kernel Principal Component Analysis method, and a linear support vector machine is used as a classifier. Extensive comparative experiments are performed to inspect the influence of several aspects of our method on classification performance, specifically the feature choice, the smoothing parameter in the registration and the use of dimensionality reduction. The optimal result from a 10-fold cross-validation using 36 month follow-up data shows competitive results: accuracy 92{\%}, sensitivity 95{\%}, specificity 90{\%}, and AUC 94{\%}. Based on the same dataset, the proposed approach outperforms two alternative ones that either depends on the baseline image only, or uses longitudinal information from larger brain areas. Good results were also obtained when scans at 6, 12, or 24 months were used for training the classifier. Besides the classification power, the proposed method can quantitatively compare brain regions that have a significant difference in development between the MCIc and MCIs groups.},
author = {Sun, Zhuo and van de Giessen, Martijn and Lelieveldt, Boudewijn P F and Staring, Marius},
doi = {10.3389/fninf.2017.00016},
issn = {1662-5196 (Print)},
journal = {Front. Neuroinform.},
mendeley-groups = {PhDThesis/Review},
pages = {16},
pmid = {28286479},
title = {{Detection of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Longitudinal Brain MRI.}},
volume = {11},
year = {2017}
}
@article{Tang2015,
abstract = {{\textcopyright}2015 Wiley Periodicals, Inc. We proposed a diffeomorphometry-based statistical pipeline to study the regional shape change rates of the bilateral hippocampus, amygdala, and ventricle in mild cognitive impairment (MCI) and Alzheimer's disease (AD) compared with healthy controls (HC), using sequential magnetic resonance imaging (MRI) scans of 713 subjects (3,123 scans in total). The subgroup shape atrophy rates of the bilateral hippocampus and amygdala, as well as the expansion rates of the bilateral ventricles, for a majority of vertices were found to follow the order of AD {\textgreater}MCI {\textgreater}HC. The bilateral hippocampus and the left amygdala were subsegmented into multiple functionally meaningful subregions with the help of high-field MRI scans. The largest group differences in localized shape atrophy rates on the hippocampus were found to occur in CA1, followed by subiculum, CA2, and finally CA3/dentate gyrus, which is consistent with the neurofibrillary tangle accumulation trajectory. Highly nonuniform group differences were detected on the amygdala; vertices on the core amygdala (basolateral and lateral nucleus) revealed much larger atrophy rates, whereas those on the noncore amygdala (mainly centromedial) displayed similar or even smaller atrophy rates in AD relative to HC. The temporal horns of the ventricles were observed to have the largest localized ventricular expansion rate differences; with the AD group showing larger localized expansion rates on the anterior horn and the body part of the ventricles as well. Significant correlations were observed between the localized shape change rates of each of these six structures and the cognitive deterioration rates as quantified by the Alzheimer's Disease Assessment Scale-Cognitive Behavior Section increase rate and the Mini Mental State Examination decrease rate.},
annote = {bilateral hippocampus, amygdala, and ventricle

Studying the deformation

Longitudinal

Shape rates.

Probabilistic approach. (stadistical shape analysis method)},
author = {Tang, Xiaoying and Holland, Dominic and Dale, Anders M and Younes, Laurent and Miller, Michael I},
doi = {10.1002/hbm.22758},
issn = {10970193},
journal = {Hum. Brain Mapp.},
keywords = {Alzheimer's disease,Diffeomorphometry,Longitudinal analysis,Medial temporal lobe,Mild cognitive impairment,Regional shape change rates},
mendeley-groups = {PhDThesis/Review},
number = {6},
pages = {2093--2117},
title = {{The diffeomorphometry of regional shape change rates and its relevance to cognitive deterioration in mild cognitive impairment and Alzheimer's disease}},
volume = {36},
year = {2015}
}
@article{Thung2016,
abstract = {Distinguishing progressive mild cognitive impairment (pMCI) from stable mild cognitive impairment (sMCI) is critical for identification of patients who are at risk for Alzheimer's disease (AD), so that early treatment can be administered. In this paper, we propose a pMCI/sMCI classification framework that harnesses information available in longitudinal magnetic resonance imaging (MRI) data, which could be incomplete, to improve diagnostic accuracy. Volumetric features were first extracted from the baseline MRI scan and subsequent scans acquired after 6, 12, and 18 months. Dynamic features were then obtained using the 18th month scan as the reference and computing the ratios of feature differences for the earlier scans. Features that are linearly or non-linearly correlated with diagnostic labels are then selected using two elastic net sparse learning algorithms. Missing feature values due to the incomplete longitudinal data are imputed using a low-rank matrix completion method. Finally, based on the completed feature matrix, we build a multi-kernel support vector machine (mkSVM) to predict the diagnostic label of samples with unknown diagnostic statuses. Our evaluation indicates that a diagnosis accuracy as high as 78.2 {\%} can be achieved when information from the longitudinal scans is used-6.6 {\%} higher than the case using only the reference time point image. In other words, information provided by the longitudinal history of the disease improves diagnosis accuracy.},
author = {Thung, Kim-Han and Wee, Chong-Yaw and Yap, Pew-Thian and Shen, Dinggang},
doi = {10.1007/s00429-015-1140-6},
issn = {1863-2661 (Electronic)},
journal = {Brain Struct. Funct.},
keywords = { Computer-Assisted, Factual, Statistical,Aged,Algorithms,Brain,Cognitive Dysfunction,Computer-Assisted,Data Interpretation,Databases,Disease Progression,Factual,Female,Humans,Image Interpretation,Longitudinal Studies,Magnetic Resonance Imaging,Male,Sensitivity and Specificity,Statistical,Support Vector Machine,classification,diagnosis,pathology},
mendeley-groups = {PhDThesis/Review},
month = {nov},
number = {8},
pages = {3979--3995},
pmid = {26603378},
title = {{Identification of progressive mild cognitive impairment patients using incomplete longitudinal MRI scans.}},
volume = {221},
year = {2016}
}
@article{Thung2018,
abstract = {In this paper, we aim to predict conversion and time-to-conversion of mild cognitive impairment (MCI) patients using multi-modal neuroimaging data and clinical data, via cross-sectional and longitudinal studies. However, such data are often heterogeneous, high-dimensional, noisy, and incomplete. We thus propose a framework that includes sparse feature selection, low-rank affinity pursuit denoising (LRAD), and low-rank matrix completion (LRMC) in this study. Specifically, we first use sparse linear regressions to remove unrelated features. Then, considering the heterogeneity of the MCI data, which can be assumed as a union of multiple subspaces, we propose to use a low rank subspace method (i.e., LRAD) to denoise the data. Finally, we employ LRMC algorithm with three data fitting terms and one inequality constraint for joint conversion and time-to-conversion predictions. Our framework aims to answer a very important but yet rarely explored question in AD study, i.e., when will the MCI convert to AD? This is different from survival analysis, which provides the probabilities of conversion at different time points that are mainly used for global analysis, while our time-to-conversion prediction is for each individual subject. Evaluations using the ADNI dataset indicate that our method outperforms conventional LRMC and other state-of-the-art methods. Our method achieves a maximal pMCI classification accuracy of 84{\%} and time prediction correlation of 0.665.},
author = {Thung, Kim-Han and Yap, Pew-Thian and Adeli, Ehsan and Lee, Seong-Whan and Shen, Dinggang},
doi = {https://doi.org/10.1016/j.media.2018.01.002},
issn = {1361-8415},
journal = {Med. Image Anal.},
keywords = {Classification,Data imputation,Low-rank representation,Matrix completion,Multi-task learning},
mendeley-groups = {PhDThesis/Review},
pages = {68--82},
title = {{Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion}},
volume = {45},
year = {2018}
}
@article{Tosun2010,
abstract = {Previously it was reported that Alzheimer's disease (AD) patients have reduced beta amyloid (A$\beta$1-42) and elevated total tau (t-tau) and phosphorylated tau (p-tau181p) in the cerebrospinal fluid (CSF), suggesting that these same measures could be used to detect early AD pathology in healthy elderly individuals and those with mild cognitive impairment (MCI). In this study, we tested the hypothesis that there would be an association among rates of regional brain atrophy, the CSF biomarkers A$\beta$1-42, t-tau, and p-tau181pand apolipoprotein E (ApoE) $\epsilon$4 status, and that the pattern of this association would be diagnosis-specific. Our findings primarily showed that lower CSF A$\beta$1-42and higher tau concentrations were associated with increased rates of regional brain tissue loss and the patterns varied across the clinical groups. Taken together, these findings demonstrate that CSF biomarker concentrations are associated with the characteristic patterns of structural brain changes in healthy elderly and mild cognitive impairment subjects that resemble to a large extent the pathology seen in AD. Therefore, the finding of faster progression of brain atrophy in the presence of lower A$\beta$1-42levels and higher tau levels supports the hypothesis that CSF A$\beta$1-42and tau are measures of early AD pathology. Moreover, the relationship among CSF biomarkers, ApoE $\epsilon$4 status, and brain atrophy rates are regionally varying, supporting the view that the genetic predisposition of the brain to beta amyloid and tau mediated pathology is regional and disease stage specific. {\textcopyright}2010 Elsevier Inc.},
author = {Tosun, Duygu and Schuff, Norbert and Truran-Sacrey, Diana and Shaw, Leslie M and Trojanowski, John Q and Aisen, Paul and Peterson, Ronald and Weiner, Michael W},
doi = {10.1016/j.neurobiolaging.2010.04.030},
isbn = {0197-4580},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,ApoE,Atrophy,Biomarkers,Brain tissue volume,Cerebrospinal fluid,Cortical thickness,Healthy aging,MRI,Mild cognitive impairment},
mendeley-groups = {PhDThesis/Review},
number = {8},
pages = {1340--1354},
pmid = {20570401},
publisher = {NIH Public Access},
title = {{Relations between brain tissue loss, CSF biomarkers, and the ApoE genetic profile: A longitudinal MRI study}},
volume = {31},
year = {2010}
}
@article{Vounou2012,
abstract = {Scanning the entire genome in search of variants related to imaging phenotypes holds great promise in elucidating the genetic etiology of neurodegenerative disorders. Here we discuss the application of a penalized multivariate model, sparse reduced-rank regression (sRRR), for the genome-wide detection of markers associated with voxel-wise longitudinal changes in the brain caused by Alzheimer's disease (AD). Using a sample from the Alzheimer's Disease Neuroimaging Initiative database, we performed three separate studies that each compared two groups of individuals to identify genes associated with disease development and progression. For each comparison we took a two-step approach: initially, using penalized linear discriminant analysis, we identified voxels that provide an imaging signature of the disease with high classification accuracy; then we used this multivariate biomarker as a phenotype in a genome-wide association study, carried out using sRRR. The genetic markers were ranked in order of importance of association to the phenotypes using a data re-sampling approach. Our findings confirmed the key role of the APOE and TOMM40 genes but also highlighted some novel potential associations with AD.},
author = {Vounou, Maria and Janousova, Eva and Wolz, Robin and Stein, Jason L and Thompson, Paul M and Rueckert, Daniel and Montana, Giovanni},
doi = {10.1016/j.neuroimage.2011.12.029},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { Computer-Assisted,Algorithms,Alzheimer Disease,Female,Genome-Wide Association Study,Humans,Image Processing,Male,Neuroimaging,Phenotype,genetics,pathology},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {1},
pages = {700--716},
pmid = {22209813},
title = {{Sparse reduced-rank regression detects genetic associations with voxel-wise longitudinal phenotypes in Alzheimer's disease.}},
volume = {60},
year = {2012}
}
@inproceedings{Wachinger2017,
abstract = {Clinically normal aging and pathological processes cause structural changes in the brain. These changes likely occur in overlapping regions that accommodate neural systems with high susceptibility to deleterious factors. Due to the overlap, the separation between aging and pathological processes is challenging when analyzing brain structures independently. We propose to identify multivariate latent processes that govern cross-sectional and longitudinal neuroanatomical changes across the brain in aging and dementia. A discriminative representation of neuroanatomy is obtained from spectral shape descriptors in the BrainPrint. We identify latent factors by maximizing the covariance between morphological change and response variables of age and a proxy for dementia. Our results reveal cross-sectional and longitudinal patterns of change in neuroanatomy that distinguishes aging processes from disease processes. Finally, latent processes do not only yield a parsimonious model but also a significantly improved prediction accuracy.},
address = {Cham},
author = {Wachinger, Christian and Rieckmann, Anna and Reuter, Martin},
booktitle = {Med. Image Comput. Comput. Assist. Interv. - MICCAI 2017},
editor = {Descoteaux, Maxime and Maier-Hein, Lena and Franz, Alfred and Jannin, Pierre and Collins, D Louis and Duchesne, Simon},
isbn = {978-3-319-66179-7},
mendeley-groups = {PhDThesis/Review},
pages = {30--37},
publisher = {Springer International Publishing},
title = {{Latent Processes Governing Neuroanatomical Change in Aging and Dementia}},
year = {2017}
}
@article{Wachingera,
abstract = {Clinically normal aging and pathological processes cause structural changes in the brain. These changes likely occur in overlap-ping regions that accommodate neural systems with high susceptibility to deleterious factors. Due to the overlap, the separation between aging and pathological processes is challenging when analyzing brain structures independently. We propose to identify multivariate latent processes that govern cross-sectional and longitudinal neuroanatomical changes across the brain in aging and dementia. A discriminative representation of neu-roanatomy is obtained from spectral shape descriptors in the BrainPrint. We identify latent factors by maximizing the covariance between mor-phological change and response variables of age and a proxy for dementia. Our results reveal cross-sectional and longitudinal patterns of change in neuroanatomy that distinguishes aging processes from disease processes. Finally, latent processes do not only yield a parsimonious model but also a significantly improved prediction accuracy.},
author = {Wachinger, Christian and Rieckmann, Anna and Reuter, Martin},
doi = {10.1007/978-3-319-66179-7},
mendeley-groups = {PhDThesis/Review},
title = {{Latent Processes Governing Neuroanatomical Change in Aging and Dementia}}
}
@article{Wang2014,
abstract = {Brain changes due to development and maturation, normal aging, or degenerative disease are continuous, gradual, and variable across individuals. To quantify the individual progression of brain changes, we propose a spatio-temporal methodology based on Hidden Markov Models (HMM), and apply it on four-dimensional structural brain magnetic resonance imaging series of older individuals. First, regional brain features are extracted in order to reduce image dimensionality. This process is guided by the objective of the study or the specific imaging patterns whose progression is of interest, for example, the evaluation of Alzheimer-like patterns of brain change in normal individuals. These regional features are used in conjunction with HMMs, which aim to measure the dynamic association between brain structure changes and progressive stages of disease over time. A bagging framework is used to obtain models with good generalization capability, since in practice the number of serial scans is limited. An application of the proposed methodology was to detect individuals with the risk of developing MCI, and therefore it was tested on modeling the progression of brain atrophy patterns in older adults. With HMM models, the state-transition paths corresponding to longitudinal brain changes were constructed from two completely independent datasets, the Alzheimer Disease Neuroimaging Initiative and the Baltimore Longitudinal Study of Aging. The statistical analysis of HMM-state paths among the normal, progressive MCI, and MCI groups indicates that, HMM-state index 1 is likely to be a predictor of the conversion from cognitively normal to MCI, potentially many years before clinical symptoms become measurable.},
author = {Wang, Ying and Resnick, Susan M and Davatzikos, Christos},
doi = {10.1002/hbm.22511},
institution = {Baltimore Longitudinal Study of Aging},
issn = {1097-0193 (Electronic)},
journal = {Hum. Brain Mapp.},
keywords = { Computer-Assisted,Aged,Aging,Algorithms,Alzheimer Disease,Atrophy,Brain,Cognitive Dysfunction,Disease Progression,Female,Humans,Image Interpretation,Longitudinal Studies,Magnetic Resonance Imaging,Male,Markov Chains,Time Factors,diagnosis,methods,pathology},
mendeley-groups = {PhDThesis/Review},
number = {9},
pages = {4777--4794},
pmid = {24706564},
title = {{Analysis of spatio-temporal brain imaging patterns by Hidden Markov Models and serial MRI images.}},
volume = {35},
year = {2014}
}
@article{jie,
annote = {-Sparse learning

- Interesting Longitudinal Method to discover AD-related biomarkers.

- Estimate clinical scores using MRI data.

- Features: Use GM (Grey Matter) volume on te 93 regions of brain. It is a region-based method, not a voxel-based method.},
author = {Jie, B and Liu, M and Zhang, D and Shen, D},
journal = {IEEE Trans. Biomed. Eng.},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {238--249},
title = {{Temporally-Constrained Group Sparse Learning for Longitudinal Data Analysis in Alzheimer's Disease}},
volume = {64},
year = {2015}
}
@article{Jie2017,
abstract = {Sparse learning has been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease and its prodromal stage, i.e., mild cognitive impairment. However, most existing sparse learning-based studies only adopt cross-sectional analysis methods, where the sparse model is learned using data from a single time-point. Actually, multiple time-points of data are often available in brain imaging applications, which can be used in some longitudinal analysis methods to better uncover the disease progression patterns. Accordingly, in this paper, we propose a novel temporallyconstrained group sparse learning method aiming for longitudinal analysis with multiple time-points of data. Specifically, we learn a sparse linear regression model by using the imaging data from multiple time-points, where a group regularization term is first employed to group the weights for the same brain region across different time-points together. Furthermore, to reflect the smooth changes between data derived from adjacent time-points, we incorporate two smoothness regularization terms into the objective function, i.e., one fused smoothness term thatrequires that the differences between two successive weight vectors from adjacent time-points should be small, and another output smoothness term thatrequires the differences between outputs of two successive models from adjacent time-points should also be small. We develop an efficient optimization algorithm to solve the proposed objective function. Experimental results on ADNI database demonstrate that, compared with conventional sparse learning-based methods, our proposed method can achieve improved regression performance and also help in discovering disease-related biomarkers.},
author = {Jie, Biao and Liu, Mingxia and Liu, Jun and Zhang, Daoqiang and Shen, Dinggang},
doi = {10.1109/TBME.2016.2553663},
issn = {1558-2531 (Electronic)},
journal = {IEEE Trans. Biomed. Eng.},
keywords = { Computer-Assisted,Aging,Algorithms,Alzheimer Disease,Brain,Cognitive Dysfunction,Humans,Image Interpretation,Longitudinal Studies,Machine Learning,Magnetic Resonance Imaging,Reproducibility of Results,Sensitivity and Specificity,Subtraction Technique,diagnostic imaging,methods,pathology},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {238--249},
pmid = {27093313},
title = {{Temporally Constrained Group Sparse Learning for Longitudinal Data Analysis in Alzheimer's Disease.}},
volume = {64},
year = {2017}
}
@article{Jordan2013,
abstract = {Big Data;Scalability},
archivePrefix = {arXiv},
arxivId = {arXiv:1309.7804v1},
author = {Jordan, Michael I},
doi = {10.3150/12-BEJSP17},
eprint = {arXiv:1309.7804v1},
issn = {1350-7265},
journal = {Bernoulli},
keywords = {()},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {1378--1390},
title = {{On statistics, computation and scalability}},
volume = {19},
year = {2013}
}
@inproceedings{Koval2017,
abstract = {We introduce a mixed-effects model to learn spatiotempo-ral patterns on a network by considering longitudinal measures dis-tributed on a fixed graph. The data come from repeated observations of subjects at different time points which take the form of measure-ment maps distributed on a graph such as an image or a mesh. The model learns a typical group-average trajectory characterizing the prop-agation of measurement changes across the graph nodes. The subject-specific trajectories are defined via spatial and temporal transforma-tions of the group-average scenario, thus estimating the variability of spatiotemporal patterns within the group. To estimate population and individual model parameters, we adapted a stochastic version of the Expectation-Maximization algorithm, the MCMC-SAEM. The model is used to describe the propagation of cortical atrophy during the course of Alzheimer's Disease. Model parameters show the variability of this aver-age pattern of atrophy in terms of trajectories across brain regions, age at disease onset and pace of propagation. We show that the personaliza-tion of this model yields accurate prediction of maps of cortical thickness in patients.},
annote = {From Duplicate 2 (Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks - Koval, I.; Schiratti, J.-B.; Routier, A.; Bacci, M.; Colliot, O.; Allassonni{\`{e}}re, S.; Durrleman, S.; Initiative, The Alzheimer's Disease Neuroimaging)

From Duplicate 1 (Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks - Koval, I.; Schiratti, J.-B.; Routier, A.; Bacci, M.; Colliot, O.; Allassonni{\`{e}}re, S.; Durrleman, S.; Initiative, The Alzheimer's Disease Neuroimaging)

Mixed effect model
Learn spatiotemporal patterns on a fixed graph.

Propagation on the nodes of a mesh. High dimensional model of brain.

From Duplicate 2 (Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks - Koval, I; Schiratti, J.-B; Routier, A; Bacci, M; Colliot, O; Allassonni{\`{e}}re, S; Durrleman, S; Initiative, The Alzheimer's Disease Neuroimaging)

Alzheimer disease longitudinal statistical learning.},
author = {Koval, I and Schiratti, J.-B. and Routier, A and Bacci, M and Colliot, O and Allassonni{\`{e}}re, S and Durrleman, S and Initiative, The Alzheimer's Disease Neuroimaging},
booktitle = {Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-66182-7_52},
isbn = {9783319661810},
mendeley-groups = {PhDThesis/Review},
pages = {451--459},
publisher = {Springer, Cham},
title = {{Statistical Learning of Spatiotemporal Patterns from Longitudinal Manifold-Valued Networks}},
volume = {10433},
year = {2017}
}
@article{Lei2017,
abstract = {It is highly desirable to predict the progression of Alzheimer's disease (AD) of patients [e.g., to predict conversion of mild cognitive impairment (MCI) to AD], especially longitudinal prediction of AD is important for its early diagnosis. Currently, most existing methods predict different clinical scores using different models, or separately predict multiple scores at different future time points. Such approaches prevent coordinated learning of multiple predictions that can be used to jointly predict clinical scores at multiple future time points. In this paper, we propose a joint learning method for predicting clinical scores of patients using multiple longitudinal prediction models for various future time points. Three important relationships among training samples, features, and clinical scores are explored. The relationship among different longitudinal prediction models is captured using a common feature set among the multiple prediction models at different time points. Our experimental results based on the Alzheimer's disease neuroimaging initiative (ADNI) database shows that our method achieves considerable improvement over competing methods in predicting multiple clinical scores.},
author = {Lei, Baiying and Jiang, Feng and Chen, Siping and Ni, Dong and Wang, Tianfu},
doi = {10.3389/fnagi.2017.00006},
issn = {16634365},
journal = {Front. Aging Neurosci.},
keywords = {Alzheimer's disease (AD),Feature selection,Joint learning,Longitudinal analysis,Prediction},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {MAR},
pages = {6},
pmid = {28316569},
publisher = {Frontiers},
title = {{Longitudinal analysis for disease progression via simultaneous multi-relational temporal-fused learning}},
volume = {9},
year = {2017}
}
@article{Lei2015,
abstract = {Longitudinal prediction of the brain disorder such as Alzheimer's disease (AD) is important for possible early detection and early intervention. Given the baseline imaging and clinical data, it will be interesting to predict the progress of disease for an individual subject, such as predicting the conversion of Mild Cognitive Impairment (MCI) to AD, in the future years. Most existing methods predicted different clinical scores using different models, or predicted multiple scores at different future time points separately. This often misses the chance of coordinated learning of multiple prediction models for jointly predict-ing multiple clinical scores at multiple future time points. In this paper, we propose a novel method for joint learning of multiple longitudinal prediction models for multiple clinical scores at multiple future time points. First, for each longitudinal prediction model, we explore three important relationships among training samples, features, and clinical scores, respectively, for enhancing its learning. Then, we further introduce additional relation among different longi-tudinal prediction models for allowing them to select a common set of features from the baseline imaging and clinical data, with l 2,1 sparsity constraint, for their joint training. We evaluate the performance of our joint prediction models with the data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, showing much better performance than the state-of-the-art methods in predicting multiple clinical scores at multiple future time points.},
annote = {Longitudinal Alzheimer.

Joint learning.

l2 1 sparsity constraint, motl t{\'{i}}pic.

Siimple regression?},
author = {Lei, Baiying and Ni, Dong and Wang, Tianfu},
doi = {10.1007/978-3-319-24888-2_40},
journal = {LNCS},
mendeley-groups = {PhDThesis/Review},
pages = {330--337},
title = {{Joint Learning of Multiple Longitudinal Prediction Models by Exploring Internal Relations}},
volume = {9352},
year = {2015}
}
@article{Li2017a,
abstract = {Characterization of long-term disease dynamics, from disease-free to end-stage, is integral to understanding the course of neurodegenerative diseases such as Parkinson's and Alzheimer's; and ultimately, how best to intervene. Natural history studies typically recruit multiple cohorts at different stages of disease and follow them longitudinally for a relatively short period of time. We propose a latent time joint mixed effects model to characterize long-term disease dynamics using this short-term data. Markov chain Monte Carlo methods are proposed for estimation, model selection, and inference. We apply the model to detailed simulation studies and data from the Alzheimer's Disease Neuroimaging Initiative.},
archivePrefix = {arXiv},
arxivId = {1703.10266},
author = {Li, Dan and Iddi, Samuel and Thompson, Wesley K and Donohue, Michael C},
doi = {10.1177/0962280217737566},
eprint = {1703.10266},
issn = {14770334},
journal = {Stat. Methods Med. Res.},
keywords = {Hierarchical Bayesian models,hierarchical bayesian models,joint mixed effects models,latent time shift,multicohort longitudinal data},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {3},
pages = {835--845},
title = {{Bayesian latent time joint mixed effect models for multicohort longitudinal data}},
volume = {28},
year = {2017}
}
@article{Li2017c,
abstract = {BACKGROUND Identifying predictors of conversion to Alzheimer's disease (AD) is critically important for AD prevention and targeted treatment. OBJECTIVE To compare various clinical and biomarker trajectories for tracking progression and predicting conversion from amnestic mild cognitive impairment to probable AD. METHODS Participants were from the ADNI-1 study. We assessed the ability of 33 longitudinal biomarkers to predict time to AD conversion, accounting for demographic and genetic factors. We used joint modelling of longitudinal and survival data to examine the association between changes of measures and disease progression. We also employed time-dependent receiver operating characteristic method to assess the discriminating capability of the measures. RESULTS 23 of 33 longitudinal clinical and imaging measures are significant predictors of AD conversion beyond demographic and genetic factors. The strong phenotypic and biological predictors are in the cognitive domain (ADAS-Cog; RAVLT), functional domain (FAQ), and neuroimaging domain (middle temporal gyrus and hippocampal volume). The strongest predictor is ADAS-Cog 13 with an increase of one SD in ADAS-Cog 13 increased the risk of AD conversion by 2.92 times. CONCLUSION Prediction of AD conversion can be improved by incorporating longitudinal change information, in addition to baseline characteristics. Cognitive measures are consistently significant and generally stronger predictors than imaging measures.},
annote = {From Duplicate 1 (Prediction of Conversion to Alzheimer's Disease with Longitudinal Measures and Time-To-Event Data - Li, Kan; Chan, Wenyaw; Doody, Rachelle S; Quinn, Joseph; Luo, Sheng)

Feature selection},
author = {Li, Kan and Chan, Wenyaw and Doody, Rachelle S and Quinn, Joseph and Luo, Sheng},
doi = {10.3233/JAD-161201},
institution = {Alzheimer's Disease Neuroimaging Initiative},
isbn = {1387-2877},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {80 and over,ADNI,Aged,Alzheimer Disease,Brain,Disease Progression,Female,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neuropsychological Tests,Positron-Emission Tomography,Predictive Value of Tests,ROC Curve,Surveys and Questionnaires,Time Factors,diagnosis,diagnostic imaging,joint modeling,longitudinal and survival data,mild cognitive impairment,mortality,pathology,physiopathology,prediction},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {361--371},
pmid = {28436391},
title = {{Prediction of Conversion to Alzheimer's Disease with Longitudinal Measures and Time-To-Event Data}},
volume = {58},
year = {2017}
}
@article{Li2017b,
abstract = {Functional data are increasingly collected in public health and medical studies to better understand many complex diseases. Besides the functional data, other clinical measures are often collected repeatedly. Investigating the association between these longitudinal data and time to a survival event is of great interest to these studies. In this article, we develop a functional joint model (FJM) to account for functional predictors in both longitudinal and survival submodels in the joint modeling framework. The parameters of FJM are estimated in a maximum likelihood framework via expectation maximization algorithm. The proposed FJM provides a flexible framework to incorporate many features both in joint modeling of longitudinal and survival data and in functional data analysis. The FJM is evaluated by a simulation study and is applied to the Alzheimer's Disease Neuroimaging Initiative study, a motivating clinical study testing whether serial brain imaging, clinical, and neuropsychological assessments can be combined to measure the progression of Alzheimer's disease. Copyright {\textcopyright}2017 John Wiley {\&} Sons, Ltd.Copyright {\textcopyright}2017 John Wiley {\&} Sons, Ltd.},
annote = {Is this really relevant? Where are the results? Good prediction.},
author = {Li, Kan and Luo, Sheng},
doi = {10.1002/sim.7381},
issn = {10970258},
journal = {Stat. Med.},
keywords = {ADNI study,functional data analysis,functional principal component analysis,longitudinal and time-to-event data},
mendeley-groups = {PhDThesis/Review},
number = {22},
pages = {3560--3572},
pmid = {28664662},
title = {{Functional joint model for longitudinal and time-to-event data: an application to Alzheimer's disease}},
volume = {36},
year = {2017}
}
@article{Li2012,
abstract = {Neuroimage measures from magnetic resonance (MR) imaging, such as cortical thickness, have been playing an increasingly important role in searching for biomarkers of Alzheimer's disease (AD). Recent studies show that, AD, mild cognitive impairment (MCI) and normal control (NC) can be distinguished with relatively high accuracy using the baseline cortical thickness. With the increasing availability of large longitudinal datasets, it also becomes possible to study the longitudinal changes of cortical thickness and their correlation with the development of pathology in AD. In this study, the longitudinal cortical thickness changes of 152 subjects from 4 clinical groups (AD, NC, Progressive-MCI and Stable-MCI) selected from Alzheimer's Disease Neuroimaging Initiative (ADNI) are measured by our recently developed 4 D (spatial+temporal) thickness measuring algorithm. It is found that the 4 clinical groups demonstrate very similar spatial distribution of grey matter (GM) loss on cortex. To fully utilize the longitudinal information and better discriminate the subjects from 4 groups, especially between Stable-MCI and Progressive-MCI, 3 different categories of features are extracted for each subject, i.e., (1) static cortical thickness measures computed from the baseline and endline, (2) cortex thinning dynamics, such as the thinning speed (mm/year) and the thinning ratio (endline/baseline), and (3) network features computed from the brain network constructed based on the correlation between the longitudinal thickness changes of different regions of interest (ROIs). By combining the complementary information provided by features from the 3 categories, 2 classifiers are trained to diagnose AD and to predict the conversion to AD in MCI subjects, respectively. In the leave-one-out cross-validation, the proposed method can distinguish AD patients from NC at an accuracy of 96.1{\%}, and can detect 81.7{\%} (AUC = 0.875) of the MCI converters 6 months ahead of their conversions to AD. Also, by analyzing the brain network built via longitudinal cortical thickness changes, a significant decrease (p {\textless}0.02) of the network clustering coefficient (associated with the development of AD pathology) is found in the Progressive-MCI group, which indicates the degenerated wiring efficiency of the brain network due to AD. More interestingly, the decreasing of network clustering coefficient of the olfactory cortex region was also found in the AD patients, which suggests olfactory dysfunction. Although the smell identification test is not performed in ADNI, this finding is consistent with other AD-related olfactory studies.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Li, Yang and Wang, Yaping and Wu, Guorong and Shi, Feng and Zhou, Luping and Lin, Weili and Shen, Dinggang},
doi = {10.1016/j.neurobiolaging.2010.11.008},
eprint = {NIHMS150003},
institution = {Alzheimer's Disease Neuroimaging Initiative},
isbn = {0197-4580$\backslash$r1558-1497},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Aged,Aging,Alzheimer Disease,Alzheimer's disease,Brain network,Cerebral Cortex,Classification,Computer-Assisted,Cortical thickness,Dynamics,Female,Humans,Image Interpretation,Longitudinal analysis,Magnetic Resonance Imaging,Male,Mild cognitive impairment,Reproducibility of Results,Sensitivity and Specificity,methods,pathology},
mendeley-groups = {PhDThesis/Review},
month = {feb},
number = {2},
pages = {15--30},
pmid = {21272960},
title = {{Discriminant analysis of longitudinal cortical thickness changes in Alzheimer's disease using dynamic and network features}},
volume = {33},
year = {2012}
}
@article{Li2013,
abstract = {Many large-scale longitudinal imaging studies have been or are being widely conducted to better understand the progress of neuropsychiatric and neurodegenerative disorders and normal brain development. The goal of this article is to develop a multiscale adaptive generalized estimation equation (MAGEE) method for spatial and adaptive analysis of neuroimaging data from longitudinal studies. MAGEE is applicable to making statistical inference on regression coefficients in both balanced and unbalanced longitudinal designs and even in twin and familial studies, whereas standard software platforms have several major limitations in handling these complex studies. Specifically, conventional voxel-based analyses in these software platforms involve Gaussian smoothing imaging data and then independently fitting a statistical model at each voxel. However, the conventional smoothing methods suffer from the lack of spatial adaptivity to the shape and spatial extent of region of interest and the arbitrary choice of smoothing extent, while independently fitting statistical models across voxels does not account for the spatial properties of imaging observations and noise distribution. To address such drawbacks, we adapt a powerful propagation-separation (PS) procedure to sequentially incorporate the neighboring information of each voxel and develop a new novel strategy to solely update a set of parameters of interest, while fixing other nuisance parameters at their initial estimators. Simulation studies and real data analysis show that MAGEE significantly outperforms voxel-based analysis. ?? 2013 Elsevier Inc.},
annote = {New method to model neuroimage longitudinal data. Voxel wise.

Paper makes a good stand of missing data.

Statistical analysis.

Generalized estimation equation.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Li, Yimei and Gilmore, John H and Shen, Dinggang and Styner, Martin and Lin, Weili and Zhu, Hongtu},
doi = {10.1016/j.neuroimage.2013.01.034},
eprint = {NIHMS150003},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Gaussian smoothing,Generalized estimation equation,Hypothesis,Longitudinal studies,Multiscale adaptive,Voxel-based analysis},
mendeley-groups = {PhDThesis/Review},
pages = {91--105},
pmid = {23357075},
title = {{Multiscale adaptive generalized estimating equations for longitudinal neuroimaging data}},
volume = {72},
year = {2013}
}
@article{Liu2014a,
abstract = {Previous studies have demonstrated that the use of integrated information from multi-modalities could significantly improve diagnosis of Alzheimer's Disease (AD). However, feature selection, which is one of the most important steps in classification, is typically performed separately for each modality, which ignores the potentially strong inter-modality relationship within each subject. Recent emergence of multi-task learning approach makes the joint feature selection from different modalities possible. However, joint feature selection may unfortunately overlook different yet complementary information conveyed by different modalities. We propose a novel multi-task feature selection method to preserve the complementary inter-modality information. Specifically, we treat feature selection from each modality as a separate task and further impose a constraint for preserving the inter-modality relationship, besides separately enforcing the sparseness of the selected features from each modality. After feature selection, a multi-kernel support vector machine (SVM) is further used to integrate the selected features from each modality for classification. Our method is evaluated using the baseline PET and MRI images of subjects obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our method achieves a good performance, with an accuracy of 94.37{\%} and an area under the ROC curve (AUC) of 0.9724 for AD identification, and also an accuracy of 78.80{\%} and an AUC of 0.8284 for mild cognitive impairment (MCI) identification. Moreover, the proposed method achieves an accuracy of 67.83{\%} and an AUC of 0.6957 for separating between MCI converters and MCI non-converters (to AD). These performances demonstrate the superiority of the proposed method over the state-of-the-art classification methods. {\textcopyright}2013 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Liu, Feng and Wee, Chong Yaw and Chen, Huafu and Shen, Dinggang},
doi = {10.1016/j.neuroimage.2013.09.015},
eprint = {NIHMS150003},
isbn = {1095-9572 (Electronic)$\backslash$n1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's Disease,Inter-modality relationship,Mild cognitive impairment,Multi-kernel support vector machine,Multi-task feature selection},
mendeley-groups = {PhDThesis/Review},
pages = {466--475},
pmid = {24045077},
title = {{Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification}},
volume = {84},
year = {2014}
}
@article{Liu2015,
abstract = {We present a longitudinal MR simulation framework which simulates the future neurodegenerative progression by outputting the predicted follow-up MR image and the voxel-based morphometry (VBM) map. This framework expects the patients to have at least 2 historical MR images available. The longitudinal and cross-sectional VBM maps are extracted to measure the affinity between the target subject and the template subjects collected for simulation. Then the follow-up simulation is performed by resampling the latest available target MR image with a weighted sum of non-linear transformations derived from the best-matched templates. The leave-one-out strategy was used to compare different simulation methods. Compared to the state-of-the-art voxel-based method, our proposed morphometry-based simulation achieves better accuracy in most cases.},
archivePrefix = {arXiv},
arxivId = {1508.05683},
author = {Liu, Siqi and Liu, Sidong and Pujol, Sonia and Kikinis, Ron and Feng, Dagan and Fulham, Michael and Cai, Weidong},
eprint = {1508.05683},
journal = {ArXiV},
mendeley-groups = {PhDThesis/Review},
title = {{Morphometry-Based Longitudinal Neurodegeneration Simulation with MR Imaging}},
year = {2015}
}

@article{Lo2012,
abstract = {OBJECTIVE: To investigate predictors of missing data in a longitudinal study of Alzheimer disease (AD). METHODS: The Alzheimer's Disease Neuroimaging Initiative (ADNI) is a clinic-based, multicenter, longitudinal study with blood, CSF, PET, and MRI scans repeatedly measured in 229 participants with normal cognition (NC), 397 with mild cognitive impairment (MCI), and 193 with mild AD during 2005-2007. We used univariate and multivariable logistic regression models to examine the associations between baseline demographic/clinical features and loss of biomarker follow-ups in ADNI. RESULTS: CSF studies tended to recruit and retain patients with MCI with more AD-like features, including lower levels of baseline CSF Abeta(42). Depression was the major predictor for MCI dropouts, while family history of AD kept more patients with AD enrolled in PET and MRI studies. Poor cognitive performance was associated with loss of follow-up in most biomarker studies, even among NC participants. The presence of vascular risk factors seemed more critical than cognitive function for predicting dropouts in AD. CONCLUSION: The missing data are not missing completely at random in ADNI and likely conditional on certain features in addition to cognitive function. Missing data predictors vary across biomarkers and even MCI and AD groups do not share the same missing data pattern. Understanding the missing data structure may help in the design of future longitudinal studies and clinical trials in AD.},
author = {Lo, Raymond Y and Jagust, William J},
doi = {10.1212/WNL.0b013e318253d5b3},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1526-632X (Electronic)},
journal = {Neurology},
keywords = { Vascular,Alzheimer Disease,Amyloid beta-Peptides,Biomarkers,Cognitive Dysfunction,Cohort Studies,Dementia,Fluorodeoxyglucose F18,Homocysteine,Humans,Logistic Models,Longitudinal Studies,Magnetic Resonance Imaging,Neuropsychological Tests,Patient Dropouts,Peptide Fragments,Positron-Emission Tomography,Research Design,Risk Factors,blood,cerebrospinal fluid,diagnosis,genetics,tau Proteins},
mendeley-groups = {PhDThesis/Review},
number = {18},
pages = {1376--1382},
pmid = {22491869},
title = {{Predicting missing biomarker data in a longitudinal study of Alzheimer disease.}},
volume = {78},
year = {2012}
}
@article{Lorenzi2015b,
abstract = {In this work we propose a novel Gaussian process-based spatio-temporal model of time series of images. By assuming separability of spatial and temporal processes we provide a very efficient and robust formulation for the marginal likelihood computation and the posterior prediction. The model adaptively accounts for local spatial correlations of the data, and the covariance structure is effectively parameterised by the Kronecker product of covariance matrices of very small size, each encoding only a single direction in space. We provide a simple and flexible framework for within- and between-subject modelling and prediction. In particular, we introduce the Hoffman-Ribak method for efficient inference on posterior processes and its uncertainty. The proposed framework is applied in the context of longitudinal modelling in Alzheimer's disease. We firstly demonstrate the advantage of our non-parametric method for modelling of within-subject structural changes. The results show that non-parametric methods demonstrably outperform conventional parametric methods. Then the framework is extended to optimize complex parametrized covariate kernels. Using Bayesian model comparison via marginal likelihood the framework enables to compare different hypotheses about individual change processes of images.},
annote = {cited By 3},
author = {Lorenzi, M and Ziegler, G and Alexander, D C and Ourselin, S},
journal = {Inf. Process. Med. Imaging},
mendeley-groups = {PhDThesis/Review},
pages = {626--637},
title = {{Efficient Gaussian Process-Based Modelling and Prediction of Image Time Series}},
volume = {24},
year = {2015}
}
@article{Lorenzi2017,
abstract = {The development of statistical approaches for the joint mod- elling of the temporal changes of imaging, biochemical, and clinical bio- markers is of paramount importance for improving the understanding of neurodegenerative disorders, and for providing a reference for the predic- tion and quantification of the pathology in unseen individuals. Nonethe- less, the use of disease progression models for probabilistic predictions still requires investigation, for example for accounting for missing obser- vations in clinical data, and for accurate uncertainty quantification. We tackle this problem by proposing a novel Gaussian process-based method for the joint modeling of imaging and clinical biomarker progressions from time series of individual observations. The model is formulated to account for individual random effects and time reparameterization, al- lowing non-parametric estimates of the biomarker evolution, as well as high flexibility in specifying correlation structure, and time transforma- tion models. Thanks to the Bayesian formulation, the model naturally accounts for missing data, and allows for uncertainty quantification in the estimate of evolutions, as well as for probabilistic prediction of disease staging in unseen patients. The experimental results show that the pro- posed model provides a biologically plausible description of the evolution of Alzheimer's pathology across the whole disease time-span as well as remarkable predictive performance when tested on a large clinical cohort with missing observations.},
archivePrefix = {arXiv},
arxivId = {1701.01668},
author = {Lorenzi, Marco and Filippone, Maurizio and Frisoni, Giovanni B and Alexander, Daniel C and Ourselin, Sebastien},
doi = {10.1016/j.neuroimage.2017.08.059},
eprint = {1701.01668},
issn = {10959572},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Clinical trials,Diagnosis,Disease progression modeling,Gaussian process},
mendeley-groups = {PhDThesis/Review},
pmid = {29079521},
title = {{Disease Progression Modeling and Prediction through Random Effect Gaussian Processes and Time Transformation}},
year = {2017}
}
@article{Lorenzi2014,
abstract = {Background: The morphology of the brain observed in patients affected by Alzheimer's disease (AD) is the contribution of different biological processes such as the normal aging and the AD-specific pathological matter loss. Being able to differentiate these complementary biological factors is fundamental in order to isolate and quantify the pathological AD-related structural changes, especially at the earliest phase of the disease, at prodromal and preclinical stages. Methods: We chose the ADNI baseline structural MRIs for 37 healthy subjects positive to the CSF Ab42 (Ab+), 86 patients with mild cognitive impairment (MCI) which subsequently converted to AD, 110 stable MCI, and 134 AD patients. For each subject, a "virtual aging" component was defined as the closest point with respect to the longitudinal deformation modeled for the healthy aging of a group of 63 normal subjects negative to the CSF Ab42 [1]. Once removed the aging component, the remaining specific morphological changes were analyzed group-wise, in order to characterize the atrophy patterns at the different clinical stages, and to test their predictive power in encoding the pathological disease progression. Results: Even though the considered groups did not significantly differ for age, the estimated virtual ages increased as the clinical condition get worse, and were significantly higher for the MCI stable, converters, and AD groups when compared to the healthy Abeta- (p{\textless}0.05, standard two sample t- test). After removing the healthy component, the morphological changes specific for the healthy Abeta+ were mild, while the changes specific for the MCI converters were more pronounced and mapped to frontal lobes, ventricles, temporal poles, entorhinal cortex and hippocampi. The same pattern, although slightly more pronounced, was appreciable for the AD patients. The stable MCIs showed a milder deformation pattern, mapping essentially to the ventricles and temporal poles. The predictive power of the specific component was 91{\%} sensitivity and 84{\%} specificity for the discrimination AD vs. healthy, and 67{\%} sensitivity and 63{\%} specificity for the discrimination MCI stable vs. MCI converters. Conclusion: We provided a rich description of the anatomical changes observed across the AD time span: normal aging, normal aging at risk, conversion to MCI and latest AD stages. More advanced AD stages were associated to both "virtually older" brains, and to increased specific morphological changes that were not related to the normal aging. Importantly, the specific changes provided a good identification of the pathological AD atrophy. These results provide new insights that can lead to new understandings of the AD dynamics, and to novel techniques for the modeling and the early detection of the disease.},
author = {Lorenzi, Marco and Pennec, Xavier and Frisoni, Giovanni B and Ayache, Nicholas},
isbn = {1279-7707},
journal = {Neurobiol Aging},
keywords = {Alzheimer disease,Student t test,aging,atrophy,biological factor,brain,cerebrospinal fluid,clinical trial (topic),disease course,dynamics,entorhinal cortex,frontal lobe,hippocampus,human,mild cognitive impairment,model,morphology,normal human,nuclear magnetic resonance,patient,risk},
mendeley-groups = {PhDThesis/Review},
pages = {801},
pmid = {70988198},
title = {{Disentangling normal aging from Alzheimer's disease in structural MR images}},
volume = {16 (9)},
year = {2014}
}
@article{Lu2017,
abstract = {To perform a joint analysis of multivariate neuroimaging phenotypes and candidate genetic markers obtained from longitudinal studies, we develop a Bayesian longitudinal low-rank regression (L2R2) model. The L2R2 model integrates three key methodologies: a low-rank matrix for approximating the high-dimensional regression coefficient matrices corresponding to the genetic main effects and their interactions with time, penalized splines for characterizing the overall time effect, and a sparse factor analysis model coupled with random effects for capturing within-subject spatio-temporal correlations of longitudinal phenotypes. Posterior computation proceeds via an efficient Markov chain Monte Carlo algorithm. Simulations show that the L2R2 model outperforms several other competing methods. We apply the L2R2 model to investigate the effect of single nucleotide polymorphisms (SNPs) on the top 10 and top 40 previously reported Alzheimer disease-associated genes. We also identify associations between the interactions of these SNPs with patient age and the tissue volumes of 93 regions of interest from patients' brain images obtained from the Alzheimer's Disease Neuroimaging Initiative.},
author = {Lu, Zhao-Hua and Khondker, Zakaria and Ibrahim, Joseph G and Wang, Yue and Zhu, Hongtu},
doi = {10.1016/j.neuroimage.2017.01.052},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { Single Nucleotide,Algorithms,Alzheimer Disease,Bayes Theorem,Genetic Markers,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Markov Chains,Monte Carlo Method,Neuroimaging,Polymorphism,diagnostic imaging,genetics,methods},
mendeley-groups = {PhDThesis/Review},
pages = {305--322},
pmid = {28143775},
title = {{Bayesian longitudinal low-rank regression models for imaging genetic data from longitudinal studies.}},
volume = {149},
year = {2017}
}
@article{McEvoy2011,
abstract = {To assess whether single-time-point and longitudinal volumetric magnetic resonance (MR) imaging measures provide predictive prognostic information in patients with amnestic mild cognitive impairment (MCI).},
annote = {Statistical study of measurements.

Very pure statistical.},
author = {McEvoy, Linda K and Holland, Dominic and Hagler, Donald J and Fennema-Notestine, Christine and Brewer, James B and Dale, Anders M},
doi = {10.1148/radiol.11101975},
isbn = {1527-1315},
issn = {1527-1315},
journal = {Radiology},
keywords = {80 and over,Aged,Alzheimer Disease,Alzheimer Disease: complications,Alzheimer Disease: diagnosis,Alzheimer Disease: pathology,Case-Control Studies,Chi-Square Distribution,Cognition Disorders,Cognition Disorders: diagnosis,Cognition Disorders: etiology,Cognition Disorders: pathology,Discriminant Analysis,Female,Humans,Magnetic Resonance Imaging,Magnetic Resonance Imaging: methods,Male,Middle Aged,Prognosis,Prospective Studies,ROC Curve,Sensitivity and Specificity,Survival Analysis},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {834--843},
pmid = {21471273},
title = {{Mild cognitive impairment: baseline and longitudinal structural MR imaging measures improve predictive prognosis.}},
volume = {259},
year = {2011}
}
@article{Ghazi2019,
abstract = {Disease progression modeling (DPM) using longitudinal data is a challenging machine learning task. Existing DPM algorithms neglect temporal dependencies among measurements, make parametric assumptions about biomarker trajectories, do not model multiple biomarkers jointly, and need an alignment of subjects' trajectories. In this paper, recurrent neural networks (RNNs) are utilized to address these issues. However, in many cases, longitudinal cohorts contain incomplete data, which hinders the application of standard RNNs and requires a pre-processing step such as imputation of the missing values. Instead, we propose a generalized training rule for the most widely used RNN architecture, long short-term memory (LSTM) networks, that can handle both missing predictor and target values. The proposed LSTM algorithm is applied to model the progression of Alzheimer's disease (AD) using six volumetric magnetic resonance imaging (MRI) biomarkers, i.e., volumes of ventricles, hippocampus, whole brain, fusiform, middle temporal gyrus, and entorhinal cortex, and it is compared to standard LSTM networks with data imputation and a parametric, regression-based DPM method. The results show that the proposed algorithm achieves a significantly lower mean absolute error (MAE) than the alternatives with p {\textless}0.05 using Wilcoxon signed rank test in predicting values of almost all of the MRI biomarkers. Moreover, a linear discriminant analysis (LDA) classifier applied to the predicted biomarker values produces a significantly larger area under the receiver operating characteristic curve (AUC) of 0.90 vs. at most 0.84 with p {\textless}0.001 using McNemar's test for clinical diagnosis of AD. Inspection of MAE curves as a function of the amount of missing data reveals that the proposed LSTM algorithm achieves the best performance up until more than 74{\%} missing values. Finally, it is illustrated how the method can successfully be applied to data with varying time intervals. This paper shows that built-in handling of missing values in training an LSTM network benefits the application of RNNs in neurodegenerative disease progression modeling in longitudinal cohorts.},
author = {{Mehdipour Ghazi}, Mostafa and Nielsen, Mads and Pai, Akshay and Cardoso, M Jorge and Modat, Marc and Ourselin, S{\'{e}}bastien and S{\o}rensen, Lauge},
doi = {10.1016/j.media.2019.01.004},
issn = {13618423},
journal = {Med. Image Anal.},
keywords = {Alzheimer's disease,Disease progression modeling,Linear discriminant analysis,Long short-term memory,Magnetic resonance imaging,Recurrent neural networks},
mendeley-groups = {PhDThesis/Review},
pages = {39--46},
publisher = {Elsevier},
title = {{Training recurrent neural networks robust to incomplete data: Application to Alzheimer's disease progression modeling}},
volume = {53},
year = {2019}
}
@article{Mendelson2017,
abstract = {The last decade has seen a great proliferation of supervised learning pipelines for individual diagnosis and prognosis in Alzheimer's disease. As more pipelines are developed and evaluated in the search for greater performance, only those results that are relatively impressive will be selected for publication. We present an empirical study to evaluate the potential for optimistic bias in classification performance results as a result of this selection. This is achieved using a novel, resampling-based experiment design that effectively simulates the optimisation of pipeline specifications by individuals or collectives of researchers using cross validation with limited data. Our findings indicate that bias can plausibly account for an appreciable fraction (often greater than half) of the apparent performance improvement associated with the pipeline optimisation, particularly in small samples. We discuss the consistency of our findings with patterns observed in the literature and consider strategies for bias reduction and mitigation.},
author = {Mendelson, Alex F and Zuluaga, Maria A and Lorenzi, Marco and Hutton, Brian F and Ourselin, S??bastien},
doi = {10.1016/j.nicl.2016.12.018},
issn = {22131582},
journal = {NeuroImage Clin.},
keywords = {ADNI,Alzheimer's disease,Classification,Cross validation,Overfitting,Selection bias},
mendeley-groups = {PhDThesis/Review},
pages = {400--416},
pmid = {28271040},
title = {{Selection bias in the reported performances of AD classification pipelines}},
volume = {14},
year = {2017}
}
@article{Mills2014,
abstract = {Magnetic resonance imaging (MRI) has allowed the unprecedented capability to measure the human brain in vivo. This technique has paved the way for longitudinal studies exploring brain changes across the entire life span. Results from these studies have given us a glimpse into the remarkably extended and multifaceted development of our brain, converging with evidence from anatomical and histological studies. Ever-evolving techniques and analytical methods provide new avenues to explore and questions to consider, requiring researchers to balance excitement with caution. This review addresses what MRI studies of structural brain development in children and adolescents typically measure and how. We focus on measurements of brain morphometry (e.g., volume, cortical thickness, surface area, folding patterns), as well as measurements derived from diffusion tensor imaging (DTI). By integrating finding from multiple longitudinal investigations, we give an update on current knowledge of structural brain development and how it relates to other aspects of biological development and possible underlying physiological mechanisms. Further, we review and discuss current strategies in image processing, analysis techniques and modeling of brain development. We hope this review will aid current and future longitudinal investigations of brain development, as well as evoke a discussion amongst researchers regarding best practices. ?? Published by Elsevier Ltd.},
annote = {A bit out of scope, but interesting nonetheless.},
author = {Mills, Kathryn L and Tamnes, Christian K},
doi = {10.1016/j.dcn.2014.04.004},
isbn = {1878-9293},
issn = {18789307},
journal = {Dev. Cogn. Neurosci.},
keywords = {Adolescence,Childhood,DTI,MRI,Maturation,Morphometry},
mendeley-groups = {PhDThesis/Review},
pages = {172--190},
pmid = {24879112},
title = {{Methods and considerations for longitudinal structural brain imaging analysis across development}},
volume = {9},
year = {2014}
}
@article{Minhas2016,
abstract = {The goal of this study is to introduce a nonparametric technique for predicting conversion from Mild Cognitive impairment (MCI)-to-Alzheimer's disease (AD). Progression of a slowly progressing disease such as AD benefits from the use of longitudinal data; however, research till now is limited due to the insufficient patient data and short follow-up time. A small dataset size invalidates the estimation of underlying disease progression model; hence, a supervised nonparametric method is proposed. While depicting a real-world setting, longitudinal data of three years are employed for training, whereas only the baseline visit's data is used for validation. The train set is preprocessed for extraction of two dense clusters representing the subjects who remain stable at MCI or progress to AD after three years of the baseline visit. Similarity between these clusters and the test point is calculated in Euclidean space. Multiple features from two modalities of biomarkers, i.e., neuropsychological measures (NM) and structural magnetic resonance imaging (MRI) morphometry are also analyzed. Due to the limited MCI dataset size (NM: 145, MRI: 52, NM+MRI: 29), leave-one-out cross validation setup is employed for performance evaluation. The algorithm performance is noted for both unimodal case and bimodal cases. Superior performance (accuracy: 89.66{\%}, sensitivity: 87.50{\%}, specificity: 92.31{\%}, precision: 93.33{\%}) is delivered by multivariate predictors. Three notable conclusions of this study are: 1) Longitudinal data are more powerful than the temporal data, 2) MRI is a better predictor of MCI-to-AD conversion than NM, and 3) multivariate predictors outperform single predictor models.},
annote = {From Duplicate 2 (A Non Parametric Approach for Mild Cognitive Impairment to AD Conversion Prediction: Results on Longitudinal Data. - Minhas; Khanum; Riaz; Alvi; Khan)
And Duplicate 3 (A Non Parametric Approach for Mild Cognitive Impairment to AD Conversion Prediction: Results on Longitudinal Data. - Minhas; Khanum; Riaz; Alvi; Khan)

Interesting classification approach that do not use a real ML technique, but I think that could be interesting to mention either there (with the ML) AND in the statistics part.},
author = {Minhas, Sidra and Khanum, Aasia and Riaz, Farhan and Alvi, Atif and Khan, S A Shoab Ahmed and Minhas and Khanum and Riaz and Alvi, Atif and Khan and Minhas, Sidra and Khanum, Aasia and Riaz, Farhan and Alvi, Atif and Khan, S A Shoab Ahmed},
doi = {10.1109/JBHI.2016.2608998},
issn = {2168-2208 (Electronic)},
journal = {IEEE J. Biomed. Heal. Informatics},
keywords = {80 and over,Aged,Alzheimer Disease,Biomarkers,Cognitive Dysfunction,Computational Biology,Disease Progression,Female,Humans,Magnetic Resonance Imaging,Male,Nonparametric,Positron-Emission Tomography,Statistics,cerebrospinal fluid,diagnosis,diagnostic imaging,methods},
mendeley-groups = {PhDThesis/Review},
number = {99},
pages = {1--2},
pmid = {28113683},
title = {{A Non Parametric Approach for Mild Cognitive Impairment to AD Conversion Prediction: Results on Longitudinal Data.}},
volume = {21},
year = {2016}
}
@article{Misra2009,
abstract = {High-dimensional pattern classification was applied to baseline and multiple follow-up MRI scans of the Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI), in order to investigate the potential of predicting short-term conversion to Alzheimer's Disease (AD) on an individual basis. MCI participants that converted to AD (average follow-up 15??months) displayed significantly lower volumes in a number of grey matter (GM) regions, as well as in the white matter (WM). They also displayed more pronounced periventricular small-vessel pathology, as well as an increased rate of increase of such pathology. Individual person analysis was performed using a pattern classifier previously constructed from AD patients and cognitively normal (CN) individuals to yield an abnormality score that is positive for AD-like brains and negative otherwise. The abnormality scores measured from MCI non-converters (MCI-NC) followed a bimodal distribution, reflecting the heterogeneity of this group, whereas they were positive in almost all MCI converters (MCI-C), indicating extensive patterns of AD-like brain atrophy in almost all MCI-C. Both MCI subgroups had similar MMSE scores at baseline. A more specialized classifier constructed to differentiate converters from non-converters based on their baseline scans provided good classification accuracy reaching 81.5{\%}, evaluated via cross-validation. These pattern classification schemes, which distill spatial patterns of atrophy to a single abnormality score, offer promise as biomarkers of AD and as predictors of subsequent clinical progression, on an individual patient basis. ?? 2008 Elsevier Inc. All rights reserved.},
annote = {Atrophy rates for classification, pattern classifier.
Builds a classifier, a bit of machine learning.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Misra, Chandan and Fan, Yong and Davatzikos, Christos},
doi = {10.1016/j.neuroimage.2008.10.031},
eprint = {NIHMS150003},
isbn = {1053-8119},
issn = {10538119},
journal = {Neuroimage},
keywords = {AD,Alzheimer's disease,Early detection,Imaging biomarker,MCI,Mild cognitive impairment,Pattern classification,Structural MRI},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {1415--1422},
pmid = {19027862},
title = {{Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of short-term conversion to AD: Results from ADNI}},
volume = {44},
year = {2009}
}
@article{Moradi2015,
abstract = {Mild cognitive impairment (MCI) is a transitional stage between age-related cognitive decline and Alzheimer's disease (AD). For the effective treatment of AD, it would be important to identify MCI patients at high risk for conversion to AD. In this study, we present a novel magnetic resonance imaging (MRI)-based method for predicting the MCI-to-AD conversion from one to three years before the clinical diagnosis. First, we developed a novel MRI biomarker of MCI-to-AD conversion using semi-supervised learning and then integrated it with age and cognitive measures about the subjects using a supervised learning algorithm resulting in what we call the aggregate biomarker. The novel characteristics of the methods for learning the biomarkers are as follows: 1) We used a semi-supervised learning method (low density separation) for the construction of MRI biomarker as opposed to more typical supervised methods; 2) We performed a feature selection on MRI data from AD subjects and normal controls without using data from MCI subjects via regularized logistic regression; 3) We removed the aging effects from the MRI data before the classifier training to prevent possible confounding between AD and age related atrophies; and 4) We constructed the aggregate biomarker by first learning a separate MRI biomarker and then combining it with age and cognitive measures about the MCI subjects at the baseline by applying a random forest classifier. We experimentally demonstrated the added value of these novel characteristics in predicting the MCI-to-AD conversion on data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. With the ADNI data, the MRI biomarker achieved a 10-fold cross-validated area under the receiver operating characteristic curve (AUC) of 0.7661 in discriminating progressive MCI patients (pMCI) from stable MCI patients (sMCI). Our aggregate biomarker based on MRI data together with baseline cognitive measurements and age achieved a 10-fold cross-validated AUC score of 0.9020 in discriminating pMCI from sMCI. The results presented in this study demonstrate the potential of the suggested approach for early AD diagnosis and an important role of MRI in the MCI-to-AD conversion prediction. However, it is evident based on our results that combining MRI data with cognitive test results improved the accuracy of the MCI-to-AD conversion prediction.},
annote = {This paper proposes a standarized dataset},
author = {Moradi, Elaheh and Pepe, Antonietta and Gaser, Christian and Huttunen, Heikki and Tohka, Jussi},
doi = {10.1016/j.neuroimage.2014.10.002},
isbn = {1053-8119},
issn = {10959572},
journal = {Neuroimage},
keywords = {ADNI,Alzheimer's disease,Classification,Early diagnosis,Feature selection,Low density separation,Magnetic resonance imaging,Mild cognitive impairment,Semi-supervised learning,Support vector machine},
mendeley-groups = {PhDThesis/Review},
pages = {398--412},
pmid = {25312773},
title = {{Machine learning framework for early MRI-based Alzheimer's conversion prediction in MCI subjects}},
volume = {104},
year = {2015}
}
@article{Mubeen2017,
abstract = {RATIONALE AND OBJECTIVES: Early prediction of incipient Alzheimer's disease (AD) dementia in individuals with mild cognitive impairment (MCI) is important for timely therapeutic intervention and identifying participants for clinical trials at greater risk of developing AD. Methods to predict incipient AD in MCI have mostly utilized cross-sectional data. Longitudinal data enables estimation of the rate of change of variables, which along with the variable levels have been shown to improve prediction power. While some efforts have already been made in this direction, all previous longitudinal studies have been based on observation periods longer than one year, hence limiting their practical utility. It remains to be seen if follow-up evaluations within shorter intervals can significantly improve the accuracy of prediction in this problem. Our aim was to determine the added value of incorporating 6-month longitudinal data for predicting progression from MCI to AD. MATERIALS AND METHODS: Using 6-months longitudinal data from 247 participants with MCI, we trained two Random Forest classifiers to distinguish between progressive MCI (n=162) and stable MCI (n=85) cases. These models utilized structural MRI, neurocognitive assessments, and demographic information. The first model (cross-sectional) only used baseline data. The second model (longitudinal) used data from both baseline and a 6-month follow-up evaluation allowing the model to additionally incorporate biomarkers' rate of change. RESULTS: The longitudinal model (AUC=0.87; accuracy=80.2{\%}) performed significantly better (P{\textless}0.05) than the cross-sectional model (AUC=0.82; accuracy=71.7{\%}). CONCLUSION: Short-term longitudinal assessments significantly enhance the performance of AD prediction models.},
author = {Mubeen, Asim M and Asaei, Ali and Bachman, Alvin H and Sidtis, John J and Ardekani, Babak A},
doi = {10.1016/j.neurad.2017.05.008},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {0150-9861 (Print)},
journal = {J. Neuroradiol.},
keywords = {Aged,Algorithms,Alzheimer Disease,Biomarkers,Cognitive Dysfunction,Female,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neuropsychological Tests,Predictive Value of Tests,diagnostic imaging,methods,pathology},
mendeley-groups = {PhDThesis/Review},
month = {oct},
number = {6},
pages = {381--387},
pmid = {28676345},
title = {{A six-month longitudinal evaluation significantly improves accuracy of predicting incipient Alzheimer's disease in mild cognitive impairment.}},
volume = {44},
year = {2017}
}

@inproceedings{Chung2014,
abstract = {In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.},
archivePrefix = {arXiv},
arxivId = {1412.3555},
author = {Chung, Junyoung and Gulcehre, Caglar and Cho, KyungHyun and Bengio, Yoshua},
booktitle = {NIPS 2014 Work. Deep Learn.},
eprint = {1412.3555},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Chung et al. - 2014 - Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.pdf:pdf},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates,PhDThesis/VAE},
pages = {1--9},
month = {dec},
title = {{Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling}},
year = {2014}
}

@inproceedings{Kingma2014,
abstract = {How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions is two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.},
archivePrefix = {arXiv},
arxivId = {1312.6114},
author = {Kingma, Diederik P. and Welling, Max},
booktitle = {2nd Int. Conf. Learn. Represent. ICLR 2014 - Conf. Track Proc.},
eprint = {1312.6114},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Kingma, Welling - 2014 - Auto-encoding variational bayes.pdf:pdf},
mendeley-groups = {Papers bib/mcvae{\_}paper,PhDThesis,PhDThesis/VAE},
number = {Ml},
pages = {1--14},
title = {{Auto-encoding variational bayes}},
year = {2014}
}

@article{Reuter2010,
abstract = {The registration of images is a task that is at the core of many applications in computer vision. In computational neuroimaging where the automated segmentation of brain structures is frequently used to quantify change, a highly accurate registration is necessary for motion correction of images taken in the same session, or across time in longitudinal studies where changes in the images can be expected. This paper, inspired by Nestares and Heeger (2000), presents a method based on robust statistics to register images in the presence of differences, such as jaw movement, differential MR distortions and true anatomical change. The approach we present guarantees inverse consistency (symmetry), can deal with different intensity scales and automatically estimates a sensitivity parameter to detect outlier regions in the images. The resulting registrations are highly accurate due to their ability to ignore outlier regions and show superior robustness with respect to noise, to intensity scaling and outliers when compared to state-of-the-art registration tools such as FLIRT (in FSL) or the coregistration tool in SPM. {\textcopyright} 2010 Elsevier Inc.},
author = {Reuter, Martin and Rosas, H. Diana and Fischl, Bruce},
doi = {10.1016/j.neuroimage.2010.07.020},
issn = {10538119},
journal = {Neuroimage},
keywords = {Image registration,Inverse consistent alignment,Longitudinal analysis,Motion correction,Robust statistics},
mendeley-groups = {Papers bib/mcvae{\_}paper/cca},
month = {dec},
number = {4},
pages = {1181--1196},
pmid = {20637289},
publisher = {Neuroimage},
title = {{Highly accurate inverse consistent registration: A robust approach}},
volume = {53},
year = {2010}
}


@inproceedings{Kingma2015a,
abstract = {We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.},
archivePrefix = {arXiv},
arxivId = {1412.6980},
author = {Kingma, Diederik P. and Ba, Jimmy Lei},
booktitle = {3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc.},
eprint = {1412.6980},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Kingma, Ba - 2015 - Adam A method for stochastic optimization.pdf:pdf},
mendeley-groups = {PhDThesis/VAE},
pages = {1--15},
month = {dec},
publisher = {International Conference on Learning Representations, ICLR},
title = {{Adam: A method for stochastic optimization}},
year = {2015}
}



@article{Reuter2012,
abstract = {Longitudinal image analysis has become increasingly important in clinical studies of normal aging and neurodegenerative disorders. Furthermore, there is a growing appreciation of the potential utility of longitudinally acquired structural images and reliable image processing to evaluate disease modifying therapies. Challenges have been related to the variability that is inherent in the available cross-sectional processing tools, to the introduction of bias in longitudinal processing and to potential over-regularization. In this paper we introduce a novel longitudinal image processing framework, based on unbiased, robust, within-subject template creation, for automatic surface reconstruction and segmentation of brain MRI of arbitrarily many time points. We demonstrate that it is essential to treat all input images exactly the same as removing only interpolation asymmetries is not sufficient to remove processing bias. We successfully reduce variability and avoid over-regularization by initializing the processing in each time point with common information from the subject template. The presented results show a significant increase in precision and discrimination power while preserving the ability to detect large anatomical deviations; as such they hold great potential in clinical applications, e.g. allowing for smaller sample sizes or shorter trials to establish disease specific biomarkers or to quantify drug effects. {\textcopyright} 2012 Elsevier Inc.},
author = {Reuter, Martin and Schmansky, Nicholas J. and Rosas, H. Diana and Fischl, Bruce},
doi = {10.1016/j.neuroimage.2012.02.084},
issn = {10538119},
journal = {Neuroimage},
keywords = {FreeSurfer,MRI biomarkers,Reliability and power,Unbiased longitudinal image processing,Within-subject template},
mendeley-groups = {Papers bib/mcvae{\_}paper/cca},
month = {jul},
number = {4},
pages = {1402--1418},
pmid = {22430496},
publisher = {Neuroimage},
title = {{Within-subject template estimation for unbiased longitudinal image analysis}},
volume = {61},
year = {2012}
}


@inproceedings{Kingma2015,
abstract = {We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic gradients for variational Bayesian inference (SGVB) of a posterior over model parameters, while retaining parallelizability. This local reparameterization translates uncertainty about global parameters into local noise that is independent across datapoints in the minibatch. Such parameterizations can be trivially parallelized and have variance that is inversely proportional to the minibatch size, generally leading to much faster convergence. Additionally, we explore a connection with dropout: Gaussian dropout objectives correspond to SGVB with local reparameterization, a scale-invariant prior and proportionally fixed posterior variance. Our method allows inference of more flexibly parameterized posteriors; specifically, we propose variational dropout, a generalization of Gaussian dropout where the dropout rates are learned, often leading to better models. The method is demonstrated through several experiments.},
archivePrefix = {arXiv},
arxivId = {1506.02557},
author = {Kingma, Diederik P. and Salimans, Tim and Welling, Max},
booktitle = {Adv. Neural Inf. Process. Syst.},
eprint = {1506.02557},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Kingma, Salimans, Welling - 2015 - Variational Dropout and the Local Reparameterization Trick.pdf:pdf},
issn = {10495258},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates},
month = {jun},
pages = {2575--2583},
publisher = {Neural information processing systems foundation},
title = {{Variational dropout and the local reparameterization trick}},
volume = {2015-Janua},
year = {2015}
}

@inproceedings{Marinescu2019a,
abstract = {We present BrainPainter, a software that automatically generates images of highlighted brain structures given a list of numbers corresponding to the output colours of each region. Compared to existing visualisation software (i.e. Freesurfer, SPM, 3D Slicer), BrainPainter has three key advantages: (1) it does not require the input data to be in a specialised format, allowing BrainPainter to be used in combination with any neuroimaging analysis tools, (2) it can visualise both cortical and subcortical structures and (3) it can be used to generate movies showing dynamic processes, e.g. propagation of pathology on the brain. We highlight three use cases where BrainPainter was used in existing neuroimaging studies: (1) visualisation of the degree of atrophy through interpolation along a user-defined gradient of colours, (2) visualisation of the progression of pathology in Alzheimer's disease as well as (3) visualisation of pathology in subcortical regions in Huntington's disease. Moreover, through the design of BrainPainter we demonstrate the possibility of using a powerful 3D computer graphics engine such as Blender to generate brain visualisations for the neuroscience community. Blender's capabilities, e.g. particle simulations, motion graphics, UV unwrapping, raster graphics editing, raytracing and illumination effects, open a wealth of possibilities for brain visualisation not available in current neuroimaging software. BrainPainter (Source code: https://github.com/mrazvan22/brain-coloring) is customisable, easy to use, and can run straight from the web browser: http://brainpainter.csail.mit.edu. It can be used to visualise biomarker data from any brain imaging modality, or simply to highlight a particular brain structure for e.g. anatomy courses.},
address = {Cham},
author = {Marinescu, R$\backslash$uazvan V and Eshaghi, Arman and Alexander, Daniel C and Golland, Polina},
booktitle = {Multimodal Brain Image Anal. Math. Found. Comput. Anat.},
editor = {Zhu, Dajiang and Yan, Jingwen and Huang, Heng and Shen, Li and Thompson, Paul M and Westin, Carl-Fredrik and Pennec, Xavier and Joshi, Sarang and Nielsen, Mads and Fletcher, Tom and Durrleman, Stanley and Sommer, Stefan},
isbn = {978-3-030-33226-6},
mendeley-groups = {PhDThesis},
pages = {112--120},
publisher = {Springer International Publishing},
title = {{BrainPainter: A Software for the Visualisation of Brain Structures, Biomarkers and Associated Pathological Processes}},
year = {2019}
}


@article{Cao2019,
abstract = {Canonical Correlation Analysis is a technique in multivariate data analysis for finding linear projections that maximize the correlation between two groups of variables. The correlations are typically defined without accounting for the serial correlations between observations, a typical setting for time series data. To understand the coupling dynamics and temporal variations between the two time-varying sources, we introduce the time-dependent canonical correlation analysis (TDCCA), a method for inferring time-dependent canonical vectors from multilevel time series data. A convex formulation of the problem is proposed, which leverages the singular value decomposition (SVD) characterization of all solutions of the CCA problem. We use simulated datasets to validate the proposed algorithm. Moreover, we propose a novel measure, canonical correlation variation as another way to assess the dynamic pattern of brain connections and we apply it to a real resting state fMRI dataset to study the aging effects on brain connectivity. Additionally, we explore our proposed method in a task-related fMRI to detect the temporal dynamics due to different motor tasks. We show that, compared to extant methods, the TDCCA-based approach not only detect temporal changes but also improves feature extraction. Together, this paper contributes broadly to new computational methodologies in understanding multilevel time series.},
annote = {We have ways to generate synthetic data described in the paper, compare it.},
author = {Cao, Xuefei and Ke, Jun and Sandstede, Bj{\"{o}}rn and Luo, Xi},
doi = {10.1101/650101},
file = {:C$\backslash$:/Users/gerar/Downloads/650101v1.full(1).pdf:pdf},
journal = {bioRxiv},
keywords = {Canonical correlation analysis,fMRI,temporal dynamics,time series},
mendeley-groups = {Papers bib/mcvae{\_}paper/cca,PhDThesis/VAE},
title = {{Time-dependent Canonical Correlation Analysis for Multilevel Time Series}},
year = {2019}
}
@article{Verbeke2014,
abstract = {Longitudinal experiments often involve multiple outcomes measured repeatedly within a set of study participants. While many questions can be answered by modeling the various outcomes separately, some questions can only be answered in a joint analysis of all of them. In this article, we will present a review of the many approaches proposed in the statistical literature. Four main model families will be presented, discussed and compared. Focus will be on presenting advantages and disadvantages of the different models rather than on the mathematical or computational details. {\textcopyright} The Author(s) 2012 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.},
annote = {General review of longitudinal general, puc citarlo jutament amb tal tal tal},
author = {Verbeke, Geert and Fieuws, Steffen and Molenberghs, Geert and Davidian, Marie},
doi = {10.1177/0962280212445834},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Verbeke et al. - 2014 - The analysis of multivariate longitudinal data A review.pdf:pdf},
issn = {09622802},
journal = {Stat. Methods Med. Res.},
keywords = {Mixed models,conditional models,latent variables,marginal models,random effects,shared parameters},
mendeley-groups = {Papers bib/mcvae{\_}paper/cca,PhDThesis/VAE},
month = {feb},
number = {1},
pages = {42--49},
pmid = {22523185},
publisher = {NIH Public Access},
title = {{The analysis of multivariate longitudinal data: A review}},
volume = {23},
year = {2014}
}



@article{Sherstinsky2020,
abstract = {Because of their effectiveness in broad practical applications, LSTM networks have received a wealth of coverage in scientific journals, technical blogs, and implementation guides. However, in most articles, the inference formulas for the LSTM network and its parent, RNN, are stated axiomatically, while the training formulas are omitted altogether. In addition, the technique of “unrolling” an RNN is routinely presented without justification throughout the literature. The goal of this tutorial is to explain the essential RNN and LSTM fundamentals in a single document. Drawing from concepts in Signal Processing, we formally derive the canonical RNN formulation from differential equations. We then propose and prove a precise statement, which yields the RNN unrolling technique. We also review the difficulties with training the standard RNN and address them by transforming the RNN into the “Vanilla LSTM”1 network through a series of logical arguments. We provide all equations pertaining to the LSTM system together with detailed descriptions of its constituent entities. Albeit unconventional, our choice of notation and the method for presenting the LSTM system emphasizes ease of understanding. As part of the analysis, we identify new opportunities to enrich the LSTM system and incorporate these extensions into the Vanilla LSTM network, producing the most general LSTM variant to date. The target reader has already been exposed to RNNs and LSTM networks through numerous available resources and is open to an alternative pedagogical approach. A Machine Learning practitioner seeking guidance for implementing our new augmented LSTM model in software for experimentation and research will find the insights and derivations in this treatise valuable as well.},
archivePrefix = {arXiv},
arxivId = {1808.03314},
author = {Sherstinsky, Alex},
doi = {10.1016/j.physd.2019.132306},
eprint = {1808.03314},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sherstinsky - 2018 - Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network.pdf:pdf},
issn = {01672789},
journal = {Phys. D Nonlinear Phenom.},
keywords = {Convolutional input context windows,External input gate,LSTM,RNN,RNN unfolding/unrolling},
mendeley-groups = {Papers bib/mcvae{\_}paper/candidates},
month = {aug},
publisher = {Elsevier B.V.},
title = {{Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network}},
volume = {404},
year = {2020}
}


@article{Mueller2005,
abstract = {With increasing life expectancy in developed countries, the incidence of Alzheimer's disease (AD) and its socioeconomic impact are growing. Increasing knowledge of the mechanisms of AD facilitates the development of treatment strategies aimed at slowing down or preventing neuronal death. AD treatment trials using clinical outcome measures require long observation times and large patient samples. There is increasing evidence that neuroimaging and cerebrospinal fluid and blood biomarkers may provide information that may reduce sample sizes and observation periods. The Alzheimer's Disease Neuroimaging Initiative will help identify clinical, neuroimaging, and biomarker outcome measures that provide the highest power for measurement of longitudinal changes and for prediction of transitions. {\textcopyright}2006 Elsevier Inc. All rights reserved.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Mueller, Susanne G and Weiner, Michael W and Thal, Leon J and Petersen, Ronald C and Jack, Clifford and Jagust, William and Trojanowski, John Q and Toga, Arthur W and Beckett, Laurel},
doi = {10.1016/j.nic.2005.09.008},
eprint = {NIHMS150003},
isbn = {1052-5149 (Print)$\backslash$n1052-5149 (Linking)},
issn = {10525149},
journal = {Neuroimaging Clin. N. Am.},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {869--877},
pmid = {16443497},
title = {{The Alzheimer's disease neuroimaging initiative}},
volume = {15},
year = {2005}
}
@article{Nasiri2018,
abstract = {In this review paper, some applications of the mixed effect modeling in medial image processing and longitudinal analysis is studied. For this purpose, a general structure is extracted from some of the researches in the literature. This structure includes a number of essential elements, each of which having a few design choices, namely 1) tracked features, 2) models mathematical expression and random effects and finally 3) response prediction. Two research study examples in Alzheimers disease and prostate tomography are also briefly introduced to further discuss the above design choices.},
annote = {MERD{\'{I}}SSIMA},
archivePrefix = {arXiv},
arxivId = {1803.04241},
author = {Nasiri, Fatemeh and Acosta-Tamayo, Oscar},
eprint = {1803.04241},
mendeley-groups = {PhDThesis/Review},
month = {mar},
title = {{A Review of Mixed-Effect Modeling in the Longitudinal Studies Using Medical Images of Patients}},
year = {2018}
}

@article{Cullen2020,
abstract = {We developed models for individualized risk prediction of cognitive decline in mild cognitive impairment (MCI) using plasma biomarkers of $\beta$-amyloid (A$\beta$), tau and neurodegeneration. A total of 573 patients with MCI from the Swedish BioFINDER study and the Alzheimer's Disease Neuroimaging Initiative (ADNI) were included in the study. The primary outcomes were longitudinal cognition and conversion to Alzheimer's disease (AD) dementia. A model combining tau phosphorylated at threonine 181 (P-tau181) and neurofilament light (NfL), but not A$\beta$42/A$\beta$40, had the best prognosis performance of all models (area under the curve = 0.88 for 4-year conversion to AD in BioFINDER, validated in ADNI), was stronger than a basic model of age, sex, education and baseline cognition, and performed similarly to cerebrospinal fluid biomarkers. A publicly available online tool for individualized prognosis in MCI based on our combined plasma biomarker models is introduced. Combination of plasma biomarkers may be of high value to identify individuals with MCI who will progress to AD dementia in clinical trials and in clinical practice. This study shows that combinations of blood-based biomarkers can be used to predict cognitive decline and dementia due to Alzheimer's disease in patients with mild cognitive impairment. Biomarkers for tau and neurodegeneration provided accurate prognosis of decline and conversion over four years.},
author = {Cullen, Nicholas C. and Leuzy, Antoine and Palmqvist, Sebastian and Janelidze, Shorena and Stomrud, Erik and Pesini, Pedro and Sarasa, Leticia and Allu{\'{e}}, Jos{\'{e}} Antonio and Proctor, Nicholas K. and Zetterberg, Henrik and Dage, Jeffrey L. and Blennow, Kaj and Mattsson-Carlgren, Niklas and Hansson, Oskar},
doi = {10.1038/s43587-020-00003-5},
file = {:C$\backslash$:/Users/gerar/Downloads/s43587-020-00003-5.pdf:pdf},
journal = {Nat. Aging},
mendeley-groups = {PhDThesis/Introduction},
title = {{Individualized prognosis of cognitive decline and dementia in mild cognitive impairment based on plasma biomarker combinations}},
year = {2020}
}
@article{Moscoso2020,
abstract = {{\textless}p{\textgreater}Tau phosphorylated at threonine 181 (p-tau181) measured in blood plasma has recently been proposed as an accessible, scalable, and highly specific biomarker for Alzheimer's disease. Longitudinal studies, however, investigating the temporal dynamics of this novel biomarker are lacking. It is therefore unclear when in the disease process plasma p-tau181 increases above physiological levels and how it relates to the spatiotemporal progression of Alzheimer's disease characteristic pathologies. We aimed to establish the natural time course of plasma p-tau181 across the sporadic Alzheimer's disease spectrum in comparison to those of established imaging and fluid-derived biomarkers of Alzheimer's disease. We examined longitudinal data from a large prospective cohort of elderly individuals enrolled in the Alzheimer's Disease Neuroimaging Initiative (ADNI) (n = 1067) covering a wide clinical spectrum from normal cognition to dementia, and with measures of plasma p-tau181 and an 18F-florbetapir amyloid-$\beta$ PET scan at baseline. A subset of participants (n = 864) also had measures of amyloid-$\beta$1–42 and p-tau181 levels in CSF, and another subset (n = 298) had undergone an 18F-flortaucipir tau PET scan 6 years later. We performed brain-wide analyses to investigate the associations of plasma p-tau181 baseline levels and longitudinal change with progression of regional amyloid-$\beta$ pathology and tau burden 6 years later, and estimated the time course of changes in plasma p-tau181 and other Alzheimer's disease biomarkers using a previously developed method for the construction of long-term biomarker temporal trajectories using shorter-term longitudinal data. Smoothing splines demonstrated that earliest plasma p-tau181 changes occurred even before amyloid-$\beta$ markers reached abnormal levels, with greater rates of change correlating with increased amyloid-$\beta$ pathology. Voxel-wise PET analyses yielded relatively weak, yet significant, associations of plasma p-tau181 with amyloid-$\beta$ pathology in early accumulating brain regions in cognitively healthy individuals, while the strongest associations with amyloid-$\beta$ were observed in late accumulating regions in patients with mild cognitive impairment. Cross-sectional and particularly longitudinal measures of plasma p-tau181 were associated with widespread cortical tau aggregation 6 years later, covering temporoparietal regions typical for neurofibrillary tangle distribution in Alzheimer's disease. Finally, we estimated that plasma p-tau181 reaches abnormal levels ∼6.5 and 5.7 years after CSF and PET measures of amyloid-$\beta$, respectively, following similar dynamics as CSF p-tau181. Our findings suggest that plasma p-tau181 increases are associated with the presence of widespread cortical amyloid-$\beta$ pathology and with prospective Alzheimer's disease typical tau aggregation, providing clear implications for the use of this novel blood biomarker as a diagnostic and screening tool for Alzheimer's disease.{\textless}/p{\textgreater}},
author = {Moscoso, Alexis and Grothe, Michel J and Ashton, Nicholas J and Karikari, Thomas K and Rodriguez, Juan Lantero and Snellman, Anniina and Su{\'{a}}rez-Calvet, Marc and Zetterberg, Henrik and Blennow, Kaj and Sch{\"{o}}ll, Michael},
doi = {10.1093/brain/awaa399},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Moscoso et al. - 2020 - Time course of phosphorylated-tau181 in blood across the Alzheimer's disease spectrum.pdf:pdf},
issn = {0006-8950},
journal = {Brain},
keywords = {Alzheimer's disease,blood biomarkers,cerebrospinal fluid,positron emission tomography,tau},
mendeley-groups = {PhDThesis/Introduction},
month = {nov},
publisher = {Oxford University Press (OUP)},
title = {{Time course of phosphorylated-tau181 in blood across the Alzheimer's disease spectrum}},
year = {2020}
}


@article{Yang2019,
abstract = {Today's artificial intelligence still faces two major challenges. One is that, in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated-learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated-learning framework, which includes horizontal federated learning, vertical federated learning, and federated transfer learning. We provide definitions, architectures, and applications for the federated-learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allowing knowledge to be shared without compromising user privacy.},
address = {New York, NY, USA},
author = {Yang, Qiang and Liu, Yang and Chen, Tianjian and Tong, Yongxin},
doi = {10.1145/3298981},
issn = {2157-6904},
journal = {ACM Trans. Intell. Syst. Technol.},
keywords = { GDPR, transfer learning,Federated learning},
mendeley-groups = {PhDThesis/Introduction},
number = {2},
publisher = {Association for Computing Machinery},
title = {{Federated Machine Learning: Concept and Applications}},
volume = {10},
year = {2019}
}

@article{Lei2020,
abstract = {Alzheimer's disease (AD) is an irreversible and progressive neurodegenerative disease. The close AD monitoring of this disease is essential for the patient treatment plan adjustment. For AD monitoring, clinical score prediction via neuroimaging data is highly desirable since it is able to reveal the disease status, adequately. For this task, most previous studies are focused on a single time point without considering relationship between neuroimaging data (e.g., Magnetic Resonance Imaging (MRI)) and clinical scores at multiple time points. Differing from these studies, we propose to build a framework based on longitudinal multiple time points data to predict clinical scores. Specifically, the proposed framework consists of three parts, feature selection based on correntropy regularized joint learning, feature encoding based on deep polynomial network, and ensemble learning for regression via the support vector regression method. Two scenarios are designed for scores prediction. Namely, scenario 1 uses the baseline data to achieve the longitudinal scores prediction, while scenario 2 utilizes all the previous time points data to obtain the predicted scores at the next time point, which can improve the score prediction's accuracy. Meanwhile, the missing clinical scores at longitudinal multiple time points are imputated to solve the incompleteness of the data. Extensive experiments on the public database of Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate that our proposed framework can effectively reveal the relationship between clinical score and MRI data and outperforms the state-of-the-art methods in scores prediction.},
author = {Lei, Baiying and Yang, Mengya and Yang, Peng and Zhou, Feng and Hou, Wen and Zou, Wenbin and Li, Xia and Wang, Tianfu and Xiao, Xiaohua and Wang, Shuqiang},
doi = {10.1016/j.patcog.2020.107247},
issn = {00313203},
journal = {Pattern Recognit.},
keywords = {Alzheimer's disease,Correntropy,Deep polynomial network,Joint learning,Longitudinal scores prediction},
mendeley-groups = {PhDThesis/Relevant papers},
month = {jun},
publisher = {Elsevier Ltd},
title = {{Deep and joint learning of longitudinal data for Alzheimer's disease prediction}},
volume = {102},
year = {2020}
}
@article{Fisher2019,
abstract = {Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Synthetic patient data generated by the CRBM accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure in the components of ADAS-Cog, and identifies sub-components associated with word recall as predictive of progression.},
archivePrefix = {arXiv},
arxivId = {1807.03876},
author = {Fisher, Charles K. and Smith, Aaron M. and Walsh, Jonathan R. and Simon, Adam J. and Edgar, Chris and Jack, Clifford R. and Holtzman, David and Russell, David and Hill, Derek and Grosset, Donald and Wood, Fred and Vanderstichele, Hugo and Morris, John and Blennow, Kaj and Marek, Ken and Shaw, Leslie M. and Albert, Marilyn and Weiner, Michael and Fox, Nick and Aisen, Paul and Cole, Patricia E. and Petersen, Ronald and Sherer, Todd and Kubick, Wayne},
doi = {10.1038/s41598-019-49656-2},
eprint = {1807.03876},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Fisher et al. - 2019 - Machine learning for comprehensive forecasting of Alzheimer's Disease progression.pdf:pdf},
issn = {20452322},
journal = {Sci. Rep.},
mendeley-groups = {PhDThesis/Relevant papers},
month = {dec},
number = {1},
pmid = {31541187},
publisher = {Nature Publishing Group},
title = {{Machine learning for comprehensive forecasting of Alzheimer's Disease progression}},
volume = {9},
year = {2019}
}


@article{Poplin2018,
abstract = {Traditionally, medical discoveries are made by observing associations, making hypotheses from them and then designing and running experiments to test the hypotheses. However, with medical images, observing and quantifying associations can often be difficult because of the wide variety of features, patterns, colours, values and shapes that are present in real data. Here, we show that deep learning can extract new knowledge from retinal fundus images. Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70). We also show that the trained deep-learning models used anatomical features, such as the optic disc or blood vessels, to generate each prediction.},
author = {Poplin, Ryan and Varadarajan, Avinash Vaidyanathan and Blumer, Katy and Liu, Yun and McConnell, Michael V. and Corrado, Greg S. and Peng, Lily and Webster, Dale R.},
doi = {10.1038/s41551-018-0195-0},
issn = {2157846X},
journal = {Nat. Biomed. Eng.},
mendeley-groups = {PhDThesis/Introduction},
number = {3},
pages = {158--164},
pmid = {31015713},
title = {{Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning}},
volume = {2},
year = {2018}
}



@article{Haibe-Kains2020,
author = {Haibe-Kains, Benjamin and Adam, George Alexandru and Hosny, Ahmed and Khodakarami, Farnoosh and Shraddha, Thakkar and Kusko, Rebecca and Sansone, Susanna-Assunta and Tong, Weida and Wolfinger, Russ D and Mason, Christopher E and Jones, Wendell and Dopazo, Joaquin and Furlanello, Cesare and Waldron, Levi and Wang, Bo and McIntosh, Chris and Goldenberg, Anna and Kundaje, Anshul and Greene, Casey S and Broderick, Tamara and Hoffman, Michael M and Leek, Jeffrey T and Korthauer, Keegan and Huber, Wolfgang and Brazma, Alvis and Pineau, Joelle and Tibshirani, Robert and Hastie, Trevor and Ioannidis, John P A and Quackenbush, John and Aerts, Hugo J W L and of Directors, Massive Analysis Quality Control (MAQC) Society Board},
doi = {10.1038/s41586-020-2766-y},
issn = {1476-4687},
journal = {Nature},
mendeley-groups = {PhDThesis/Introduction},
number = {7829},
pages = {E14--E16},
title = {{Transparency and reproducibility in artificial intelligence}},
volume = {586},
year = {2020}
}
@article{McKinney2020,
abstract = {Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7{\%} and 1.2{\%} (USA and UK) in false positives and 9.4{\%} and 2.7{\%} in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5{\%}. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88{\%}. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.},
author = {McKinney, Scott Mayer and Sieniek, Marcin and Godbole, Varun and Godwin, Jonathan and Antropova, Natasha and Ashrafian, Hutan and Back, Trevor and Chesus, Mary and Corrado, Greg S and Darzi, Ara and Etemadi, Mozziyar and Garcia-Vicente, Florencia and Gilbert, Fiona J and Halling-Brown, Mark and Hassabis, Demis and Jansen, Sunny and Karthikesalingam, Alan and Kelly, Christopher J and King, Dominic and Ledsam, Joseph R and Melnick, David and Mostofi, Hormuz and Peng, Lily and Reicher, Joshua Jay and Romera-Paredes, Bernardino and Sidebottom, Richard and Suleyman, Mustafa and Tse, Daniel and Young, Kenneth C and {De Fauw}, Jeffrey and Shetty, Shravya},
doi = {10.1038/s41586-019-1799-6},
issn = {1476-4687},
journal = {Nature},
mendeley-groups = {PhDThesis/Introduction},
number = {7788},
pages = {89--94},
title = {{International evaluation of an AI system for breast cancer screening}},
volume = {577},
year = {2020}
}



@article{Oxtoby2017,
abstract = {PURPOSE OF REVIEW This article argues that the time is approaching for data-driven disease modelling to take centre stage in the study and management of neurodegenerative disease. The snowstorm of data now available to the clinician defies qualitative evaluation; the heterogeneity of data types complicates integration through traditional statistical methods; and the large datasets becoming available remain far from the big-data sizes necessary for fully data-driven machine-learning approaches. The recent emergence of data-driven disease progression models provides a balance between imposed knowledge of disease features and patterns learned from data. The resulting models are both predictive of disease progression in individual patients and informative in terms of revealing underlying biological patterns. RECENT FINDINGS Largely inspired by observational models, data-driven disease progression models have emerged in the last few years as a feasible means for understanding the development of neurodegenerative diseases. These models have revealed insights into frontotemporal dementia, Huntington's disease, multiple sclerosis, Parkinson's disease and other conditions. For example, event-based models have revealed finer graded understanding of progression patterns; self-modelling regression and differential equation models have provided data-driven biomarker trajectories; spatiotemporal models have shown that brain shape changes, for example of the hippocampus, can occur before detectable neurodegeneration; and network models have provided some support for prion-like mechanistic hypotheses of disease propagation. The most mature results are in sporadic Alzheimer's disease, in large part because of the availability of the Alzheimer's disease neuroimaging initiative dataset. Results generally support the prevailing amyloid-led hypothetical model of Alzheimer's disease, while revealing finer detail and insight into disease progression. SUMMARY The emerging field of disease progression modelling provides a natural mechanism to integrate different kinds of information, for example from imaging, serum and cerebrospinal fluid markers and cognitive tests, to obtain new insights into progressive diseases. Such insights include fine-grained longitudinal patterns of neurodegeneration, from early stages, and the heterogeneity of these trajectories over the population. More pragmatically, such models enable finer precision in patient staging and stratification, prediction of progression rates and earlier and better identification of at-risk individuals. We argue that this will make disease progression modelling invaluable for recruitment and end-points in future clinical trials, potentially ameliorating the high failure rate in trials of, e.g., Alzheimer's disease therapies. We review the state of the art in these techniques and discuss the future steps required to translate the ideas to front-line application.This is an open access article distributed under the terms of the Creative Commons Attribution-Non Commercial-No Derivatives License 4.0 (CCBY-NC-ND), where it is permissible to download and share the work provided it is properly cited. The work cannot be changed in any way or used commercially without permission from the journal. http://creativecommons.org/licenses/by-nc-nd/4.0.},
author = {Oxtoby, Neil P and Alexander, Daniel C},
doi = {10.1097/WCO.0000000000000460},
isbn = {0000000000000},
issn = {14736551},
journal = {Curr. Opin. Neurol.},
keywords = {Ageing,Alzheimer,computational,disease progression,generative,modelling,multiple sclerosis,neurodegeneration,neurological,prion,statistical},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {371--379},
pmid = {28520598},
title = {{Imaging plus X: Multimodal models of neurodegenerative disease}},
volume = {30},
year = {2017}
}
@article{Rathore2017,
abstract = {Neuroimaging has made it possible to measure pathological brain changes associated with Alzheimer's disease (AD) in vivo. Over the past decade, these measures have been increasingly integrated into imaging signatures of AD by means of classification frameworks, offering promising tools for individualized diagnosis and prognosis. We reviewed neuroimaging-based studies for AD and mild cognitive impairment classification, selected after online database searches in Google Scholar and PubMed (January, 1985–June, 2016). We categorized these studies based on the following neuroimaging modalities (and sub-categorized based on features extracted as a post-processing step from these modalities): i) structural magnetic resonance imaging [MRI] (tissue density, cortical surface, and hippocampal measurements), ii) functional MRI (functional coherence of different brain regions, and the strength of the functional connectivity), iii) diffusion tensor imaging (patterns along the white matter fibers), iv) fluorodeoxyglucose positron emission tomography (FDG-PET) (metabolic rate of cerebral glucose), and v) amyloid-PET (amyloid burden). The studies reviewed indicate that the classification frameworks formulated on the basis of these features show promise for individualized diagnosis and prediction of clinical progression. Finally, we provided a detailed account of AD classification challenges and addressed some future research directions.},
annote = {TO READ, incredibly interesting.},
author = {Rathore, Saima and Habes, Mohamad and Iftikhar, Muhammad Aksam and Shacklett, Amanda and Davatzikos, Christos},
journal = {Neuroimage},
doi = {10.1016/j.neuroimage.2017.03.057},
isbn = {1095-9572$\backslash$r1053-8119},
issn = {10959572},
keywords = {Alzheimer's disease,Classification,Feature extraction,Machine learning,Mild cognitive impairment,Neuroimaging},
mendeley-groups = {PhDThesis/Review},
pages = {530--548},
pmid = {28414186},
title = {{A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages}},
volume = {155},
year = {2017}
}
@article{Jack2009,
abstract = {The purpose of this study was to use serial imaging to gain insight into the sequence of pathologic events in Alzheimer's disease, and the clinical features associated with this sequence. We measured change in amyloid deposition over time using serial (11)C Pittsburgh compound B (PIB) positron emission tomography and progression of neurodegeneration using serial structural magnetic resonance imaging. We studied 21 healthy cognitively normal subjects, 32 with amnestic mild cognitive impairment and 8 with Alzheimer's disease. Subjects were drawn from two sources--ongoing longitudinal registries at Mayo Clinic, and the Alzheimer's disease Neuroimaging Initiative (ADNI). All subjects underwent clinical assessments, MRI and PIB studies at two time points, approximately one year apart. PIB retention was quantified in global cortical to cerebellar ratio units and brain atrophy in units of cm(3) by measuring ventricular expansion. The annual change in global PIB retention did not differ by clinical group (P = 0.90), and although small (median 0.042 ratio units/year overall) was greater than zero among all subjects (P {\{}{\textless}{\}} 0.001). Ventricular expansion rates differed by clinical group (P {\{}{\textless}{\}} 0.001) and increased in the following order: cognitively normal (1.3 cm(3)/year) {\{}{\textless}{\}} amnestic mild cognitive impairment (2.5 cm(3)/year) {\{}{\textless}{\}} Alzheimer's disease (7.7 cm(3)/year). Among all subjects there was no correlation between PIB change and concurrent change on CDR-SB (r = -0.01, P = 0.97) but some evidence of a weak correlation with MMSE (r =-0.22, P = 0.09). In contrast, greater rates of ventricular expansion were clearly correlated with worsening concurrent change on CDR-SB (r = 0.42, P {\{}{\textless}{\}} 0.01) and MMSE (r =-0.52, P {\{}{\textless}{\}} 0.01). Our data are consistent with a model of typical late onset Alzheimer's disease that has two main features: (i) dissociation between the rate of amyloid deposition and the rate of neurodegeneration late in life, with amyloid deposition proceeding at a constant slow rate while neurodegeneration accelerates and (ii) clinical symptoms are coupled to neurodegeneration not amyloid deposition. Significant plaque deposition occurs prior to clinical decline. The presence of brain amyloidosis alone is not sufficient to produce cognitive decline, rather, the neurodegenerative component of Alzheimer's disease pathology is the direct substrate of cognitive impairment and the rate of cognitive decline is driven by the rate of neurodegeneration. Neurodegeneration (atrophy on MRI) both precedes and parallels cognitive decline. This model implies a complimentary role for MRI and PIB imaging in Alzheimer's disease, with each reflecting one of the major pathologies, amyloid dysmetabolism and neurodegeneration.},
annote = {No explanation of follow-up subjects.

THIS IS STATISTICAL},
author = {Jack, Clifford R and Lowe, Val J and Weigand, Stephen D and Wiste, Heather J and Senjem, Matthew L and Knopman, David S and Shiung, Maria M and Gunter, Jeffrey L and Boeve, Bradley F and Kemp, Bradley J and Weiner, Michael and Petersen, Ronald C},
doi = {10.1093/brain/awp062},
isbn = {1460-2156 (Electronic) 0006-8950 (Linking)},
issn = {14602156},
journal = {Brain},
keywords = {Alzheimers disease,Amyloid imaging,Magnetic resonance imaging,Mild cognitive impairment,Pittsburgh compound B,longitudinal imaging},
mendeley-groups = {PhDThesis/Review},
number = {5},
pages = {1355--1365},
pmid = {19339253},
publisher = {Oxford University Press},
title = {{Serial PIB and MRI in normal, mild cognitive impairment and Alzheimers disease: Implications for sequence of pathological events in Alzheimers disease}},
volume = {132},
year = {2009}
}
@article{Jack2010,
abstract = {Currently available evidence strongly supports the position that the initiating event in Alzheimer's disease (AD) is related to abnormal processing of $\beta$-amyloid (A$\beta$) peptide, ultimately leading to formation of A$\beta$ plaques in the brain. This process occurs while individuals are still cognitively normal. Biomarkers of brain $\beta$-amyloidosis are reductions in CSF A$\beta$42and increased amyloid PET tracer retention. After a lag period, which varies from patient to patient, neuronal dysfunction and neurodegeneration become the dominant pathological processes. Biomarkers of neuronal injury and neurodegeneration are increased CSF tau and structural MRI measures of cerebral atrophy. Neurodegeneration is accompanied by synaptic dysfunction, which is indicated by decreased fluorodeoxyglucose uptake on PET. We propose a model that relates disease stage to AD biomarkers in which A$\beta$ biomarkers become abnormal first, before neurodegenerative biomarkers and cognitive symptoms, and neurodegenerative biomarkers become abnormal later, and correlate with clinical symptom severity. {\textcopyright}2010 Elsevier Ltd. All rights reserved.},
author = {Jack, Clifford R and Knopman, David S and Jagust, William J and Shaw, Leslie M and Aisen, Paul S and Weiner, Michael W and Petersen, Ronald C and Trojanowski, John Q},
doi = {10.1016/S1474-4422(09)70299-6},
isbn = {1474-4465 (Electronic)$\backslash$r1474-4422 (Linking)},
issn = {14744422},
journal = {Lancet Neurol.},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {119--128},
pmid = {20083042},
publisher = {NIH Public Access},
title = {{Hypothetical model of dynamic biomarkers of the Alzheimer's pathological cascade}},
volume = {9},
year = {2010}
}
@article{Ching2017,
abstract = {Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems{\{}$\backslash$textemdash{\}}patient classification, fundamental biological processes and treatment of patients{\{}$\backslash$textemdash{\}}and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network{\{}$\backslash$textquoteright{\}}s prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.},
author = {Ching, Travers and Do, Brian T and Himmelstein, Daniel S and Beaulieu-Jones, Brett K and Kalinin, Alexandr A and Way, Gregory P and Ferrero, Enrico and Agapow, Paul-Michael and Carpenter, Anne E and Zietz, Michael and Hoffman, Michael M and Xie, Wei and Rosen, Gail L and Lanchantin, Jack and Xu, Jinbo and Woloszynek, Stephen and Lu, Zhiyong and Harris, David J and Peng, Yifan and Wiley, Laura K and Do, Brian T and Way, Gregory P and Ferrero, Enrico and Agapow, Paul-Michael and Zietz, Michael and Hoffman, Michael M and Xie, Wei and Rosen, Gail L and Lengerich, Benjamin J and Israeli, Johnny and Lanchantin, Jack and Woloszynek, Stephen and Carpenter, Anne E and Shrikumar, Avanti and Xu, Jinbo and Cofer, Evan M and Lavender, Christopher A and Turaga, Srinivas C and Alexandari, Amr M and Lu, Zhiyong and Harris, David J and DeCaprio, Dave and Qi, Yanjun and Kundaje, Anshul and Peng, Yifan and Wiley, Laura K and Segler, Marwin H S and Boca, Simina M and Swamidass, S Joshua and Huang, Austin and Gitter, Anthony and Greene, Casey S},
doi = {https://doi.org/10.1101/142760},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Ching et al. - 2018 - Opportunities and obstacles for deep learning in biology and medicine.pdf:pdf},
issn = {1742-5689},
journal = {J. R. Soc. Interface},
keywords = {deep learning,genomic,precision medicine,review},
mendeley-groups = {PHD/Reviews,PhDThesis/Review},
number = {141},
pages = {.},
publisher = {The Royal Society},
title = {{Opportunities and obstacles for deep learning in biology and medicine}},
volume = {15},
year = {2018}
}
@article{Schmidt1992,
author = {Schmidt, Reinhold},
journal = {Eur Neurol},
mendeley-groups = {PhDThesis/Review},
pages = {164--169},
title = {{Comparison of Magnetic Resonance Imaging in Alzheimer's Disease, Vascular Dementia and Normal Aging}},
volume = {32},
year = {1992}
}
@article{Bhat2015,
abstract = {Alzheimer's disease (AD) is a progressive disorder affecting intellectual, behavioral and functional abilities. It is associated with age and pathological alterations leading to the formation of amyloid plaques and tangles. It is the most common source of dementia in the older population, which varies in its degrees of severity. We are yet to find efficient methods of diagnosis of AD, as its symptoms vary among individuals. This paper presents a review of recent research on the clinical neurophysiological and automated electroencephalography-based diagnosis of the AD. Various therapeutic measures are also discussed briefly.},
author = {Bhat, Shreya and {Rajendra Acharya}, U and Dadmehr, Nahid and Adeli, Hojjat},
doi = {10.1159/000441447},
issn = {14219913},
journal = {Eur. Neurol.},
keywords = {Alzheimer's,Aphasia,Apraxia,Donepezil,Neurodegeneration,Plaques,Tangles},
mendeley-groups = {PhDThesis/Review},
number = {3-4},
pages = {202--210},
title = {{Clinical neurophysiological and automated EEG-based diagnosis of the Alzheimer's disease}},
volume = {74},
year = {2015}
}
@article{Acharya2019,
abstract = {The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer's disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student's t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer's diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54{\%}, precision of 88.33{\%}, sensitivity of 96.30{\%} and specificity of 93.64{\%}. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48{\%}, 100{\%}, 96.97{\%} and 100{\%}, respectively, with the benchmark MRI database.},
author = {Acharya, U Rajendra and Fernandes, Steven Lawrence and WeiKoh, Joel En and Ciaccio, Edward J and Fabell, Mohd Kamil Mohd and Tanik, U John and Rajinikanth, V and Yeong, Chai Hong},
doi = {10.1007/s10916-019-1428-9},
issn = {1573689X},
journal = {J. Med. Syst.},
keywords = {Alzheimer's disease,Brain MRI,Feature extraction,KNN classifier,Performance evaluation},
mendeley-groups = {PhDThesis/Review},
number = {9},
publisher = {Springer New York LLC},
title = {{Automated Detection of Alzheimer's Disease Using Brain MRI Images– A Study with Various Feature Extraction Techniques}},
volume = {43},
year = {2019}
}
@article{Bhagwat2018,
abstract = {Computational models predicting symptomatic progression at the individual level can be highly beneficial for early intervention and treatment planning for Alzheimer's disease (AD). Individual prognosis is complicated by many factors including the definition of the prediction objective itself. In this work, we present a computational framework comprising machine-learning techniques for 1) modeling symptom trajectories and 2) prediction of symptom trajectories using multimodal and longitudinal data. We perform primary analyses on three cohorts from Alzheimer's Disease Neuroimaging Initiative (ADNI), and a replication analysis using subjects from Australian Imaging, Biomarker {\&} Lifestyle Flagship Study of Ageing (AIBL). We model the prototypical symptom trajectory classes using clinical assessment scores from mini-mental state exam (MMSE) and Alzheimer's Disease Assessment Scale (ADAS-13) at nine timepoints spanned over six years based on a hierarchical clustering approach. Subsequently we predict these trajectory classes for a given subject using magnetic resonance (MR) imaging, genetic, and clinical variables from two timepoints (baseline + follow-up). For prediction, we present a longitudinal Siamese neural-network (LSN) with novel architectural modules for combining multimodal data from two timepoints. The trajectory modeling yields two (stable and decline) and three (stable, slow-decline, fast-decline) trajectory classes for MMSE and ADAS-13 assessments, respectively. For the predictive tasks, LSN offers highly accurate performance with 0.900 accuracy and 0.968 AUC for binary MMSE task and 0.760 accuracy for 3-way ADAS-13 task on ADNI datasets, as well as, 0.724 accuracy and 0.883 AUC for binary MMSE task on replication AIBL dataset.},
author = {Bhagwat, Nikhil and Viviano, Joseph D and Voineskos, Aristotle N and Chakravarty, M Mallar},
doi = {10.1371/journal.pcbi.1006376},
editor = {Jbabdi, Saad},
issn = {15537358},
journal = {PLoS Comput. Biol.},
mendeley-groups = {PhDThesis/Review},
number = {9},
pages = {e1006376},
publisher = {Public Library of Science},
title = {{Modeling and prediction of clinical symptom trajectories in Alzheimer's disease using longitudinal data}},
volume = {14},
year = {2018}
}
@article{Houmani2018,
abstract = {This study addresses the problem of Alzheimer's disease (AD) diagnosis with Electroencephalography (EEG). The use of EEG as a tool for AD diagnosis has been widely studied by comparing EEG signals of AD patients only to those of healthy subjects. By contrast, we perform automated EEG diagnosis in a differential diagnosis context using a new database, acquired in clinical conditions, which contains EEG data of 169 patients: subjective cognitive impairment (SCI) patients, mild cognitive impairment (MCI) patients, possible Alzheimer's disease (AD) patients, and patients with other pathologies. We show that two EEG features, namely epoch-based entropy (a measure of signal complexity) and bump modeling (a measure of synchrony) are sufficient for efficient discrimination between these groups. We studied the performance of our methodology for the automatic discrimination of possible AD patients from SCI patients and from patients with MCI or other pathologies. A classification accuracy of 91.6{\%} (specificity = 100{\%}, sensitivity = 87.8{\%}) was obtained when discriminating SCI patients from possible AD patients and 81.8{\%} to 88.8{\%} accuracy was obtained for the 3-class classification of SCI, possible AD and other patients.},
author = {Houmani, Nesma and Vialatte, Fran{\c{c}}ois and Gallego-Jutgl{\`{a}}, Esteve and Dreyfus, G{\'{e}}rard and Nguyen-Michel, Vi Huong and Mariani, Jean and Kinugawa, Kiyoka},
doi = {10.1371/journal.pone.0193607},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {3},
publisher = {Public Library of Science},
title = {{Diagnosis of Alzheimer's disease with electroencephalography in a differential framework}},
volume = {13},
year = {2018}
}
@article{Aksman2016,
abstract = {Longitudinal designs are widely used in medical studies as a means of observing within-subject changes over time in groups of subjects, thereby aiming to improve sensitivity for detecting disease effects. Paralleling an increased use of such studies in neuroimaging has been the adoption of pattern recognition algorithms for making individualized predictions of disease. However, at present few pattern recognition methods exist to make full use of neuroimaging data that have been collected longitudinally, with most methods relying instead on cross-sectional style analysis. This article presents a principal component analysis-based feature construction method that uses longitudinal high-dimensional data to improve predictive performance of pattern recognition algorithms. The method can be applied to data from a wide range of longitudinal study designs and permits an arbitrary number of time-points per subject. We apply the method to two longitudinal datasets, one containing subjects with mild cognitive impairment along with healthy controls, the other with early dementia subjects and healthy controls. Across both datasets, we show improvements in predictive accuracy relative to cross-sectional classifiers for discriminating disease subjects from healthy controls on the basis of whole-brain structural magnetic resonance image-based voxels. In addition, we can transfer longitudinal information from one set of subjects to make disease predictions in another set of subjects. The proposed method is simple and, as a feature construction method, flexible with respect to the choice of classifier and image registration algorithm. Hum Brain Mapp 37:4385-4404, 2016. (c) 2016 Wiley Periodicals, Inc.},
author = {Aksman, Leon M and Lythgoe, David J and Williams, Steven C R and Jokisch, Martha and Monninghoff, Christoph and Streffer, Johannes and Jockel, Karl-Heinz and Weimar, Christian and Marquand, Andre F},
doi = {10.1002/hbm.23317},
issn = {1097-0193 (Electronic)},
journal = {Hum. Brain Mapp.},
keywords = { 80 and over, Automated, Computer-Assisted,Aged,Brain,Cognitive Dysfunction,Cross-Sectional Studies,Dementia,Follow-Up Studies,Humans,Image Interpretation,Linear Models,Longitudinal Studies,Magnetic Resonance Imaging,Middle Aged,Neuroimaging,Pattern Recognition,Principal Component Analysis,Prospective Studies,Sensitivity and Specificity,Support Vector Machine,diagnostic imaging,methods},
mendeley-groups = {PhDThesis/Review},
number = {12},
pages = {4385--4404},
pmid = {27451934},
title = {{Making use of longitudinal information in pattern recognition.}},
volume = {37},
year = {2016}
}
@article{Al-Hameed2017,
abstract = {This study investigates the deteriorating speech signal of people suffering from Alzheimer's disease (AD). The aim is to firstly predict a common clinical examination score used for dementia (MMSE) using acoustic information extracted from people describing a picture – a common dementia assessment task. Secondly, we aim to develop a diagnostic tool able to distinguish people with AD from people with Mild Cognitive Impairment (MCI) and healthy control (HC). This is done on a longitudinal dataset (DementiaBank) allowing us to study the natural deterioration happening across a total of three visits. We extracted 811 acoustic features and build two machine learning models: a regression model capable of predicting MMSE scores for each visit with an average mean absolute error of 3.1, and a classification model with an average cross-visit accuracy ranging between 89.2{\%} and 92.4{\%} when doing pairwise classification between the AD, MCI and HC classes.},
author = {Al-Hameed, Sabah and Benaissa, Mohammed and Christensen, Heidi},
doi = {10.1145/3175587.3175589},
isbn = {9781450353823},
journal = {Proc. Int. Conf. Bioinforma. Res. Appl. 2017 - ICBRA 2017},
keywords = {alzheimer,classification,feature extraction,mmse and,s disease},
mendeley-groups = {PhDThesis/Review},
pages = {57--61},
title = {{Detecting and Predicting Alzheimer's Disease Severity in Longitudinal Acoustic Data}},
year = {2017}
}
@article{AraqueCaballero2017,
abstract = {A substantial proportion of cognitively healthy elders (HC) show abnormally high amyloid-beta (Abeta) deposition, a major pathology of Alzheimer's disease (AD). These subjects are at increased risk of Alzheimer's disease (AD) dementia, and biomarkers are needed to predict their cognitive deterioration. Here we used relevance vector regression (RVR), a pattern-recognition method, to predict concurrent cognitive decline on the basis of longitudinal gray matter (GM) changes, within two a priori, meta-analytically defined functional networks subserving episodic memory and executive function. Ninety-six HC subjects were assessed annually for three years with structural MRI and cognitive tests within the Alzheimer's Disease Neuroimaging Initiative. Presence of abnormal biomarker values of Abeta (Abeta+) were determined with cerebrospinal fluid and amyloid-PET (HC-Abeta+, n=30; with n=66 for normal HC-Abeta-). Using leave-one-out cross-validation, we found that in HC-Abeta+ patterns of GM changes within both networks predicted decline in episodic memory (r=0.61, p{\textless}0.001; r=0.40, p=0.03), but not executive function. In HC-Abeta-, GM changes within the executive function network predicted decline in executive function (r=0.44, p{\textless}0.001). Previously established region-of-interest (ROI)-based predictors such as changes in hippocampal volume, within an AD-signature multi-ROI, or total GM volume were not predictive of cognitive decline in any group or cognitive domain. RVR analyses unrestricted to the a priori networks yielded compatible results with the restricted case. In conclusion, RVR-derived patterns of subtle cortical GM changes are biomarker candidates of concurrent cognitive decline in aging and subjects at risk for AD.},
author = {{Araque Caballero}, Miguel Angel and Kloppel, Stefan and Dichgans, Martin and Ewers, Michael},
doi = {10.3233/JAD-160327},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = { Episodic, Three-Dimensional,Aged,Amyloid beta-Peptides,Apolipoproteins E,Atrophy,Biomarkers,Brain,Cognitive Dysfunction,Executive Function,Female,Follow-Up Studies,Gray Matter,Humans,Imaging,Longitudinal Studies,Magnetic Resonance Imaging,Male,Memory,Neural Pathways,Positron-Emission Tomography,Prognosis,Regression Analysis,cerebrospinal fluid,diagnostic imaging,genetics,metabolism},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {343--358},
pmid = {27662291},
title = {{Spatial Patterns of Longitudinal Gray Matter Change as Predictors of Concurrent Cognitive Decline in Amyloid Positive Healthy Subjects.}},
volume = {55},
year = {2017}
}
@article{Arco2016,
abstract = {{\textcopyright}Springer International Publishing Switzerland 2016. Nowadays, 35million peopleworldwide suffer fromsome formof dementia. Given the increase in life expectancy it is estimated that in 2035 this number will grow to 115 million. Alzheimer's disease is the most common cause of dementia and it is of great importance diagnose it at an early stage. This is the main goal of this work, the development of a new automatic method to predict the mild cognitive impairment (MCI) patients who will develop Alzheimer's disease within one year or, conversely, its impairment will remain stable. This technique will analyze data from both magnetic resonance imaging and neuropsychological tests by utilizing a t-test for feature selection, maximum-uncertainty linear discriminant analysis (MLDA) for classification and leave-one-out cross validation (LOOCV) for evaluating the performance of the methods, which achieved a classification accuracy of 73.95 {\%}, with a sensitivity of 72.14{\%} and a specificity of 73.77 {\%}.},
annote = {basura paper},
author = {Arco, J E and Ram{\'{i}}rez, J and G{\'{o}}rriz, J M and Puntonet, C G and Ruz, M},
doi = {10.1007/978-3-319-23024-5_35},
isbn = {9783319230238},
issn = {21903026},
journal = {Smart Innov. Syst. Technol.},
mendeley-groups = {PhDThesis/Review},
pages = {385--394},
title = {{Short-term prediction of MCI to AD conversion based on longitudinal MRI analysis and neuropsychological tests}},
volume = {45},
year = {2016}
}
@article{Ardekani2016,
abstract = {BACKGROUND Mild cognitive impairment (MCI) is a transitional stage from normal aging to Alzheimer's disease (AD) dementia. It is extremely important to develop criteria that can be used to separate the MCI subjects at imminent risk of conversion to Alzheimer-type dementia from those who would remain stable. We have developed an automatic algorithm for computing a novel measure of hippocampal volumetric integrity (HVI) from structural MRI scans that may be useful for this purpose. OBJECTIVE To determine the utility of HVI in classification between stable and progressive MCI patients using the Random Forest classification algorithm. METHODS We used a 16-dimensional feature space including bilateral HVI obtained from baseline and one-year follow-up structural MRI, cognitive tests, and genetic and demographic information to train a Random Forest classifier in a sample of 164 MCI subjects categorized into two groups [progressive (n = 86) or stable (n = 78)] based on future conversion (or lack thereof) of their diagnosis to probable AD. RESULTS The overall accuracy of classification was estimated to be 82.3{\%} (86.0{\%} sensitivity, 78.2{\%} specificity). The accuracy in women (89.1{\%}) was considerably higher than that in men (78.9{\%}). The prediction accuracy achieved in women is the highest reported in any previous application of machine learning to AD diagnosis in MCI. CONCLUSION The method presented in this paper can be used to separate stable MCI patients from those who are at early stages of AD dementia with high accuracy. There may be stronger indicators of imminent AD dementia in women with MCI as compared to men.},
annote = {Tot lo interessant est{\`{a}} al abstract},
author = {Ardekani, Babak A and Bermudez, Elaine and Mubeen, Asim M and Bachman, Alvin H},
doi = {10.3233/JAD-160594},
isbn = {1875-8908 (Electronic) 1387-2877 (Linking)},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {Alzheimer's disease,Random Forest,atrophy,hippocampus,longitudinal analysis,magnetic resonance imaging,mild cognitive impairment,prediction,sex},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {269--281},
pmid = {27662309},
title = {{Prediction of incipient Alzheimer's disease dementia in patients with mild cognitive impairment}},
volume = {55},
year = {2016}
}
@article{Ashford2001,
abstract = {Alzheimer's disease (AD) progresses from a preclinical period, through a middle phase of cognitive deterioration, to a late, profound state. The temporal progression of disability can be modeled with a horologic (time-based) function using "time-index" (TI) intervals (day- or year-units) to quantify an individual's disability across multiple cognitive and functional domains relative to a reference AD population. Clinicians and researchers can use TI quantification to assess dementia severity and initial therapy benefits. Rate of progression and confidence intervals require at least two successive measurements. Rate of progression measures can be used to support diagnosis and to investigate disease-course-modifying therapies.},
author = {Ashford, J.Wesson Wesson and Schmitt, FrederickA. A},
doi = {10.1007/s11920-001-0067-1},
isbn = {1523-3812 (Print)},
issn = {1523-3812},
journal = {Curr. Psychiatry Rep.},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {20--28},
pmid = {11177755},
title = {{Modeling the time-course of Alzheimer dementia.}},
volume = {3},
year = {2001}
}
@article{Backman2004,
abstract = {The literature on cognitive markers in preclinical AD is reviewed. The findings demonstrate that impairment in multiple cognitive domains is typically observed several years before clinical diagnosis. Measures of executive functioning, episodic memory and perceptual speed appear to be most effective at identifying at-risk individuals. The fact that these cognitive domains are most implicated in normal cognitive aging suggests that the cognitive deficit observed preclinically is not qualitatively different from that observed in normal aging. The degree of cognitive impairment prior to the diagnosis of Alzheimer's disease (AD) appears to generalize relatively well across major study characteristics, including sample ascertainment procedures, age and cognitive status of participants, as well as time to diagnosis of dementia. In episodic memory, there is evidence that the size of the preclinical deficit increases with increasing cognitive demands. The global cognitive impairment observed is highly consistent with observations that multiple brain structures and functions are affected long before the diagnosis of AD. However, there is substantial overlap in the distribution of cognitive scores between those who will and those who will not be diagnosed with AD, hence limiting the clinical utility of cognitive markers for early identification of cases. Future research should consider combining cognitive indicators with other types of markers (i.e. social, somatic, genetic, brain-based) in order to increase prediction accuracy.},
author = {B{\"{a}}ckman, L and Jones, S and Berger, A K and Laukka, E J and Small, B J},
doi = {10.1111/j.1365-2796.2004.01386.x},
isbn = {0954-6820 (Print)},
issn = {09546820},
journal = {J. Intern. Med.},
keywords = {Alzheimer's disease,Cognition,Markers,Memory,Preclinical,Transition},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {195--204},
pmid = {15324363},
title = {{Multiple cognitive deficits during the transition to Alzheimer's disease}},
volume = {256},
year = {2004}
}
@article{Ballard2011,
abstract = {An estimated 24 million people worldwide have dementia, the majority of whom are thought to have Alzheimer's disease. Thus, Alzheimer's disease represents a major public health concern and has been identified as a research priority. Although there are licensed treatments that can alleviate symptoms of Alzheimer's disease, there is a pressing need to improve our understanding of pathogenesis to enable development of disease-modifying treatments. Methods for improving diagnosis are also moving forward, but a better consensus is needed for development of a panel of biological and neuroimaging biomarkers that support clinical diagnosis. There is now strong evidence of potential risk and protective factors for Alzheimer's disease, dementia, and cognitive decline, but further work is needed to understand these better and to establish whether interventions can substantially lower these risks. In this Seminar, we provide an overview of recent evidence regarding the epidemiology, pathogenesis, diagnosis, and treatment of Alzheimer's disease, and discuss potential ways to reduce the risk of developing the disease. {\textcopyright}2011 Elsevier Ltd.},
author = {Ballard, Clive and Gauthier, Serge and Corbett, Anne and Brayne, Carol and Aarsland, Dag and Jones, Emma},
doi = {10.1016/S0140-6736(10)61349-9},
isbn = {0140-6736},
issn = {01406736},
journal = {Lancet},
mendeley-groups = {PhDThesis/Review},
number = {9770},
pages = {1019--1031},
pmid = {21371747},
publisher = {Elsevier Ltd},
title = {{Alzheimer's disease}},
volume = {377},
year = {2011}
}
@article{Bateman2012,
abstract = {BACKGROUND: The order and magnitude of pathologic processes in Alzheimer's disease are not well understood, partly because the disease develops over many years. Autosomal dominant Alzheimer's disease has a predictable age at onset and provides an opportunity to determine the sequence and magnitude of pathologic changes that culminate in symptomatic disease. METHODS: In this prospective, longitudinal study, we analyzed data from 128 participants who underwent baseline clinical and cognitive assessments, brain imaging, and cerebrospinal fluid (CSF) and blood tests. We used the participant's age at baseline assessment and the parent's age at the onset of symptoms of Alzheimer's disease to calculate the estimated years from expected symptom onset (age of the participant minus parent's age at symptom onset). We conducted cross-sectional analyses of baseline data in relation to estimated years from expected symptom onset in order to determine the relative order and magnitude of pathophysiological changes. RESULTS: Concentrations of amyloid-beta (A$\beta$)(42) in the CSF appeared to decline 25 years before expected symptom onset. A$\beta$ deposition, as measured by positron-emission tomography with the use of Pittsburgh compound B, was detected 15 years before expected symptom onset. Increased concentrations of tau protein in the CSF and an increase in brain atrophy were detected 15 years before expected symptom onset. Cerebral hypometabolism and impaired episodic memory were observed 10 years before expected symptom onset. Global cognitive impairment, as measured by the Mini-Mental State Examination and the Clinical Dementia Rating scale, was detected 5 years before expected symptom onset, and patients met diagnostic criteria for dementia at an average of 3 years after expected symptom onset. CONCLUSIONS: We found that autosomal dominant Alzheimer's disease was associated with a series of pathophysiological changes over decades in CSF biochemical markers of Alzheimer's disease, brain amyloid deposition, and brain metabolism as well as progressive cognitive impairment. Our results require confirmation with the use of longitudinal data and may not apply to patients with sporadic Alzheimer's disease. (Funded by the National Institute on Aging and others; DIAN ClinicalTrials.gov number, NCT00869817.).},
annote = {Work that can serve as an example of a work},
author = {Bateman, Randall J and Xiong, Chengjie and Benzinger, Tammie L S and Fagan, Anne M and Goate, Alison and Fox, Nick C and Marcus, Daniel S and Cairns, Nigel J and Xie, Xianyun and Blazey, Tyler M and Holtzman, David M and Santacruz, Anna and Buckles, Virginia and Oliver, Angela and Moulder, Krista and Aisen, Paul S and Ghetti, Bernardino and Klunk, William E and McDade, Eric and Martins, Ralph N and Masters, Colin L and Mayeux, Richard and Ringman, John M and Rossor, Martin N and Schofield, Peter R and Sperling, Reisa A and Salloway, Stephen and Morris, John C},
doi = {10.1056/NEJMoa1202753},
isbn = {1533-4406 (Electronic)$\backslash$r0028-4793 (Linking)},
issn = {0028-4793},
journal = {N. Engl. J. Med.},
mendeley-groups = {PhDThesis/Review},
number = {9},
pages = {795--804},
pmid = {22784036},
publisher = {Massachusetts Medical Society},
title = {{Clinical and Biomarker Changes in Dominantly Inherited Alzheimer's Disease}},
volume = {367},
year = {2012}
}

@inproceedings{Bellare2005,
abstract = {We describe an RSA-based signing scheme which combines essentially optimal efficiency with attractive security properties. Signing takes one RSA decryption plus some hashing, verification takes one RSA encryption plus some hashing, and the size of the signature is ... {\$}\backslash{\$}n},
archivePrefix = {arXiv},
arxivId = {9780201398298},
author = {Bellare, Mihir and Rogaway, Phillip},
doi = {10.1007/b137723},
eprint = {9780201398298},
isbn = {978-3-540-26545-0},
issn = {0302-9743},
journal = {Lect. Notes Comput. Sci. 3565 - 19th Int. Conf.},
keywords = {adni,alzheimer,as such,cortical thickness,data used in preparation,database,disease progression model,edu,loni,measures,neuroimaging initiative,obtained from the alzheimer,of this article were,posterior cortical atrophy,s disease,the inves-,usc,vertex-wise},
mendeley-groups = {PhDThesis/Review},
pages = {399--416},
pmid = {4520227},
publisher = {Springer, Cham},
title = {{Information Processing in Medical Imaging}},
volume = {3565},
year = {2005}
}

@article{Bertsch2015,
abstract = {In this paper we propose a mathematical model for the onset and progression of Alzheimer's disease based on transport and diffusion equations. We regard brain neurons as a continuous medium, and structure them by their degree of malfunctioning. Two different mechanisms are assumed to be relevant for the temporal evolution of the disease: i) diffusion and agglomeration of soluble polymers of amyloid, produced by damaged neurons; ii) neuron-to-neuron prion-like transmission. We model these two processes by a system of Smoluchowski equations for the amyloid concentration, coupled to a kinetic-type transport equation for the distribution function of the degree of malfunctioning of neurons. The second equation contains an integral term describing the random onset of the disease as a jump process localised in particularly sensitive areas of the brain. Our numerical simulations are in good qualitative agreement with clinical images of the disease distribution in the brain which vary from early to advanced stages.},
annote = {REMOVED BECAUSE USES NO LONG. DATA (IS A MODEL)

However, could be interesting to read},
archivePrefix = {arXiv},
arxivId = {1503.04669},
author = {Bertsch, Michiel and Franchi, Bruno and Marcello, Norina and Tesi, Maria Carla and Tosin, Andrea},
doi = {10.1093/imammb/dqw003},
eprint = {1503.04669},
isbn = {1477-8602 (Electronic)$\backslash$r1477-8599 (Linking)},
issn = {14778602},
journal = {Math. Med. Biol.},
keywords = {Alzheimer's disease,Numerical simulations,Smoluchowski equations,Transport and diffusion equations},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {2},
pages = {193--214},
pmid = {27079222},
title = {{Alzheimer's disease: A mathematical model for onset and progression}},
volume = {34},
year = {2017}
}
@article{Bilgel2014,
abstract = {AbstractBackground The delineation of the relative temporal trajectories of specific cognitive measures associated with Alzheimer's disease (AD) is important for evaluating preclinical markers and monitoring disease progression. Methods We characterized the temporal trajectories of measures of verbal episodic memory, short-term visual memory, and mental status using data from 895 participants in the Baltimore Longitudinal Study of Aging. Results The California Verbal Learning Test (CVLT) immediate recall was the first measure to decline, followed by CVLT delayed recall. However, further along the disease progression scale, CVLT delayed recall and visual memory changed more rapidly than CVLT immediate recall. Conclusions Our findings reconcile reports of early changes in immediate recall with greater reliance on delayed recall performance in clinical settings. Moreover, the utility of cognitive markers in evaluating AD progression depends on the stage of cognitive decline, suggesting that optimal endpoints in therapeutic trials may vary across different stages of the disease process.},
author = {Bilgel, Murat and An, Yang and Lang, Andrew and Prince, Jerry and Ferrucci, Luigi and Jedynak, Bruno and Resnick, Susan M},
doi = {https://doi.org/10.1016/j.jalz.2014.04.520},
issn = {1552-5260},
journal = {Alzheimer's Dement.},
keywords = {Alzheimer's disease,California verbal learning test,Disease progression score,Memory},
mendeley-groups = {PhDThesis/Review},
month = {nov},
number = {6},
pages = {735----742.e4},
title = {{Trajectories of Alzheimer disease-related cognitive measures in a longitudinal sample}},
volume = {10},
year = {2014}
}
@article{Bilgel2018,
abstract = {Introduction: Characterization of longitudinal trajectories of biomarkers implicated in sporadic Alzheimer's disease (AD) in decades before clinical diagnosis is important for disease prevention and monitoring. Methods: We used a multivariate Bayesian model to temporally align 1369 Alzheimer's disease Neuroimaging Initiative participants based on the similarity of their longitudinal biomarker measures and estimated a quantitative template of the temporal evolution of cerebrospinal fluid A$\beta$ 1−42 , p-tau 181p , and t-tau and hippocampal volume, brain glucose metabolism, and cognitive measurements. We computed biomarker trajectories as a function of time to AD dementia and predicted AD dementia onset age in a disjoint sample. Results: Quantitative template showed early changes in verbal memory, cerebrospinal fluid A$\beta$ 1–42 and p-tau 181p , and hippocampal volume. Mean error in predicted AD dementia onset age was {\textless}1.5 years. Discussion: Our method provides a quantitative approach for characterizing the natural history of AD starting at preclinical stages despite the lack of individual-level longitudinal data spanning the entire disease timeline.},
author = {Bilgel, Murat and Jedynak, Bruno M},
doi = {10.1016/j.dadm.2019.01.005},
issn = {23528729},
journal = {Alzheimer's Dement. Diagnosis, Assess. Dis. Monit.},
keywords = {Alzheimer,Biomarkers,Cognition,Dementia,Kaplan-Meier,Longitudinal,Onset,Prediction,Quantitative template},
mendeley-groups = {PhDThesis/Review},
month = {nov},
pages = {205--215},
publisher = {Cold Spring Harbor Laboratory},
title = {{Predicting time to dementia using a quantitative template of disease progression}},
volume = {11},
year = {2019}
}
@inproceedings{Bilgel2015a,
abstract = {Abstract. Cortical $\beta$-amyloid deposition begins in Alzheimer's disease (AD) years before the onset of any clinical symptoms. It is therefore important to determine the temporal trajectories of amyloid deposition in these earliest stages in order to better understand their associations with progression to AD. A method for estimating the temporal trajectories of voxelwise amyloid as measured using longitudinal positron emission tomography (PET) imaging is presented. The method involves the estimation of a score for each subject visit based on the PET data that reflects their amyloid progression. This amyloid progression score allows subjects with similar progressions to be aligned and analyzed together. The estimation of the progression scores and the amyloid trajectory parameters are performed using an expectation-maximization algorithm. The correlations among the voxel measures of amyloid are modeled to reflect the spatial nature of PET images. Simulation results show that model parameters are captured well at a variety of noise and spatial correlation levels. The method is applied to longitudinal amyloid imaging data considering each cerebral hemisphere separately. The results are consistent across the hemispheres and agree with a global index of brain amyloid known as mean cortical DVR. Unlike mean cortical DVR, which depends on a priori defined regions, the progression score extracted by the method is data-driven and does not make assumptions about regional longitudinal changes. Compared to regressing on age at each voxel, the longitudinal trajectory slopes estimated using the proposed method show better localized longitudinal changes.},
annote = {From Duplicate 4 (Temporal trajectory and progression score estimation from voxelwise longitudinal imaging measures: Application to amyloid imaging - Bilgel, Murat; Jedynak, Bruno; Wong, Dean F; Resnick, Susan M; Prince, Jerry L)

Results are a model of longitudinal changes.},
author = {Bilgel, Murat and Jedynak, Bruno and Wong, Dean F and Resnick, Susan M and Prince, Jerry L},
booktitle = {Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-19992-4_33},
isbn = {3-540-54246-9},
issn = {16113349},
keywords = {Algorithms,Amyloid,Amyloid beta-Peptides,Aniline Compounds,Biomarkers,Cerebral Cortex,Computer-Assisted,Disease Progression,Humans,Image Enhancement,Image Interpretation,Imaging,Longitudinal Studies,Longitudinal image analysis,Molecular Imaging,PiB,Pittsburgh compound B,Positron-Emission Tomography,Progression score,Radiopharmaceuticals,Reproducibility of Results,Sensitivity and Specificity,Spatio-Temporal Analysis,Thiazoles,Three-Dimensional,Tissue Distribution,diagnostic imaging,metabolism,methods,pharmacokinetics},
mendeley-groups = {PhDThesis/Review},
pages = {424--436},
pmid = {26221692},
publisher = {NIH Public Access},
title = {{Temporal trajectory and progression score estimation from voxelwise longitudinal imaging measures: Application to amyloid imaging}},
volume = {9123},
year = {2015}
}
@article{Bilgel2017,
abstract = {Investigation of the temporal trajectories of currently used neuropsychological tests is critical to identifying earliest changing measures on the path to dementia due to Alzheimer's disease (AD). We used the Progression Score (PS) method to characterize the temporal trajectories of measures of verbal memory, executive function, attention, processing speed, language, and mental state using data spanning normal cognition, mild cognitive impairment (MCI), and AD from 1661 participants with a total of 7839 visits (age at last visit 77.6 SD 9.2) in the Baltimore Longitudinal Study of Aging and 1542 participants with a total of 4467 visits (age at last visit 59.9 SD 7.3) in the Wisconsin Registry for Alzheimer's Prevention. This method aligns individuals in time based on the similarity of their longitudinal measurements to reveal temporal trajectories. As a validation of our methodology, we explored the associations between the individualized cognitive progression scores (Cog‑PS) computed by our method and clinical diagnosis. Digit span tests were the first to show declines in both data sets, and were detected mainly among cognitively normal individuals. These were followed by tests of verbal memory, which were in turn followed by Trail Making Tests, Boston Naming Test, and Mini-Mental State Examination. Differences in Cog-PS across the clinical diagnosis groups were statistically significant, highlighting the potential use of Cog-PS as individualized indicators of disease progression. Identifying cognitive measures that are changing in preclinical AD can lead to the development of novel cognitive tests that are finely tuned to detecting earliest changes.},
archivePrefix = {arXiv},
arxivId = {15334406},
author = {Bilgel, Murat and Koscik, Rebecca L and An, Yang and Prince, Jerry L and Resnick, Susan M and Johnson, Sterling C and Jedynak, Bruno M},
doi = {10.3233/JAD-170448},
eprint = {15334406},
isbn = {6462654600},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {Alzheimer's disease,cognition,longitudinal studies,neuropsychological tests,preclinical},
mendeley-groups = {PhDThesis/Review},
month = {oct},
number = {4},
pages = {1335--1347},
pmid = {28731452},
publisher = {Cold Spring Harbor Laboratory},
title = {{Temporal order of Alzheimer's disease-related cognitive marker changes in BLSA and WRAP longitudinal studies}},
volume = {59},
year = {2017}
}
@article{Bilgel2016,
abstract = {It is important to characterize the temporal trajectories of disease-related biomarkers in order to monitor progression and identify potential points of intervention. These are especially important for neurodegenerative diseases, as therapeutic intervention is most likely to be effective in the preclinical disease stages prior to significant neuronal damage. Neuroimaging allows for the measurement of structural, functional, and metabolic integrity of the brain at the level of voxels, whose volumes are on the order of mm(3). These voxelwise measurements provide a rich collection of disease indicators. Longitudinal neuroimaging studies enable the analysis of changes in these voxelwise measures. However, commonly used longitudinal analysis approaches, such as linear mixed effects models, do not account for the fact that individuals enter a study at various disease stages and progress at different rates, and generally consider each voxelwise measure independently. We propose a multivariate nonlinear mixed effects model for estimating the trajectories of voxelwise neuroimaging biomarkers from longitudinal data that accounts for such differences across individuals. The method involves the prediction of a progression score for each visit based on a collective analysis of voxelwise biomarker data within an expectation-maximization framework that efficiently handles large amounts of measurements and variable number of visits per individual, and accounts for spatial correlations among voxels. This score allows individuals with similar progressions to be aligned and analyzed together, which enables the construction of a trajectory of brain changes as a function of an underlying progression or disease stage. We apply our method to studying cortical beta-amyloid deposition, a hallmark of preclinical Alzheimer's disease, as measured using positron emission tomography. Results on 104 individuals with a total of 300 visits suggest that precuneus is the earliest cortical region to accumulate amyloid, closely followed by the cingulate and frontal cortices, then by the lateral parietal cortex. The extracted progression scores reveal a pattern similar to mean cortical distribution volume ratio (DVR), an index of global brain amyloid levels. The proposed method can be applied to other types of longitudinal imaging data, including metabolism, blood flow, tau, and structural imaging-derived measures, to extract individualized summary scores indicating disease progression and to provide voxelwise trajectories that can be compared between brain regions.},
author = {Bilgel, Murat and Prince, Jerry L and Wong, Dean F and Resnick, Susan M and Jedynak, Bruno M},
doi = {10.1016/j.neuroimage.2016.04.001},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { 80 and over, Computer-Assisted,Aged,Alzheimer Disease,Amyloid beta-Peptides,Biomarkers,Cerebral Cortex,Disease Progression,Female,Humans,Image Interpretation,Longitudinal Studies,Male,Multivariate Analysis,Positron-Emission Tomography,diagnostic imaging,metabolism,methods,pathology},
mendeley-groups = {PhDThesis/Review},
month = {jul},
pages = {658--670},
pmid = {27095307},
title = {{A multivariate nonlinear mixed effects model for longitudinal image analysis: Application to amyloid imaging.}},
volume = {134},
year = {2016}
}

@inproceedings{Bone2018,
abstract = {We propose a method to learn a distribution of shape trajectories from longitudinal data, i.e. the collection of individual objects repeatedly observed at multiple time-points. The method allows to compute an average spatiotemporal trajectory of shape changes at the group level, and the individual variations of this trajectory both in terms of geometry and time dynamics. First, we formulate a non-linear mixed-effects statistical model as the combination of a generic statistical model for manifold-valued longitudinal data, a deformation model defining shape trajectories via the action of a finite-dimensional set of diffeomorphisms with a manifold structure, and an efficient numerical scheme to compute parallel transport on this manifold. Second, we introduce a MCMC-SAEM algorithm with a specific approach to shape sampling, an adaptive scheme for proposal variances, and a log-likelihood tempering strategy to estimate our model. Third, we validate our algorithm on 2D simulated data, and then estimate a scenario of alteration of the shape of the hippocampus 3D brain structure during the course of Alzheimer's disease. The method shows for instance that hippocampal atrophy progresses more quickly in female subjects, and occurs earlier in APOE4 mutation carriers. We finally illustrate the potential of our method for classifying pathological trajectories versus normal ageing.},
annote = {Longitudinal, citar i prou.},
archivePrefix = {arXiv},
arxivId = {1803.10119},
author = {B{\^{o}}ne, Alexandre and Colliot, Olivier and Durrleman, Stanley},
booktitle = {Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit.},
doi = {10.1109/CVPR.2018.00966},
eprint = {1803.10119},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/B{\^{o}}ne, Colliot, Durrleman - 2018 - Learning distributions of shape trajectories from longitudinal datasets a hierarchical model on a m(5).pdf:pdf},
isbn = {9781538664209},
issn = {10636919},
mendeley-groups = {Papers bib/hipppaper/shape/shape-revision},
month = {mar},
pages = {9271--9280},
publisher = {IEEE Computer Society},
title = {{Learning Distributions of Shape Trajectories from Longitudinal Datasets: A Hierarchical Model on a Manifold of Diffeomorphisms}},
year = {2018}
}


@article{Breiman2001,
abstract = {There are two cultures in the use of statistical modeling to reach conclusions from data. One assumes that the data are generated by a given stochastic data model. The other uses algorithmic models and treats the data mechanism as unknown. The statistical community has been committed to the almost exclusive use of data models. This commit-ment has led to irrelevant theory, questionable conclusions, and has kept statisticians from working on a large range of interesting current prob-lems. Algorithmic modeling, both in theory and practice, has developed rapidly in fields outside statistics. It can be used both on large complex data sets and as a more accurate and informative alternative to data modeling on smaller data sets. If our goal as a field is to use data to solve problems, then we need to move away from exclusive dependence on data models and adopt a more diverse set of tools.},
annote = {Base paper discussing stadistical modelling. Differences between statistical paradigmn and machine learning.

The paper is 15 years old and it shows in some of the arguments the author and other commenters use, but most of the main ideas are valid points.},
archivePrefix = {arXiv},
arxivId = {0010},
author = {Breiman, Leo},
doi = {10.2307/2676681},
eprint = {0010},
isbn = {08834237},
issn = {08834237},
journal = {Stat. Sci.},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {199--231},
pmid = {10511666},
title = {{Statistical Modeling: The Two Cultures}},
volume = {16},
year = {2001}
}
@article{Cabral2015,
abstract = {Early diagnosis of Alzheimer disease (AD), while still at the stage known as mild cognitive impairment (MCI), is important for the development of new treatments. However, brain degeneration in MCI evolves with time and differs from patient to patient, making early diagnosis a very challenging task. Despite these difficulties, many machine learning techniques have already been used for the diagnosis of MCI and for predicting MCI to AD conversion, but the MCI group used in previous works is usually very heterogeneous containing subjects at different stages. The goal of this paper is to investigate how the disease stage impacts on the ability of machine learning methodologies to predict conversion. After identifying the converters and estimating the time of conversion (TC) (using neuropsychological test scores), we devised 5 subgroups of MCI converters (MCI-C) based on their temporal distance to the conversion instant (0, 6, 12, 18 and 24 months before conversion). Next, we used the FDG-PET images of these subgroups and trained classifiers to distinguish between the MCI-C at different stages and stable non-converters (MCI-NC). Our results show that MCI to AD conversion can be predicted as early as 24 months prior to conversion and that the discriminative power of the machine learning methods decreases with the increasing temporal distance to the TC, as expected. These findings were consistent for all the tested classifiers. Our results also show that this decrease arises from a reduction in the information contained in the regions used for classification and by a decrease in the stability of the automatic selection procedure.},
author = {Cabral, Carlos and Morgado, Pedro M and {Campos Costa}, Durval and Silveira, Margarida},
doi = {10.1016/j.compbiomed.2015.01.003},
isbn = {1879-0534 0010-4825},
issn = {18790534},
journal = {Comput. Biol. Med.},
keywords = {Alzheimer's disease,Conversion,Early diagnosis,FDG-PET,Machine learning,Mild cognitive impairment},
mendeley-groups = {PhDThesis/Review},
pages = {101--109},
pmid = {25625698},
title = {{Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages}},
volume = {58},
year = {2015}
}
@article{Casanova2018,
abstract = {INTRODUCTION: The main goal of this work is to investigate the feasibility of estimating an anatomical index that can be used as an Alzheimer's disease (AD) risk factor in the Women's Health Initiative Magnetic Resonance Imaging Study (WHIMS-MRI) using MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), a well-characterized imaging database of AD patients and cognitively normal subjects. We called this index AD Pattern Similarity (AD-PS) scores. To demonstrate the construct validity of the scores, we investigated their associations with several AD risk factors. The ADNI and WHIMS imaging databases were collected with different goals, populations and data acquisition protocols: it is important to demonstrate that the approach to estimating AD-PS scores can bridge these differences. METHODS: MRI data from both studies were processed using high-dimensional warping methods. High-dimensional classifiers were then estimated using the ADNI MRI data. Next, the classifiers were applied to baseline and follow-up WHIMS-MRI GM data to generate the GM AD-PS scores. To study the validity of the scores we investigated associations between GM AD-PS scores at baseline (Scan 1) and their longitudinal changes (Scan 2 -Scan 1) with: 1) age, cognitive scores, white matter small vessel ischemic disease (WM SVID) volume at baseline and 2) age, cognitive scores, WM SVID volume longitudinal changes respectively. In addition, we investigated their associations with time until classification of independently adjudicated status in WHIMS-MRI. RESULTS: Higher GM AD-PS scores from WHIMS-MRI baseline data were associated with older age, lower cognitive scores, and higher WM SVID volume. Longitudinal changes in GM AD-PS scores (Scan 2 - Scan 1) were also associated with age and changes in WM SVID volumes and cognitive test scores. Increases in the GM AD-PS scores predicted decreases in cognitive scores and increases in WM SVID volume. GM AD-PS scores and their longitudinal changes also were associated with time until classification of cognitive impairment. Finally, receiver operating characteristic curves showed that baseline GM AD-PS scores of cognitively normal participants carried information about future cognitive status determined during follow-up. DISCUSSION: We applied a high-dimensional machine learning approach to estimate a novel AD risk factor for WHIMS-MRI study participants using ADNI data. The GM AD-PS scores showed strong associations with incident cognitive impairment and cross-sectional and longitudinal associations with age, cognitive function, cognitive status and WM SVID volume lending support to the ongoing validation of the GM AD-PS score.},
author = {Casanova, Ramon and Barnard, Ryan T and Gaussoin, Sarah A and Saldana, Santiago and Hayden, Kathleen M and Manson, JoAnn E and Wallace, Robert B and Rapp, Stephen R and Resnick, Susan M and Espeland, Mark A and Chen, Jiu-Chiuan},
doi = {10.1016/j.neuroimage.2018.08.040},
institution = {WHIMS-MRI Study Group and the Alzheimer's disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Review},
pages = {401--411},
pmid = {30130645},
title = {{Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer's disease across imaging databases.}},
volume = {183},
year = {2018}
}
@article{miriad,
annote = {Atrophy evolution (longitudinal)

MIRIAD Dataset

Stadistical analysis again

Not really important?},
author = {Cash, D M and Frost, C and Iheme, L O and {\"{U}}nay, D and Kandemir, M and Fripp, J and Salvado, O and Bourgeat, P and Reuter, M and Fischl, B and Lorenzi, M and Frisoni, G B and Pennec, X and Peirson, R K and Gunter, J L and Senjem, M L and Jack, C R and Guizard, N and Fonov, V S and Collins, D L and Modat, M and Cardoso, M J and Leung, K K and Wang, H and Das, S R and Yushkevich, P A and Malone, I B and Fox, N C and Schott, J M and Ourselin, S},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Review},
pages = {149--164},
title = {{Assessing atrophy measurement techniques in dementia: Results from the MIRIAD atrophy challenge}},
volume = {123},
year = {2015}
}
@article{Chen2012,
abstract = {Identifying interactions among brain regions from structural magnetic-resonance images presents one of the major challenges in computational neuroanatomy. We propose a Bayesian data-mining approach to the detection of longitudinal morphological changes in the human brain. Our method uses a dynamic Bayesian network to represent evolving inter-regional dependencies. The major advantage of dynamic Bayesian network modeling is that it can represent complicated interactions among temporal processes. We validated our approach by analyzing a simulated atrophy study, and found that this approach requires only a small number of samples to detect the ground-truth temporal model. We further applied dynamic Bayesian network modeling to a longitudinal study of normal aging and mild cognitive impairment--the Baltimore Longitudinal Study of Aging. We found that interactions among regional volume-change rates for the mild cognitive impairment group are different from those for the normal-aging group.},
author = {Chen, Rong and Resnick, Susan M and Davatzikos, Christos and Herskovits, Edward H},
doi = {10.1016/j.neuroimage.2011.09.023},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { 80 and over, Statistical,Aged,Aging,Algorithms,Atrophy,Bayes Theorem,Brain,Brain Mapping,Cognitive Dysfunction,Computer Simulation,Data Mining,Disease Progression,Echo-Planar Imaging,Female,Humans,Longitudinal Studies,Male,Middle Aged,Models,Neural Networks (Computer),Reproducibility of Results,Sample Size,Stereotaxic Techniques,anatomy {\&} histology,growth {\&} development,methods,pathology,physiology},
mendeley-groups = {PhDThesis/Review},
month = {feb},
number = {3},
pages = {2330--2338},
pmid = {21963916},
title = {{Dynamic Bayesian network modeling for longitudinal brain morphometry.}},
volume = {59},
year = {2012}
}
@article{Chen2011b,
abstract = {Recent technological advances have made it possible for many studies to collect high dimensional data (HDD) longitudinally, for example, images collected during different scanning sessions. Such studies may yield temporal changes of selected features that, when incorporated with machine learning methods, are able to predict disease status or responses to a therapeutic treatment. Support vector machine (SVM) techniques are robust and effective tools well suited for the classification and prediction of HDD. However, current SVM methods for HDD analysis typically consider cross-sectional data collected during one time period or session (e.g., baseline). We propose a novel support vector classifier (SVC) for longitudinal HDD that allows simultaneous estimation of the SVM separating hyperplane parameters and temporal trend parameters, which determine the optimal means to combine the longitudinal data for classification and prediction. Our approach is based on an augmented reproducing kernel function and uses quadratic programming for optimization. We demonstrate the use and potential advantages of our proposed methodology using a simulation study and a data example from the Alzheimer's disease Neuroimaging Initiative. The results indicate that our proposed method leverages the additional longitudinal information to achieve higher accuracy than methods using only cross-sectional data and methods that combine longitudinal data by naively expanding the feature space.},
annote = {Vaia, aquest paper ja l'havia mirat.},
archivePrefix = {arXiv},
arxivId = {1206.3552},
author = {Chen, Shuo and {Dubois Bowman}, F},
doi = {10.1002/sam.10141},
eprint = {1206.3552},
isbn = {1932-1872},
issn = {19321872},
journal = {Stat. Anal. Data Min.},
keywords = {Alzheimer's disease,FMRI,Longitudinal high-dimensional data,PET,Prediction,Support vector classifier},
mendeley-groups = {PhDThesis/Review},
number = {6},
pages = {604--611},
pmid = {21824845},
publisher = {NIH Public Access},
title = {{A novel support vector classifier for longitudinal high-dimensional data and its application to neuroimaging data}},
volume = {4},
year = {2011}
}
@article{Chen2015,
abstract = {Predicting disease risk and progression is one of the main goals in many clinical research studies. Cohort studies on the natural history and etiology of chronic diseases span years and data are collected at multiple visits. Although, kernel-based statistical learning methods are proven to be powerful for a wide range of disease prediction problems, these methods are only well studied for independent data, but not for longitudinal data. It is thus important to develop time-sensitive prediction rules that make use of the longitudinal nature of the data. In this paper, we develop a novel statistical learning method for longitudinal data by introducing subject-specific short-term and long-term latent effects through a designed kernel to account for within-subject correlation of longitudinal measurements. Since the presence of multiple sources of data is increasingly common, we embed our method in a multiple kernel learning framework and propose a regularized multiple kernel statistical learning with random effects to construct effective nonparametric prediction rules. Our method allows easy integration of various heterogeneous data sources and takes advantage of correlation among longitudinal measures to increase prediction power. We use different kernels for each data source taking advantage of the distinctive feature of each data modality, and then optimally combine data across modalities. We apply the developed methods to two large epidemiological studies, one on Huntington's disease and the other on Alzheimer's Disease (Alzheimer's Disease Neuroimaging Initiative, ADNI) where we explore a unique opportunity to combine imaging and genetic data to study prediction of mild cognitive impairment, and show a substantial gain in performance while accounting for the longitudinal aspect of the data.},
annote = {Implementation of Longitudinal Kernel.

Authors tag their work as "Statistical Learning", but it is more of a machine learning approach.

Really old papers.

Use SVM.

Interesting to review further.},
author = {Chen, Tianle and Zeng, Donglin and Wang, Yuanjia},
doi = {10.1111/biom.12343},
isbn = {0006-341x},
issn = {15410420},
journal = {Biometrics},
keywords = {Disease prediction,Integrative analysis,Latent effects,Statistical learning},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {918--928},
pmid = {26177419},
title = {{Multiple kernel learning with random effects for predicting longitudinal outcomes and data integration}},
volume = {71},
year = {2015}
}
@article{Chen2016,
abstract = {OBJECTIVE: To evaluate the potential clinical value of quantitative functional FDG PET and pathological amyloid-beta PET with cerebrospinal fluid (CSF) biomarkers and clinical assessments in the prediction of Alzheimer's disease (AD) progression. METHODS: We studied 82 subjects for up to 96 months (median = 84 months) in a longitudinal Alzheimer's Disease Neuroimaging Initiative (ADNI) project. All preprocessed PET images were spatially normalized to standard Montreal Neurologic Institute space. Regions of interest (ROI) were defined on MRI template, and standard uptake values ratios (SUVRs) to the cerebellum for FDG and amyloid-beta PET were calculated. Predictive values of single and multiparametric PET biomarkers with and without clinical assessments and CSF biomarkers for AD progression were evaluated using receiver operating characteristic (ROC) analysis and logistic regression model. RESULTS: The posterior precuneus and cingulate SUVRs were identified for both FDG and amyloid-beta PET in predicating progression in normal controls (NCs) and subjects with mild cognitive impairment (MCI). FDG parietal and lateral temporal SUVRs were suggested for monitoring NCs and MCI group progression, respectively. 18F-AV45 global cortex attained (78.6{\%}, 74.5{\%}, 75.4{\%}) (sensitivity, specificity, accuracy) in predicting NC progression, which is comparable to the 11C-PiB global cortex SUVR's in predicting MCI to AD. A logistic regression model to combine FDG parietal and posterior precuneus SUVR and Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) Total Mod was identified in predicating NC progression with (80.0{\%}, 94.9{\%}, 93.9{\%}) (sensitivity, specificity, accuracy). The selected model including FDG posterior cingulate SUVR, ADAS-Cog Total Mod, and Mini-Mental State Exam (MMSE) scores for predicating MCI to AD attained (96.4{\%}, 81.2{\%}, 83.6{\%}) (sensitivity, specificity, accuracy). 11C-PiB medial temporal SUVR with MMSE significantly increased 11C-PiB PET AUC to 0.915 (p{\textless}0.05) in predicating MCI to AD with (77.8{\%}, 90.4{\%}, 88.5{\%}) (sensitivity, specificity, accuracy). CONCLUSION: Quantitative FDG and 11C-PiB PET with clinical cognitive assessments significantly improved accuracy in the predication of AD progression.},
annote = {ES ESTADISTIC},
author = {Chen, Xueqi and Zhou, Yun and Wang, Rongfu and Cao, Haoyin and Reid, Savina and Gao, Rui and Han, Dong},
doi = {10.1371/journal.pone.0154406},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1932-6203 (Electronic)},
journal = {PLoS One},
keywords = { 80 and over, Computer-Assisted, Factual,80 and over,Aged,Alzheimer Disease,Amyloid beta-Peptides,Biomarkers,Computer-Assisted,Databases,Disease Progression,Factual,Female,Fluorodeoxyglucose F18,Humans,Image Processing,Magnetic Resonance Imaging,Male,Positron-Emission Tomography,Prognosis,ROC Curve,Radiopharmaceuticals,diagnostic imaging,etiology,metabolism,methods,pathology},
mendeley-groups = {PhDThesis/Review},
number = {5},
pages = {e0154406},
pmid = {27183116},
title = {{Potential Clinical Value of Multiparametric PET in the Prediction of Alzheimer's Disease Progression.}},
volume = {11},
year = {2016}
}
@article{Chenhui2014,
abstract = {Pinpointing the sources of dementia is crucial to the effective treatment of neurodegenerative diseases. In this paper, we model the dementia progression by a diffusive model over the brain network with sparse impulsive stimulations. By solving inverse problems, we localize the possible origins of Alzheimer's disease based on a large set of repeated magnetic resonance imaging (MRI) scans in ADNI. The distribution of the sources averaged over the sample population is evaluated. We find that the dementia sources have different concentrations in the brain lobes for Alzheimer's disease (AD) patients and mild cognitive impairment (MCI) subjects, indicating possible switch of the dementia driving mechanism. Our model provides a quantitative way to perform explanatory analysis of the dynamics of dementia.},
annote = {difussion model},
author = {Chenhui, Hu and Hua, Xue and Thompson, Paul M and Fakhri, Georges El and Li, Quanzheng},
doi = {10.1007/978-3-319-10581-9_6},
issn = {16113349},
journal = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
keywords = {Alzheimer's disease,Brain morphology,Longitudinal study,MRI,Network diffusion,Sources of dementia},
mendeley-groups = {PhDThesis/Review},
pages = {42--49},
title = {{Inferring sources of dementia progression with network diffusion model}},
volume = {8679},
year = {2014}
}

@article{Chetelat2003,
abstract = {Patients with mild cognitive impairment (MCI) were assessed, and a metabolic profile associated with conversion to AD at 18-month follow-up was sought. As compared with nonconverters (n = 10), converters (n = 7) had lower fluorodeoxyglucose uptake in the right temporoparietal cortex (p = 0.02, corrected for cluster size), without individual overlap. Awaiting replication in an independent sample, these findings suggest that among patients with MCI, fluorodeoxyglucose PET may accurately identify rapid converters.},
author = {Ch{\'{e}}telat, G and Desgranges, B and {De la Sayette}, V and Viader, F and Eustache, F and Baron, Jean Claude},
doi = {10.1212/01.WNL.0000055847.17752.E6},
isbn = {1526-632X (Electronic)$\backslash$n0028-3878 (Linking)},
issn = {00283878},
journal = {Neurology},
mendeley-groups = {PhDThesis/Review},
month = {jun},
number = {8},
pages = {1374--1377},
pmid = {12707450},
publisher = {American Academy of Neurology},
title = {{Mild cognitive impairment: Can FDG-PET predict who is to rapidly convert to Alzheimer's disease?}},
volume = {60},
year = {2003}
}
@article{Chi2017,
abstract = {Prediction of onset and progression of cognitive decline and dementia is important both for understanding the underlying disease processes and for planning health care for populations at risk. Predictors identified in research studies are typically accessed at one point in time. In this manuscript, we argue that an accurate model for predicting cognitive status over relatively long periods requires inclusion of time-varying components that are sequentially assessed at multiple time points (e.g., in multiple follow-up visits). We developed a pilot model to test the feasibility of using either estimated or observed risk factors to predict cognitive status. We developed two models, the first using a sequential estimation of risk factors originally obtained from 8 years prior, then improved by optimization. This model can predict how cognition will change over relatively long time periods. The second model uses observed rather than estimated time-varying risk factors and, as expected, results in better prediction. This model can predict when newly observed data are acquired in a follow-up visit. Performances of both models that are evaluated in10-fold cross-validation and various patient subgroups show supporting evidence for these pilot models. Each model consists of multiple base prediction units (BPUs), which were trained using the same set of data. The difference in usage and function between the two models is the source of input data: either estimated or observed data. In the next step of model refinement, we plan to integrate the two types of data together to flexibly predict dementia status and changes over time, when some time-varying predictors are measured only once and others are measured repeatedly. Computationally, both data provide upper and lower bounds for predictive performance.},
author = {Chi, Chih Lin and Zeng, Wenjun and Oh, Wonsuk and Borson, Soo and Lenskaia, Tatiana and Shen, Xinpeng and Tonellato, Peter J},
doi = {10.1016/j.jbi.2017.11.002},
issn = {15320464},
journal = {J. Biomed. Inform.},
keywords = {Dementia,Machine learning,Predict cognitive decline,Risk factors},
mendeley-groups = {PhDThesis/Review},
pages = {78--86},
publisher = {Academic Press},
title = {{Personalized long-term prediction of cognitive function: Using sequential assessments to improve model performance}},
volume = {76},
year = {2017}
}
@article{chincarini,
annote = {-Longitudinal

-Hippocampal segmentation algorithm. Volume change per year.

-Machine learning},
author = {Chincarini, A and Sensi, F and Rei, L and Gemme, G and Squarcia, S and Longo, R and Brun, F and Tangaro, S and Bellotti, R and Amoroso, N and Bocchetta, M and Redolfi, A and Bosco, P and Boccardi, M and Frisoni, G B and Nobili, F},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Review},
pages = {834--847},
title = {{Integrating longitudinal information in hippocampal volume measurements for the early detection of Alzheimer's disease}},
volume = {125},
year = {2016}
}
@article{Choi2017,
abstract = {For effective treatment of Alzheimer disease (AD), it is important to identify subjects who are most likely to exhibit rapid cognitive decline. Herein, we developed a novel framework based on a deep convolutional neural network which can predict future cognitive decline in mild cognitive impairment (MCI) patients using flurodeoxyglucose and florbetapir positron emission tomography (PET). The architecture of the network only relies on baseline PET studies of AD and normal subjects as the training dataset. Feature extraction and complicated image preprocessing including nonlinear warping are unnecessary for our approach. Accuracy of prediction (84.2{\%}) for conversion to AD in MCI patients outperformed conventional feature-based quantification approaches. ROC analyses revealed that performance of CNN-based approach was significantly higher than that of the conventional quantification methods (p {\textless}0.05). Output scores of the network were strongly correlated with the longitudinal change in cognitive measurements. These results show the feasibility of deep learning as a tool for predicting disease outcome using brain images.},
annote = {NO LONGITUDINAL},
archivePrefix = {arXiv},
arxivId = {1704.06033},
author = {Choi, Hongyoon and Jin, Kyong Hwan},
doi = {10.1016/j.bbr.2018.02.017},
eprint = {1704.06033},
issn = {01664328},
mendeley-groups = {PhDThesis/Review},
title = {{Predicting Cognitive Decline with Deep Learning of Brain Metabolism and Amyloid Imaging}},
year = {2017}
}
@article{Choo2013,
abstract = {The biomarker-based new diagnostic criteria have been proposed for Alzheimer's disease (AD) spectrum. However, any biomarker alone has not been known to have satisfactory AD predictability. We explored the best combination model with baseline demography, neuropsychology, 18F-fluorodeoxyglucose positron emission tomography (FDG-PET), cerebrospinal fluid (CSF) biomarkers, and apolipoprotein E (APOE) genotype evaluation to predict progression to AD in mild cognitive impairment (MCI) patients. A longitudinal clinical follow-up (mean, 44 months; range, 1.6-161.7 months) of MCI patients was done. Among 83 MCI patients, 26 progressed to AD (MCI-AD) and 51 did not deteriorate (MCI-Stable). We applied that univariate and multivariate logistic regression analyses, and multistep model selection for AD predictors including biomarkers. In univariate logistic analysis, we selected age, Rey Auditory Verbal Retention Test, parietal glucose metabolic rate, CSF total tau, and presence or not of at least one APOE epsilon4 allele as predictors. Through multivariate stepwise logistic analysis and model selection, we found the combination of parietal glucose metabolic rate and total tau representing the best model for AD prediction. In conclusion, our findings highlight that the combination of regional glucose metabolic assessment by PET and CSF biomarkers evaluation can significantly improve AD predictive diagnostic accuracy of each respective method.},
annote = {NOT LONGITUDINAL},
author = {Choo, Il Han and Ni, Ruiqing and Scholl, Michael and Wall, Anders and Almkvist, Ove and Nordberg, Agneta},
doi = {10.3233/JAD-2012-121489},
issn = {1875-8908 (Electronic)},
journal = {J. Alzheimers. Dis.},
keywords = {Aged,Alzheimer Disease,Biomarkers,Cognitive Dysfunction,Disease Progression,Female,Fluorodeoxyglucose F18,Follow-Up Studies,Humans,Longitudinal Studies,Male,Middle Aged,Neuropsychological Tests,Positron-Emission Tomography,Predictive Value of Tests,cerebrospinal fluid,diagnostic imaging,psychology,standards},
mendeley-groups = {PhDThesis/Review},
number = {4},
pages = {929--939},
pmid = {23047371},
title = {{Combination of 18F-FDG PET and cerebrospinal fluid biomarkers as a better predictor of the progression to Alzheimer's disease in mild cognitive impairment patients.}},
volume = {33},
year = {2013}
}
@article{Clark2012,
abstract = {This article investigates longitudinal imaging characteristics of early cognitive decline during normal aging, leveraging on high-dimensional imaging pattern classification methods for the development of early biomarkers of cognitive decline. By combining magnetic resonance imaging (MRI) and resting positron emission tomography (PET) cerebral blood flow (CBF) images, an individualized score is generated using high-dimensional pattern classification, which predicts subsequent cognitive decline in cognitively normal older adults of the Baltimore Longitudinal Study of Aging. The resulting score, termed SPARE-CD (Spatial Pattern of Abnormality for Recognition of Early Cognitive Decline), analyzed longitudinally for 143 cognitively normal subjects over 8 years, shows functional and structural changes well before (2.3-2.9 years) changes in neurocognitive testing (California Verbal Learning Test [CVLT] scores) can be measured. Additionally, this score is found to be correlated to the [(11)C] Pittsburgh compound B (PiB) PET mean distribution volume ratio at a later time. This work indicates that MRI and PET images, combined with advanced pattern recognition methods, may be useful for very early detection of cognitive decline.},
author = {Clark, Vanessa H and Resnick, Susan M and Doshi, Jimit and Beason-Held, Lori L and Zhou, Yun and Ferrucci, Luigi and Wong, Dean F and Kraut, Michael A and Davatzikos, Christos},
doi = {10.1016/j.neurobiolaging.2012.01.010},
issn = {1558-1497 (Electronic)},
journal = {Neurobiol. Aging},
keywords = { 80 and over,Age Factors,Aged,Aging,Aniline Compounds,Brain,Brain Mapping,Cerebrovascular Circulation,Cognition Disorders,Female,Fluorodeoxyglucose F18,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Male,Middle Aged,Neuropsychological Tests,Positron-Emission Tomography,Radiopharmaceuticals,Statistics as Topic,Thiazoles,diagnosis,diagnostic imaging,pathology,physiopathology},
mendeley-groups = {PhDThesis/Review},
number = {12},
pages = {2733--2745},
pmid = {22365049},
title = {{Longitudinal imaging pattern analysis (SPARE-CD index) detects early structural and functional changes before cognitive decline in healthy older adults.}},
volume = {33},
year = {2012}
}
@article{cuingnet,
annote = {-Review Paper for AD classification with different features and methods using same dataset.

-For the prediction of conversion, no classifier
obtained significantly better results than chance. 
- Features: cortical thickness : direct, atlas based, ROI
hippocampus: Volume, shape

-Specificity and sensitivity.},
author = {Cuingnet, R and Gerardin, E and Tessieras, J and Auzias, G and Leh{\'{e}}ricy, S and Habert, M O and Chupin, M and Benali, H and Colliot, O},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Review},
pages = {766--781},
title = {{Automatic classification of patients with Alzheimer's disease from structural MRI: A comparison of ten methods using the ADNI database}},
volume = {56},
year = {2011}
}
@article{Da2014,
abstract = {This study evaluates the individual, as well as relative and joint value of indices obtained from magnetic resonance imaging (MRI) patterns of brain atrophy (quantified by the SPARE-AD index), cerebrospinal fluid (CSF) biomarkers, APOE genotype, and cognitive performance (ADAS-Cog) in progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) within a variable follow-up period up to 6 years, using data from the Alzheimer's Disease Neuroimaging Initiative-1 (ADNI-1). SPARE-AD was first established as a highly sensitive and specific MRI-marker of AD vs. cognitively normal (CN) subjects (AUC = 0.98). Baseline predictive values of all aforementioned indices were then compared using survival analysis on 381 MCI subjects. SPARE-AD and ADAS-Cog were found to have similar predictive value, and their combination was significantly better than their individual performance. APOE genotype did not significantly improve prediction, although the combination of SPARE-AD, ADAS-Cog and APOE epsilon4 provided the highest hazard ratio estimates of 17.8 (last vs. first quartile). In a subset of 192 MCI patients who also had CSF biomarkers, the addition of Abeta1-42, t-tau, and p-tau181p to the previous model did not improve predictive value significantly over SPARE-AD and ADAS-Cog combined. Importantly, in amyloid-negative patients with MCI, SPARE-AD had high predictive power of clinical progression. Our findings suggest that SPARE-AD and ADAS-Cog in combination offer the highest predictive power of conversion from MCI to AD, which is improved, albeit not significantly, by APOE genotype. The finding that SPARE-AD in amyloid-negative MCI patients was predictive of clinical progression is not expected under the amyloid hypothesis and merits further investigation.},
author = {Da, Xiao and Toledo, Jon B and Zee, Jarcy and Wolk, David A and Xie, Sharon X and Ou, Yangming and Shacklett, Amanda and Parmpi, Paraskevi and Shaw, Leslie and Trojanowski, John Q and Davatzikos, Christos},
doi = {10.1016/j.nicl.2013.11.010},
institution = {Alzheimer's Neuroimaging Initiative},
issn = {2213-1582 (Print)},
journal = {NeuroImage. Clin.},
keywords = { 80 and over,Aged,Alzheimer Disease,Amyloid beta-Peptides,Apolipoproteins E,Atrophy,Biomarkers,Brain,Cognitive Dysfunction,Disease Progression,Female,Genotype,Humans,Longitudinal Studies,Magnetic Resonance Imaging,Male,Neuropsychological Tests,Peptide Fragments,Psychiatric Status Rating Scales,ROC Curve,cerebrospinal fluid,diagnosis,genetics,pathology,tau Proteins},
mendeley-groups = {PhDThesis/Review},
pages = {164--173},
pmid = {24371799},
title = {{Integration and relative value of biomarkers for prediction of MCI to AD progression: spatial patterns of brain atrophy, cognitive scores, APOE genotype and CSF biomarkers.}},
volume = {4},
year = {2014}
}
@article{Davatzikos2011,
abstract = {Magnetic resonance imaging (MRI) patterns were examined together with cerebrospinal fluid (CSF) biomarkers in serial scans of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI). The SPARE-AD score, summarizing brain atrophy patterns, was tested as a predictor of short-term conversion to Alzheimer's disease (AD). MCI individuals that converted to AD (MCI-C) had mostly positive baseline SPARE-AD (Spatial Pattern of Abnormalities for Recognition of Early AD) and atrophy in temporal lobe gray matter (GM) and white matter (WM), posterior cingulate/precuneous, and insula. MCI individuals that converted to AD had mostly AD-like baseline CSF biomarkers. MCI nonconverters (MCI-NC) had mixed baseline SPARE-AD and CSF values, suggesting that some MCI-NC subjects may later convert. Those MCI-NC with most negative baseline SPARE-AD scores (normal brain structure) had significantly higher baseline Mini Mental State Examination (MMSE) scores (28.67) than others, and relatively low annual rate of Mini Mental State Examination decrease (-0.25). MCI-NC with midlevel baseline SPARE-AD displayed faster annual rates of SPARE-AD increase (indicating progressing atrophy). SPARE-AD and CSF combination improved prediction over individual values. In summary, both SPARE-AD and CSF biomarkers showed high baseline sensitivity, however, many MCI-NC had abnormal baseline SPARE-AD and CSF biomarkers. Longer follow-up will elucidate the specificity of baseline measurements. {\textcopyright}2011 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Davatzikos, Christos and Bhatt, Priyanka and Shaw, Leslie M and Batmanghelich, Kayhan N and Trojanowski, John Q},
doi = {10.1016/j.neurobiolaging.2010.05.023},
eprint = {NIHMS150003},
isbn = {0197-4580 1558-1497 (electronic)},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,CSF biomarkers,Early detection,Imaging biomarkers,MCI,Mild cognitive impairment,Pattern classification,SPARE-AD},
mendeley-groups = {PhDThesis/Review},
pmid = {20594615},
title = {{Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification}},
year = {2011}
}
@article{Davatzikos2009,
abstract = {A challenge in developing informative neuroimaging biomarkers for early diagnosis of Alzheimer's disease is the need to identify biomarkers that are evident before the onset of clinical symptoms, and which have sufficient sensitivity and specificity on an individual patient basis. Recent literature suggests that spatial patterns of brain atrophy discriminate amongst Alzheimer's disease, mild cognitive impairment (MCI) and cognitively normal (CN) older adults with high accuracy on an individual basis, thereby offering promise that subtle brain changes can be detected during prodromal Alzheimer's disease stages. Here, we investigate whether these spatial patterns of brain atrophy can be detected in CN and MCI individuals and whether they are associated with cognitive decline. Images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to construct a pattern classifier that recognizes spatial patterns of brain atrophy which best distinguish Alzheimer's disease patients from CN on an individual person basis. This classifier was subsequently applied to longitudinal magnetic resonance imaging scans of CN and MCI participants in the Baltimore Longitudinal Study of Aging (BLSA) neuroimaging study. The degree to which Alzheimer's disease-like patterns were present in CN and MCI subjects was evaluated longitudinally in relation to cognitive performance. The oldest BLSA CN individuals showed progressively increasing Alzheimer's disease-like patterns of atrophy, and individuals with these patterns had reduced cognitive performance. MCI was associated with steeper longitudinal increases of Alzheimer's disease-like patterns of atrophy, which separated them from CN (receiver operating characteristic area under the curve equal to 0.89). Our results suggest that imaging-based spatial patterns of brain atrophy of Alzheimer's disease, evaluated with sophisticated pattern analysis and recognition methods, may be useful in discriminating among CN individuals who are likely to be stable versus those who will show cognitive decline. Future prospective studies will elucidate the temporal dynamics of spatial atrophy patterns and the emergence of clinical symptoms. Abbreviations: ADNI = Alzheimer's Disease Neuroimaging Initiative; BLSA = Baltimore Longitudinal Study of Aging; CN = cognitively normal; ICV = intra-cranial volume; MCI = mild cognitive impairment; SPARE-AD = Spatial Pattern of Abnormality for Recognition of Early Alzheimer's disease},
annote = {From Duplicate 2 (Longitudinal progression of Alzheimers-like patterns of atrophy in normal older adults: The SPARE-AD index - Davatzikos, Christos; Xu, Feng; An, Yang; Fan, Yong; Resnick, Susan M)

- Main method:
Pattern classification method to create a score (SPARE-AD), later use mixed models to model longitudinal progression and do prediction.
- Type of problem to solve
Classification CN/MCI, plus longitudinal progression.
- Small evaluation:
More statistical paper: fixed prodefined model, no training, finding relationship between variables, no test set.

Other observations: actual age progression.},
author = {Davatzikos, Christos and Xu, Feng and An, Yang and Fan, Yong and Resnick, Susan M},
doi = {10.1093/brain/awp091},
isbn = {1460-2156 (Electronic)$\backslash$n0006-8950 (Linking)},
issn = {00068950},
journal = {Brain},
keywords = {80 and over,Aged,Ageing,Aging,Alzheimer Disease,Atrophy,Brain,Cognition Disorders,Computer-Assisted,Disease Progression,Early Alzheimers disease,Female,Humans,Image Interpretation,Longitudinal Studies,Magnetic Resonance Imaging,Male,Middle Aged,Mild cognitive impairment,Neuroimaging,Neuropsychological Tests,Prognosis,SPARE-AD,complications,etiology,methods,pathology,psychology},
mendeley-groups = {PhDThesis/Review},
number = {8},
pages = {2026--2035},
pmid = {19416949},
title = {{Longitudinal progression of Alzheimers-like patterns of atrophy in normal older adults: The SPARE-AD index}},
volume = {132},
year = {2009}
}
@article{Dawson2016,
abstract = {Longitudinal data are often plagued with sparsity of time points where measurements are available. The functional data analysis perspective has been shown to provide an effective and flexible approach to address this problem for the case where measurements are sparse but their times are randomly distributed over an interval. Here we focus on a different scenario where available data can be characterized as snippets, which are very short stretches of longitudinal measurements. For each subject the stretch of available data is much shorter than the time frame of interest, a common occurrence in accelerated longitudinal studies. An added challenge is introduced if a time proxy that is basic for usual longitudinal modeling is not available. This situation arises in the case of Alzheimer's disease and comparable scenarios, where one is interested in time dynamics of declining performance, but the time of disease onset is unknown and the chronological age does not provide a meaningful time reference for longitudinal modeling. Our main methodological contribution is to address this problem with a novel approach. Key quantities for our approach are conditional quantile trajectories for monotonic processes that emerge as solutions of a dynamic system, and for which we obtain uniformly consistent estimates. These trajectories are shown to be useful to describe processes that quantify deterioration over time, such as hippocampal volumes in Alzheimer's patients.},
annote = {dIRECT MISSING DATA IMPUTATION METHOD

It considers long data as snippets of observed data over age.},
archivePrefix = {arXiv},
arxivId = {1606.00991},
author = {Dawson, Matthew and M{\"{u}}ller, Hans-Georg},
doi = {10.1080/01621459.2017.1356321},
eprint = {1606.00991},
issn = {0162-1459},
journal = {J. Am. Stat. Assoc.},
mendeley-groups = {PhDThesis/Review},
month = {jun},
title = {{Dynamic Modeling of Conditional Quantile Trajectories, with Application to Longitudinal Snippet Data}},
year = {2017}
}
@article{Delor2013,
abstract = {Disease-onset time (DOT) and disease trajectory concepts were applied to derive an Alzheimer's disease (AD) progression population model using the clinical dementia rating scale-sum of boxes (CDR-SOB) from the AD neuroimaging initiative (ADNI) database. The model enabled the estimation of a DOT and a disease trajectory for each patient. The model also allowed distinguishing fast and slow-progressing subpopulations according to the functional assessment questionnaire, normalized hippocampal volume, and CDR-SOB score at study entry. On the basis of these prognostic factors, 81{\%} of the mild cognitive impairment (MCI) subjects could correctly be assigned to slow or fast progressers, and 77{\%} of MCI to AD conversions could be predicted whereas the model described correctly 84{\%} of the conversions. Finally, synchronization of the biomarker-time profiles on estimated individual DOT virtually expanded the population observation period from 3 to 8 years. DOT-disease trajectory model is a powerful approach that could be applied to many progressive diseases.CPT: Pharmacometrics {\&} Systems Pharmacology (2013) 2, e78; doi:10.1038/psp.2013.54; advance online publication 2 October 2013.},
author = {Delor, I and Charoin, J E and Gieschke, R and Retout, S and Jacqmin, P},
doi = {10.1038/psp.2013.54},
isbn = {2163-8306 (Electronic)},
issn = {21638306},
journal = {CPT Pharmacometrics Syst. Pharmacol.},
mendeley-groups = {PhDThesis/Review},
number = {10},
pages = {1--10},
pmid = {24088949},
title = {{Modeling Alzheimer's disease progression using disease onset time and disease trajectory concepts applied to CDR-SOB scores from ADNI}},
volume = {2},
year = {2013}
}
@article{Dimitriadis2017,
abstract = {Background: In the era of computer-assisted diagnostic tools for various brain diseases, Alzheimer's disease (AD) covers a large percentage of neuroimaging research, with the main scope being its use in daily practice. However, there has been no study attempting to simultaneously discriminate among Healthy Controls (HC), early mild cognitive impairment (MCI), late MCI (cMCI) and stable AD, using features derived from a single modality, namely MRI. New method: Based on preprocessed MRI images from the organizers of a neuroimaging challenge,.33The preprocessing of the T1-weighted Magnetic Resonance Images (MRI) was conducted by the organizers of the competition; information can be found here: https://inclass.kaggle.com/c/mci-prediction we attempted to quantify the prediction accuracy of multiple morphological MRI features to simultaneously discriminate among HC, MCI, cMCI and AD. We explored the efficacy of a novel scheme that includes multiple feature selections via Random Forest from subsets of the whole set of features (e.g. whole set, left/right hemisphere etc.), Random Forest classification using a fusion approach and ensemble classification via majority voting.From the ADNI database, 60 HC, 60 MCI, 60 cMCI and 60 CE were used as a training set with known labels. An extra dataset of 160 subjects (HC: 40, MCI: 40, cMCI: 40 and AD: 40) was used as an external blind validation dataset to evaluate the proposed machine learning scheme. Results: In the second blind dataset, we succeeded in a four-class classification of 61.9{\%} by combining MRI-based features with a Random Forest-based Ensemble Strategy. We achieved the best classification accuracy of all teams that participated in this neuroimaging competition. Comparison with existing method(s): The results demonstrate the effectiveness of the proposed scheme to simultaneously discriminate among four groups using morphological MRI features for the very first time in the literature. Conclusions: Hence, the proposed machine learning scheme can be used to define single and multi-modal biomarkers for AD.},
annote = {NOT LONGITUDINAL},
author = {Dimitriadis, Stavros I and Liparas, Dimitris and Tsolaki, Magda N},
doi = {10.1016/j.jneumeth.2017.12.010},
issn = {1872678X},
journal = {J. Neurosci. Methods},
keywords = {ADNI,Alzheimer's disease,Classification,Mild cognitive impairment,Multi-class,Neuroimaging,Random forest},
mendeley-groups = {PhDThesis/Review},
pages = {236141},
pmid = {29269320},
publisher = {Cold Spring Harbor Laboratory},
title = {{Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer's disease patients: From the alzheimer's disease neuroimaging initiative (ADNI) data}},
year = {2018}
}
@article{Dodge2014,
abstract = {Background It is unknown which commonly used Alzheimer disease (AD) biomarker values - baseline or progression - best predict longitudinal cognitive decline. Methods 526 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). ADNI composite memory and executive scores were the primary outcomes. Individual-specific slope of the longitudinal trajectory of each biomarker was first estimated. These estimates and observed baseline biomarker values were used as predictors of cognitive declines. Variability in cognitive declines explained by baseline biomarker values was compared with variability explained by biomarker progression values. Results About 40{\%} of variability in memory and executive function declines was explained by ventricular volume progression among mild cognitive impairment patients. A total of 84{\%} of memory and 65{\%} of executive function declines were explained by fluorodeoxyglucose positron emission tomography (FDG-PET) score progression and ventricular volume progression, respectively, among AD patients. Conclusions For most biomarkers, biomarker progressions explained higher variability in cognitive decline than biomarker baseline values. This has important implications for clinical trials targeted to modify AD biomarkers.},
annote = {Study about progression of the disease. It indicates that progression biomarkers are better at characterizing some cognitive scores than baseline biomarkers.},
author = {Dodge, Hiroko H and Zhu, Jian and Harvey, Danielle and Saito, Naomi and Silbert, Lisa C and Kaye, Jeffrey A and Koeppe, Robert A and Albin, Roger L},
doi = {10.1016/j.jalz.2014.04.513},
isbn = {1552-5260},
issn = {15525279},
journal = {Alzheimer's Dement.},
keywords = {ADNI,ADNI-exe,ADNI-mem,Biomarker,Biomarker progressions,Cognitive declines,FDG-PET,MCI,MRI volume},
mendeley-groups = {PhDThesis/Review},
number = {6},
pages = {690--703},
pmid = {25022534},
title = {{Biomarker progressions explain higher variability in stage-specific cognitive decline than baseline values in Alzheimer disease}},
volume = {10},
year = {2014}
}
@article{Donohue14,
abstract = {Motivation Diseases that progress slowly are often studied by observing cohorts at different stages of disease for short periods of time. The Alzheimer's Disease Neuroimaging Initiative (ADNI) follows elders with various degrees of cognitive impairment, from normal to impaired. The study includes a rich panel of novel cognitive tests, biomarkers, and brain images collected every 6 months for as long as 6 years. The relative timing of the observations with respect to disease pathology is unknown. We propose a general semiparametric model and iterative estimation procedure to estimate simultaneously the pathological timing and long-term growth curves. The resulting estimates of long-term progression are fine-tuned using cognitive trajectories derived from the long-term "Personnes Ag??es Quid" study. Results We demonstrate with simulations that the method can recover long-term disease trends from short-term observations. The method also estimates temporal ordering of individuals with respect to disease pathology, providing subject-specific prognostic estimates of the time until onset of symptoms. When the method is applied to ADNI data, the estimated growth curves are in general agreement with prevailing theories of the Alzheimer's disease cascade. Other data sets with common outcome measures can be combined using the proposed algorithm. Availability Software to fit the model and reproduce results with the statistical software R is available as the grace package. ADNI data can be downloaded from the Laboratory of NeuroImaging.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Donohue, Michael C and Jacqmin-Gadda, Helenne and {Le Goff}, M{\'{e}}lanie and Thomas, Ronald G and Raman, Rema and Gamst, Anthony C and Beckett, Laurel A and Jack, Clifford R and Weiner, Michael W and Dartigues, Jean Francois and Aisen, Paul S},
journal = {Alzheimer's Dement.},
doi = {10.1016/j.jalz.2013.10.003},
eprint = {NIHMS150003},
isbn = {8585348585},
issn = {15525279},
keywords = {Growth curves,Multiple outcomes,Progression curves,Self-modeling regression,Semiparametric regression},
mendeley-groups = {PhDThesis/Review},
number = {5},
pages = {S400----S410},
pmid = {24656849},
title = {{Estimating long-term multivariate progression from short-term data}},
volume = {10},
year = {2014}
}


@article{Farzan2011,
abstract = {Diagnosing Alzheimer's disease through MRI neuroimaging biomarkers has been used as a complementary marker for traditional clinical markers to improve diagnostic accuracy and also help in developing new pharmacotherapeutic trials. It has been revealed that longitudinal analysis of the whole brain atrophy has the power of discriminating Alzheimer's disease and elderly normal controls. In this work, effect of involving intermediate atrophy rates and impact of using uncorrelated principal components of these features instead of original ones on discriminating normal controls and Alzheimer's disease subjects, is inspected. In fact, linear discriminative analysis of atrophy rates is used to classify subjects into Alzheimer's disease and controls. Leave-one-out cross-validation has been adopted to evaluate the generalization rate of the classifier along with its memorization. Results show that incorporating uncorrelated version of intermediate features leads to the same memorization performance as the original ones but higher generalization rate. As a conclusion, it is revealed that in a longitudinal study, using intermediate MRI scans and transferring them to an uncorrelated feature space can improve diagnostic accuracy.},
annote = {IS STATISTICAL},
author = {Farzan, Ali and Mashohor, Syamsiah and Ramli, Rahman and Mahmud, Rozi},
doi = {10.1186/1746-1596-6-105},
issn = {1746-1596 (Electronic)},
journal = {Diagn. Pathol.},
keywords = { Theoretical,Aged,Alzheimer Disease,Atrophy,Brain,Discriminant Analysis,Disease Progression,Female,Humans,Longitudinal Studies,Male,Models,Principal Component Analysis,ROC Curve,Theoretical,pathology},
mendeley-groups = {PhDThesis/Review},
month = {oct},
pages = {105},
pmid = {22035255},
title = {{Discriminant analysis of intermediate brain atrophy rates in longitudinal diagnosis of Alzheimer's disease.}},
volume = {6},
year = {2011}
}
@article{Farzan2015,
abstract = {Objective: Boosting accuracy in automatically discriminating patients with Alzheimer's disease (AD) and normal controls (NC), based on multidimensional classification of longitudinal whole brain atrophy rates and their intermediate counterparts in analyzing magnetic resonance images (MRI). Method: Longitudinal percentage of brain volume changes (PBVC) in two-year follow up and its intermediate counterparts in early 6-month and late 18-month are used as features in supervised and unsupervised classification procedures based on K-mean, fuzzy clustering method (FCM) and support vector machine (SVM). The most relevant features for classification are selected using discriminative analysis (DA) of features and their principal components (PC). Accuracy of the proposed method is evaluated in a group of 30 patients with AD (16 males, 14 females, age. ±. standard-deviation (SD). =. 75. ±. 1.36 years) and 30 normal controls (15 males, 15 females, age. ±. SD. =. 77. ±. 0.88 years) using leave-one-out cross-validation. Results: Results indicate superiority of supervised machine learning techniques over unsupervised ones in diagnosing AD and withal, predominance of RBF kernel over lineal one. Accuracies of 83.3{\%}, 83.3{\%}, 90{\%} and 91.7{\%} are achieved in classification by K-mean, FCM, linear SVM and SVM with radial based function (RBF) respectively. Conclusion: Evidence that SVM classification of longitudinal atrophy rates may results in high accuracy is given. Additionally, it is realized that use of intermediate atrophy rates and their principal components improves diagnostic accuracy.},
author = {Farzan, Ali and Mashohor, Syansiah and Ramli, Abd Rahman and Mahmud, Rozi},
doi = {10.1016/j.bbr.2015.04.010},
isbn = {0166-4328},
issn = {18727549},
journal = {Behav. Brain Res.},
keywords = {Alzheimer's disease,Diagnostic,FCM,Longitudinal atrophy,MRI,SVM},
mendeley-groups = {PhDThesis/Review},
pages = {124--130},
pmid = {25889456},
publisher = {Elsevier},
title = {{Boosting diagnosis accuracy of Alzheimer's disease using high dimensional recognition of longitudinal brain atrophy patterns}},
volume = {290},
year = {2015}
}
@article{Fiorini2016,
abstract = {Multiple Sclerosis is a degenerative condition of the central nervous system that affects nearly 2.5 million of individuals in terms of their physical, cognitive, psychological and social capabilities. Researchers are currently investigating on the use of patient reported outcome measures for the assessment of impact and evolution of the disease on the life of the patients. To date, a clear understanding on the use of such measures to predict the evolution of the disease is still lacking. In this work we resort to regularized machine learning methods for binary classification and multiple output regression. We propose a pipeline that can be used to predict the disease progression from patient reported measures. The obtained model is tested on a data set collected from an ongoing clinical research project.},
annote = {NOT ALZHEIMER, NOT DEMENTIA},
archivePrefix = {arXiv},
arxivId = {1612.00615},
author = {Fiorini, Samuele and Tacchino, Andrea and Brichetto, Giampaolo and Verri, Alessandro and Barla, Annalisa},
eprint = {1612.00615},
mendeley-groups = {PhDThesis/Review},
title = {{A temporal model for multiple sclerosis course evolution}},
year = {2016}
}
@article{Fiot2012,
abstract = {In the context of Alzheimer's disease (AD), state-of-the-art methods separating normal control (NC) from AD patients or CN from progressive MCI (mild cognitive impairment patients converting to AD) achieve decent classification rates. However, they all perform poorly at separating stable MCI (MCI patients not converting to AD) and progressive MCI. Instead of using features extracted from a single temporal point, we address this problem using descriptors of the hippocampus evolutions between two time points. To encode the transformation, we use the framework of large deformations by diffeomorphisms that provides geodesic evolutions. To perform statistics on those local features in a common coordinate system, we introduce an extension of the K{\"{a}}rcher mean algorithm that defines the template modulo rigid registrations, and an initialization criterion that provides a final template leading to better matching with the patients. Finally, as local descriptors transported to this template do not directly perform as well as global descriptors (e.g. volume difference), we propose a novel strategy combining the use of initial momentum from geodesic shooting, extended K{\"{a}}rcher algorithm, density transport and integration on a hippocampus subregion, which is able to outperform global descriptors. {\textcopyright}2012 Springer-Verlag.},
author = {Fiot, Jean Baptiste and Risser, Laurent and Cohen, Laurent D and Fripp, Jurgen and Vialard, Fran{\c{c}}ois Xavier},
doi = {10.1007/978-3-642-33555-6_2},
isbn = {9783642335549},
issn = {03029743},
journal = {Lect. Notes Comput. Sci.},
keywords = {Alzheimer's disease,Brain imaging,K{\"{a}}rcher mean,geodesic shooting,population analysis,time-series image data},
mendeley-groups = {PhDThesis/Review},
pages = {13--24},
title = {{Local vs global descriptors of hippocampus shape evolution for Alzheimer's longitudinal population analysis}},
volume = {7570},
year = {2012}
}
@article{Fiot2014,
abstract = {In the context of Alzheimer's disease, two challenging issues are (1) the characterization of local hippocampal shape changes specific to disease progression and (2) the identification of mild-cognitive impairment patients likely to convert. In the literature, (1) is usually solved first to detect areas potentially related to the disease. These areas are then considered as an input to solve (2). As an alternative to this sequential strategy, we investigate the use of a classification model using logistic regression to address both issues (1) and (2) simultaneously. The classification of the patients therefore does not require any a priori definition of the most representative hippocampal areas potentially related to the disease, as they are automatically detected. We first quantify deformations of patients' hippocampi between two time points using the large deformations by diffeomorphisms framework and transport these deformations to a common template. Since the deformations are expected to be spatially structured, we perform classification combining logistic loss and spatial regularization techniques, which have not been explored so far in this context, as far as we know. The main contribution of this paper is the comparison of regularization techniques enforcing the coefficient maps to be spatially smooth (Sobolev), piecewise constant (total variation) or sparse (fused LASSO) with standard regularization techniques which do not take into account the spatial structure (LASSO, ridge and ElasticNet). On a dataset of 103 patients out of ADNI, the techniques using spatial regularizations lead to the best classification rates. They also find coherent areas related to the disease progression.},
author = {Fiot, Jean-Baptiste and Raguet, Hugo and Risser, Laurent and Cohen, Laurent D and Fripp, Jurgen and Vialard, Francois-Xavier},
doi = {10.1016/j.nicl.2014.02.002},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {2213-1582 (Print)},
journal = {NeuroImage. Clin.},
keywords = { Computer-Assisted, Factual, Neurological,Alzheimer Disease,Cognitive Dysfunction,Databases,Disease Progression,Hippocampus,Humans,Image Processing,Logistic Models,Magnetic Resonance Imaging,Models,pathology,physiopathology,statistics {\&} numerical data},
mendeley-groups = {PhDThesis/Review},
pages = {718--729},
pmid = {24936423},
title = {{Longitudinal deformation models, spatial regularizations and learning strategies to quantify Alzheimer's disease progression.}},
volume = {4},
year = {2014}
}
@article{Firth2018,
abstract = {Dementia is characterised by its progressive degeneration of cognitive abilities. In research cohorts, detailed neuropsychological test batteries are often administered to better understand how cognition changes over time. Understanding cognitive changes in dementia is of great importance, particularly in determining how structural changes in the brain may affect cognition and in facilitating earlier detection of symptomatic changes. Disease progression models are often applied to these data to understand how a disease changes over time from cross-sectional data or to disease trajectories from large numbers of individuals. Previous disease progression models used to build longitudinal models from cross-sectional data have focused on brain imaging data; however, these models are not directly applicable to cognitive data. Here we use the novel, non-parametric, Kernel Density Estimation Mixture Modelling (KDEMM) approach and demonstrate accurate modelling of the progression of cognitive test data. We found that using KDEMM resulted in more accurate models of disease progression in simulated data compared to Gaussian Mixture Models (GMMs) for the majority of parameters used to simulate the data. When comparing KDEMM and GMM to cognitive data collected in different Alzheimer's Disease subtypes, we found the KDEMM resulted in a model much more in line with clinical phenotype. We anticipate that the KDEMM will be used to integrate cognitive test data, and other non-normally distributed datasets into complex disease progression models.},
annote = {Extension of event based models

NOT LONGITUDINAL},
author = {Firth, Nicholas C and Oxtoby, Neil P and Primativo, Silvia and Brotherhood, Emily and Young, Alexandra L and Yong, Keir X X and Crutch, Sebastian J and Alexander, Daniel C},
doi = {10.1101/297978},
journal = {bioRxiv},
mendeley-groups = {PhDThesis/Review},
pages = {297978},
publisher = {Cold Spring Harbor Laboratory},
title = {{Non-Parametric Mixture Modelling and its Application to Disease Progression Modelling}},
year = {2018}
}
@article{Fitzmaurice2008,
abstract = {L ongitudinal data, comprising repeated measurements of the same individuals over time, arise frequently in cardiology and the biomedical sciences in general. For example, Frison and Pocock 1 used repeated measurements of the liver enzyme creatine kinase in serum of cardiac patients to study changes in liver function over a 12-month study period. The main goal, indeed the raison d'{\^{e}}tre, of a longi-tudinal study is characterization of changes in the response of interest over time. Ordinarily, changes in the response are also related to selected covariates. For example, Frison and Pocock 1 compared changes in creatine kinase between pa-tients randomized to active drug and placebo. The past 25 years have witnessed remarkable develop-ments in statistical methods for the analysis of longitudinal data. Despite these important advances, researchers in the biomedical sciences have been somewhat slow to adopt these methods and often rely on statistical techniques that fail to adequately account for longitudinal study designs. The goal of the present report is to provide an overview of some recently developed methods for longitudinal analyses that are more appropriate, with a focus on 2 methods for continuous responses: the analysis of response profiles and linear mixed-effects models. The analysis of response profiles is better suited to settings with a relatively small number of repeated measurements, obtained on a common set of occasions, whereas linear mixed-effects models are suitable in more general settings. Before describing these methods, we review some of the defining features of longitudinal studies and highlight the main aspects of longitudinal data that compli-cate their analysis. A common feature of repeated measurements on an individ-ual is correlation; that is, knowledge of the value of the response on one occasion provides information about the likely value of the response on a future occasion. Another common feature of longitudinal data is heterogeneous vari-ability; that is, the variance of the response changes over the duration of the study. These 2 features of longitudinal data violate the fundamental assumptions of independence and homogeneity of variance that are at the basis of many standard techniques (eg, t test, ANOVA, and multiple linear regression). To account for these features, statistical models for longitudinal data have 2 main components: a model for the covariance among repeated measures, coupled with a model for the mean response and its dependence on covari-ates (eg, treatment group in the context of clinical trials). By the term " covariance, " we mean both the correlations among pairs of repeated measures on an individual and the variabil-ity of the responses on different occasions (conversely, correlation can be interpreted as the standardized covariance). Although the main scientific interest is normally focused on the model for the mean response, inferences about change in the response and its relation to covariates are sensitive to the chosen model for the covariance among the repeated mea-sures. Failure to properly account for the covariance results in hypothesis tests and CIs that are invalid and may result in misleading inferences.},
annote = {Description of longitudinal stadistics tests},
author = {Fitzmaurice, Garrett M and Ravichandran, Caitlin},
doi = {10.1161/CIRCULATIONAHA.107.714618},
isbn = {9780761960270},
issn = {00097322},
journal = {Circulation},
keywords = {Statistical linear models data collection,Statistics as topic data interpretation},
mendeley-groups = {PhDThesis/Review},
number = {19},
pages = {2005--2010},
pmid = {18981315},
title = {{A primer in longitudinal data analysis}},
volume = {118},
year = {2008}
}
@article{Fonteijn2012,
abstract = {Understanding the progression of neurological diseases is vital for accurate and early diagnosis and treatment planning. We introduce a new characterization of disease progression, which describes the disease as a series of events, each comprising a significant change in patient state. We provide novel algorithms to learn the event ordering from heterogeneous measurements over a whole patient cohort and demonstrate using combined imaging and clinical data from familial Alzheimer's and Huntington's disease cohorts. Results provide new detail in the progression pattern of these diseases, while confirming known features, and give unique insight into the variability of progression over the cohort. The key advantage of the new model and algorithms over previous progression models is that they do not require a priori division of the patients into clinical stages. The model and its formulation extend naturally to a wide range of other diseases and developmental processes and accommodate cross-sectional and longitudinal input data. {\textcopyright}2012 Elsevier Inc.},
author = {Fonteijn, Hubert M and Modat, Marc and Clarkson, Matthew J and Barnes, Josephine and Lehmann, Manja and Hobbs, Nicola Z and Scahill, Rachael I and Tabrizi, Sarah J and Ourselin, Sebastien and Fox, Nick C and Alexander, Daniel C},
doi = {10.1016/j.neuroimage.2012.01.062},
isbn = {10538119},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Disease progression,Huntington's disease,MRI},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {1880--1889},
pmid = {22281676},
title = {{An event-based model for disease progression and its application in familial Alzheimer's disease and Huntington's disease}},
volume = {60},
year = {2012}
}
@article{Franke2010,
abstract = {The early identification of brain anatomy deviating from the normal pattern of growth and atrophy, such as in Alzheimer's disease (AD), has the potential to improve clinical outcomes through early intervention. Recently, Davatzikos et al. (2009) supported the hypothesis that pathologic atrophy in AD is an accelerated aging process, implying accelerated brain atrophy. In order to recognize faster brain atrophy, a model of healthy brain aging is needed first. Here, we introduce a framework for automatically and efficiently estimating the age of healthy subjects from their T1-weighted MRI scans using a kernel method for regression. This method was tested on over 650 healthy subjects, aged 19-86??years, and collected from four different scanners. Furthermore, the influence of various parameters on estimation accuracy was analyzed. Our age estimation framework included automatic preprocessing of the T1-weighted images, dimension reduction via principal component analysis, training of a relevance vector machine (RVM; Tipping, 2000) for regression, and finally estimating the age of the subjects from the test samples. The framework proved to be a reliable, scanner-independent, and efficient method for age estimation in healthy subjects, yielding a correlation of r = 0.92 between the estimated and the real age in the test samples and a mean absolute error of 5??years. The results indicated favorable performance of the RVM and identified the number of training samples as the critical factor for prediction accuracy. Applying the framework to people with mild AD resulted in a mean brain age gap estimate (BrainAGE) score of + 10??years. ?? 2010 Elsevier Inc. All rights reserved.},
annote = {1. One day have to create small bibliography on Alzheimer's disease

BrainAGE related Paper},
author = {Franke, Katja and Ziegler, Gabriel and Kl{\"{o}}ppel, Stefan and Gaser, Christian},
doi = {10.1016/j.neuroimage.2010.01.005},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Aging,Brain disease,MRI,Regression,Relevance vector machines (RVM),Support vector machines (SVM)},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {883--892},
pmid = {20070949},
title = {{Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: Exploring the influence of various parameters}},
volume = {50},
year = {2010}
}
@article{franko,
abstract = {Alzheimer's disease (AD) is characterized by neurofibrillary tangle and neuropil thread deposition, which ultimately results in neuronal loss. A large number of magnetic resonance imaging studies have reported a smaller hippocampus in AD patients as compared to healthy elderlies. Even though this difference is often interpreted as atrophy, it is only an indirect measurement. A more direct way of measuring the atrophy is to use repeated MRIs within the same individual. Even though several groups have used this appropriate approach, the pattern of hippocampal atrophy still remains unclear and difficult to relate to underlying pathophysiology. Here, in this longitudinal study, we aimed to map hippocampal atrophy rates in patients with AD, mild cognitive impairment (MCI) and elderly controls. Data consisted of two MRI scans for each subject. The symmetric deformation field between the first and the second MRI was computed and mapped onto the three-dimensional hippocampal surface. The pattern of atrophy rate was similar in all three groups, but the rate was significantly higher in patients with AD than in control subjects. We also found higher atrophy rates in progressive MCI patients as compared to stable MCI, particularly in the antero-lateral portion of the right hippocampus. Importantly, the regions showing the highest atrophy rate correspond to those that were described to have the highest burden of tau deposition. Our results show that local hippocampal atrophy rate is a reliable biomarker of disease stage and progression and could also be considered as a method to objectively evaluate treatment effects.},
annote = {Paper not focused on diagnostic, but in probabilistic study of atrophy rate in the hippocampus.

Longitudinal.

statistical},
author = {Frank{\'{o}}, Edit and Joly, Olivier},
doi = {10.1371/journal.pone.0071354},
isbn = {1932-6203 (Electronic)$\backslash$r1932-6203 (Linking)},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Review},
number = {8},
pmid = {23951142},
title = {{Evaluating Alzheimer's Disease Progression Using Rate of Regional Hippocampal Atrophy}},
volume = {8},
year = {2013}
}
@article{Gamberger2017,
abstract = {The heterogeneity of Alzheimer's disease contributes to the high failure rate of prior clinical trials. We analyzed 5-year longitudinal outcomes and biomarker data from 562 subjects with mild cognitive impairment (MCI) from two national studies (ADNI) using a novel multilayer clustering algorithm. The algorithm identified homogenous clusters of MCI subjects with markedly different prognostic cognitive trajectories. A cluster of 240 rapid decliners had 2-fold greater atrophy and progressed to dementia at almost 5 times the rate of a cluster of 184 slow decliners. A classifier for identifying rapid decliners in one study showed high sensitivity and specificity in the second study. Characterizing subgroups of at risk subjects, with diverse prognostic outcomes, may provide novel mechanistic insights and facilitate clinical trials of drugs to delay the onset of AD.},
author = {Gamberger, Dragan and Lavra{\v{c}}, Nada and Srivatsa, Shantanu and Tanzi, Rudolph E and Doraiswamy, P Murali},
doi = {10.1038/s41598-017-06624-y},
isbn = {4159801706},
issn = {20452322},
journal = {Sci. Rep.},
keywords = {Biomarkers,Medical research},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {6763},
pmid = {28755001},
publisher = {Nature Publishing Group},
title = {{Identification of clusters of rapid and slow decliners among subjects at risk for Alzheimer's disease}},
volume = {7},
year = {2017}
}
@article{Gaser2013,
abstract = {Alzheimer's disease (AD), the most common form of dementia, shares many aspects of abnormal brain aging. We present a novel magnetic resonance imaging (MRI)-based biomarker that predicts the individual progression of mild cognitive impairment (MCI) to AD on the basis of pathological brain aging patterns. By employing kernel regression methods, the expression of normal brain-aging patterns forms the basis to estimate the brain age of a given new subject. If the estimated age is higher than the chronological age, a positive brain age gap estimation (BrainAGE) score indicates accelerated atrophy and is considered a risk factor for conversion to AD. Here, the BrainAGE framework was applied to predict the individual brain ages of 195 subjects with MCI at baseline, of which a total of 133 developed AD during 36 months of follow-up (corresponding to a pre-test probability of 68{\%}). The ability of the BrainAGE framework to correctly identify MCI-converters was compared with the performance of commonly used cognitive scales, hippocampus volume, and state-of-the-art biomarkers derived from cerebrospinal fluid (CSF). With accuracy rates of up to 81{\%}, BrainAGE outperformed all cognitive scales and CSF biomarkers in predicting conversion of MCI to AD within 3 years of follow-up. Each additional year in the BrainAGE score was associated with a 10{\%} greater risk of developing AD (hazard rate: 1.10 [CI: 1.07-1.13]). Furthermore, the post-test probability was increased to 90{\%} when using baseline BrainAGE scores to predict conversion to AD. The presented framework allows an accurate prediction even with multicenter data. Its fast and fully automated nature facilitates the integration into the clinical workflow. It can be exploited as a tool for screening as well as for monitoring treatment options.},
annote = {-Kernel regression methods

-Age prediction

-CerebroSpinalFluid (CSF) seems to be the state of the art.

- Not directly longitudinal},
author = {Gaser, Christian and Franke, Katja and Kl{\"{o}}ppel, Stefan and Koutsouleris, Nikolaos and Sauer, Heinrich},
doi = {10.1371/journal.pone.0067346},
isbn = {1932-6203 (electronic)},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Review},
number = {6},
pmid = {23826273},
title = {{BrainAGE in Mild Cognitive Impaired Patients: Predicting the Conversion to Alzheimer's Disease}},
volume = {8},
year = {2013}
}
@article{Gavidia-Bovadilla2017,
abstract = {Incipient Alzheimer's Disease (AD) is characterized by a slow onset of clinical symptoms, with pathological brain changes starting several years earlier. Consequently, it is necessary to first understand and differentiate age-related changes in brain regions in the absence of disease, and then to support early and accurate AD diagnosis. However, there is poor understanding of the initial stage of AD; seemingly healthy elderly brains lose matter in regions related to AD, but similar changes can also be found in non-demented subjects having mild cognitive impairment (MCI). By using a Linear Mixed Effects approach, we modelled the change of 166 Magnetic Resonance Imaging (MRI)-based biomarkers available at a 5-year follow up on healthy elderly control (HC, n = 46) subjects. We hypothesized that, by identifying their significant variant (vr) and quasi-variant (qvr) brain regions over time, it would be possible to obtain an age-based null model, which would characterize their normal atrophy and growth patterns as well as the correlation between these two regions. By using the null model on those subjects who had been clinically diagnosed as HC (n = 161), MCI (n = 209) and AD (n = 331), normal age-related changes were estimated and deviation scores (residuals) from the observed MRI-based biomarkers were computed. Subject classification, as well as the early prediction of conversion to MCI and AD, were addressed through residual-based Support Vector Machines (SVM) modelling. We found reductions in most cortical volumes and thicknesses (with evident gender differences) as well as in sub-cortical regions, including greater atrophy in the hippocampus. The average accuracies (ACC) recorded for men and women were: AD-HC: 94.11{\%}, MCI-HC: 83.77{\%} and MCI converted to AD (cAD)-MCI non-converter (sMCI): 76.72{\%}. Likewise, as compared to standard clinical diagnosis methods, SVM classifiers predicted the conversion of cAD to be 1.9 years earlier for females (ACC:72.5{\%}) and 1.4 years earlier for males (ACC:69.0{\%}).},
author = {Gavidia-Bovadilla, Giovana and Kanaan-Izquierdo, Samir and Matar{\'{o}}-Serrat, Mar{\'{i}}a and Perera-Lluna, Alexandre},
doi = {10.1371/journal.pone.0168011},
editor = {Chen, Kewei},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1932-6203},
journal = {PLoS One},
keywords = {80 and over,Aged,Alzheimer Disease,Amyloid beta-Peptides,Atrophy,Biomarkers,Brain,Case-Control Studies,Cohort Studies,Female,Hippocampus,Humans,Magnetic Resonance Imaging,Male,Middle Aged,Reproducibility of Results,Sex Factors,Support Vector Machine,cerebrospinal fluid,diagnostic imaging,pathology},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {e0168011},
pmid = {28045907},
title = {{Early Prediction of Alzheimer's Disease Using Null Longitudinal Model-Based Classifiers}},
volume = {12},
year = {2017}
}
@article{Givon2017,
abstract = {Accurate diagnosis of Alzheimer's Disease (AD) entails clinical evaluation of multiple cognition metrics and biomarkers. Metrics such as the Alzheimer's Disease Assessment Scale - Cognitive test (ADAS-cog) comprise multiple subscores that quantify different aspects of a patient's cognitive state such as learning, memory, and language production/comprehension. Although computer-aided diagnostic techniques for classification of a patient's current disease state exist, they provide little insight into the relationship between changes in brain structure and different aspects of a patient's cognitive state that occur over time in AD. We have developed a Convolutional Neural Network architecture that can concurrently predict the trajectories of the 13 subscores comprised by a subject's ADAS-cog examination results from a current minimally preprocessed structural MRI scan up to 36 months from image acquisition time without resorting to manual feature extraction. Mean performance metrics are within range of those of existing techniques that require manual feature selection and are limited to predicting aggregate scores.},
annote = {From Duplicate 1 (Cognitive Subscore Trajectory Prediction in Alzheimer's Disease - Givon, Lev E; Mariano, Laura J; O'Dowd, David; Irvine, John M; Schneider, Abraham R)

CNN por prediction in time.

interesting method to incorporate time.},
archivePrefix = {arXiv},
arxivId = {1706.08491},
author = {Givon, Lev E and Mariano, Laura J and O'Dowd, David and Irvine, John M and Schneider, Abraham R},
eprint = {1706.08491},
journal = {ArXiv},
mendeley-groups = {PhDThesis/Review},
month = {jun},
title = {{Cognitive Subscore Trajectory Prediction in Alzheimer's Disease}},
year = {2017}
}
@article{Gonen2011,
abstract = {In recent years, several methods have been proposed to combine multiple kernels instead of using a single one. These different kernels may correspond to using different notions of similarity or may be using information coming from multiple sources (different representations or different feature subsets). In trying to organize and highlight the similarities and differences between them, we give a taxonomy of and review several multiple kernel learning algorithms. We perform experiments on real data sets for better illustration and comparison of existing algorithms. We see that though there may not be large differences in terms of accuracy, there is difference between them in complexity as given by the number of stored support vectors, the sparsity of the solution as given by the number of used kernels, and training time complexity. We see that overall, using multiple kernels instead of a single one is useful and believe that combining kernels in a nonlinear or data-dependent way seems more promising than linear combination in fusing information provided by simple linear kernels, whereas linear methods are more reasonable when combining complex Gaussian kernels.},
author = {G{\"{o}}nen, Mehmet and Alpaydın, Ethem},
isbn = {1532-4435},
issn = {15324435},
journal = {J. Mach. Learn. Res.},
keywords = {kernel machines,multiple kernel learning,support vector machines},
mendeley-groups = {PhDThesis/Review},
pages = {2211--2268},
title = {{Multiple Kernel Learning Algorithms}},
volume = {12},
year = {2011}
}
@article{Goyal2018,
abstract = {Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogeneous in their clinical presentation. Patients may progress through disease stages at varying rates. This leads to pathophysiological misalignment over time, making it difficult to consistently compare patients in a clinically meaningful way. Furthermore, patients present clinically for the first time at different stages of disease. This eliminates the possibility of simply aligning patients based on their initial presentation. Finally, patient data may be sampled at different rates due to differences in schedules or missed visits. To address these challenges, we propose a robust measure of patient similarity based on subsequence alignment. Compared to global alignment techniques that do not account for pathophysiological misalignment, focusing on the most relevant subsequences allows for an accurate measure of similarity between patients. We demonstrate the utility of our approach in settings where longitudinal data, while useful, are limited and lack a clear temporal alignment for comparison. Applied to the task of stratifying patients for risk of progression to probable Alzheimer's Disease, our approach outperforms models that use only snapshot data (AUROC of 0.839 vs. 0.812) and models that use global alignment techniques (AUROC of 0.822). Our results support the hypothesis that patients' trajectories are useful for quantifying inter-patient similarities and that using subsequence matching and can help account for heterogeneity and misalignment in longitudinal data.},
archivePrefix = {arXiv},
arxivId = {1803.00744},
author = {Goyal, Dev and Syed, Zeeshan and Wiens, Jenna},
doi = {arXiv:1803.00744v1},
eprint = {1803.00744},
journal = {ArXiv},
mendeley-groups = {PhDThesis/Review},
month = {mar},
title = {{Clinically Meaningful Comparisons Over Time: An Approach to Measuring Patient Similarity based on Subsequence Alignment}},
year = {2018}
}
@article{Goyal2018b,
abstract = {Introduction Models characterizing intermediate disease stages of Alzheimer's disease (AD) are needed to inform clinical care and prognosis. Current models, however, use only a small subset of available biomarkers, capturing only coarse changes along the complete spectrum of disease progression. We propose the use of machine learning techniques and clinical, biochemical, and neuroimaging biomarkers to characterize progression to AD. Methods We used a large multimodal longitudinal data set of biomarkers and demographic and genotype information from 1624 participants from the Alzheimer's Disease Neuroimaging Initiative. Using hidden Markov models, we characterized intermediate disease stages. We validated inferred disease trajectories by comparing time to first clinical AD diagnosis. We trained an L2-regularized logistic regression model to predict disease trajectory and evaluated its discriminative performance on a test set. Results We identified 12 distinct disease states. Progression to AD occurred most often through one of two possible paths through these states. Paths differed in terms of rate of disease progression (by 5.44 years on average), amyloid and total-tau (t-tau) burden (by 10{\%} and 69{\%}, respectively), and hippocampal neurodegeneration (P {\textless}.001). On the test set, the predictive model achieved an area under the receiver operating characteristic curve of 0.85. Discussion Progression to AD, in terms of biomarker trajectories, can be predicted based on participant-specific factors. Such disease staging tools could help in targeting high-risk patients for therapeutic intervention trials. As longitudinal data with richer features are collected, such models will help increase our understanding of the factors that drive the different trajectories of AD.},
author = {Goyal, Devendra and Tjandra, Donna and Migrino, Raymond Q and Giordani, Bruno and Syed, Zeeshan and Wiens, Jenna},
doi = {https://doi.org/10.1016/j.dadm.2018.06.007},
issn = {2352-8729},
journal = {Alzheimer's Dement. Diagnosis, Assess. Dis. Monit.},
keywords = {Biomarkers,Longitudinal,Machine learning,Staging,Trajectory},
mendeley-groups = {PhDThesis/Review},
pages = {629--637},
title = {{Characterizing heterogeneity in the progression of Alzheimer's disease using longitudinal clinical and neuroimaging biomarkers}},
volume = {10},
year = {2018}
}
@article{Gray2012,
abstract = {Imaging biomarkers for Alzheimer's disease are desirable for improved diagnosis and monitoring, as well as drug discovery. Automated image-based classification of individual patients could provide valuable diagnostic support for clinicians, when considered alongside cognitive assessment scores. We investigate the value of combining cross-sectional and longitudinal multi-region FDG-PET information for classification, using clinical and imaging data from the Alzheimer's Disease Neuroimaging Initiative. Whole-brain segmentations into 83 anatomically defined regions were automatically generated for baseline and 12-month FDG-PET images. Regional signal intensities were extracted at each timepoint, as well as changes in signal intensity over the follow-up period. Features were provided to a support vector machine classifier. By combining 12-month signal intensities and changes over 12. months, we achieve significantly increased classification performance compared with using any of the three feature sets independently. Based on this combined feature set, we report classification accuracies of 88{\%} between patients with Alzheimer's disease and elderly healthy controls, and 65{\%} between patients with stable mild cognitive impairment and those who subsequently progressed to Alzheimer's disease. We demonstrate that information extracted from serial FDG-PET through regional analysis can be used to achieve state-of-the-art classification of diagnostic groups in a realistic multi-centre setting. This finding may be usefully applied in the diagnosis of Alzheimer's disease, predicting disease course in individuals with mild cognitive impairment, and in the selection of participants for clinical trials. ?? 2012 Elsevier Inc.},
annote = {From Duplicate 1 (Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease - Gray, Katherine R; Wolz, Robin; Heckemann, Rolf A; Aljabar, Paul; Hammers, Alexander; Rueckert, Daniel)

- Main method
Feature selection on FDG-PET, 1 2months change.
- Type of problem to solve
Classification CN/MCI/AD
- Small evaluation: Machine learning or statistics?

Machine learning, SVM using diferent feuatres and accounting to},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Gray, Katherine R and Wolz, Robin and Heckemann, Rolf A and Aljabar, Paul and Hammers, Alexander and Rueckert, Daniel},
doi = {10.1016/j.neuroimage.2011.12.071},
eprint = {NIHMS150003},
institution = {Alzheimer's Disease Neuroimaging Initiative},
isbn = {1095-9572 (Electronic)$\backslash$n1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Aged,Alzheimer Disease,Alzheimer's disease,Classification,Female,Fluorodeoxyglucose F18,Humans,Image segmentation,Longitudinal analysis,Male,Mild cognitive impairment,Positron-Emission Tomography,Radiopharmaceuticals,[18F]fluorodeoxyglucose positron emission tomograp,classification,diagnostic imaging,image segmentation,longitudinal analysis,methods,mild cognitive impairment},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {1},
pages = {221--229},
pmid = {22236449},
title = {{Multi-region analysis of longitudinal FDG-PET for the classification of Alzheimer's disease}},
volume = {60},
year = {2012}
}
@article{Grydeland2013,
abstract = {Brain morphometry measures derived from magnetic resonance imaging (MRI) are important biomarkers for Alzheimer's disease (AD). The objective of the present study was to test whether we could improve morphometry-based detection and prediction of disease state by use of white matter/gray matter (WM/GM) signal intensity contrast obtained from conventional MRI scans. We hypothesized that including WM/GM contrast change along with measures of atrophy in the entorhinal cortex and the hippocampi would yield better classification of AD patients, and more accurate prediction of early disease progression. T1 -weighted MRI scans from two sessions approximately 2 years apart from 78 participants with AD (Clinical Dementia Rating (CDR) = 0.5-2) and 71 age-matched controls were used to calculate annual change rates. Results showed that WM/GM contrast decay was larger in AD compared with controls in the medial temporal lobes. For the discrimination between AD and controls, entorhinal WM/GM contrast decay contributed significantly when included together with decrease in entorhinal cortical thickness and hippocampal volume, and increased the area under the curve to 0.79 compared with 0.75 when using the two morphometric variables only. Independent effects of WM/GM contrast decay and improved classification were also observed for the CDR-based subgroups, including participants converting from either a non-AD status to very mild AD, or from very mild to mild AD. Thus, WM/GM contrast decay increased diagnostic accuracy beyond what was obtained by well-validated morphometric measures alone. The findings suggest that signal intensity properties constitute a sensitive biomarker for cerebral degeneration in AD.},
author = {Grydeland, Hakon and Westlye, Lars T and Walhovd, Kristine B and Fjell, Anders M},
doi = {10.1002/hbm.22103},
issn = {1097-0193 (Electronic)},
journal = {Hum. Brain Mapp.},
keywords = { 80 and over, Computer-Assisted,Aged,Alzheimer Disease,Area Under Curve,Atrophy,Brain,Cerebral Cortex,Educational Status,Entorhinal Cortex,Female,Hippocampus,Humans,Image Processing,Longitudinal Studies,Magnetic Resonance Imaging,Male,Middle Aged,Neuropsychological Tests,ROC Curve,Reproducibility of Results,Socioeconomic Factors,diagnosis,pathology,psychology},
mendeley-groups = {PhDThesis/Review},
month = {nov},
number = {11},
pages = {2775--2785},
pmid = {22674625},
title = {{Improved prediction of Alzheimer's disease with longitudinal white matter/gray matter contrast changes.}},
volume = {34},
year = {2013}
}
@article{Guan2017,
abstract = {Amnestic MCI (aMCI) and non-amnestic MCI (naMCI) are considered to differ in etiology and outcome. Accurately classifying MCI into meaningful subtypes would enable early intervention with targeted treatment. In this study, we employed structural magnetic resonance imaging (MRI) for MCI subtype classification. This was carried out in a sample of 184 community-dwelling individuals (aged 73-85 years). Cortical surface based measurements were computed from longitudinal and cross-sectional scans. By introducing a feature selection algorithm, we identified a set of discriminative features, and further investigated the temporal patterns of these features. A voting classifier was trained and evaluated via 10 iterations of cross-validation. The best classification accuracies achieved were: 77{\%} (naMCI vs. aMCI), 81{\%} (aMCI vs. cognitively normal (CN)) and 70{\%} (naMCI vs. CN). The best results for differentiating aMCI from naMCI were achieved with baseline features. Hippocampus, amygdala and frontal pole were found to be most discriminative for classifying MCI subtypes. Additionally, we observed the dynamics of classification of several MRI biomarkers. Learning the dynamics of atrophy may aid in the development of better biomarkers, as it may track the progression of cognitive impairment.},
author = {Guan, Hao and Liu, Tao and Jiang, Jiyang and Tao, Dacheng and Zhang, Jicong and Niu, Haijun and Zhu, Wanlin and Wang, Yilong and Cheng, Jian and Kochan, Nicole A and Brodaty, Henry and Sachdev, Perminder and Wen, Wei},
doi = {10.3389/fnagi.2017.00309},
issn = {1663-4365 (Print)},
journal = {Front. Aging Neurosci.},
mendeley-groups = {PhDThesis/Review},
pages = {309},
pmid = {29085292},
title = {{Classifying MCI Subtypes in Community-Dwelling Elderly Using Cross-Sectional and Longitudinal MRI-Based Biomarkers.}},
volume = {9},
year = {2017}
}
@article{Guerrero2016,
abstract = {The assessment and prediction of a subject's current and future risk of developing neurodegenerative diseases like Alzheimer's disease are of great interest in both the design of clinical trials as well as in clinical decision making. Exploring the longitudinal trajectory of markers related to neurodegeneration is an important task when selecting subjects for treatment in trials and the clinic, in the evaluation of early disease indicators and the monitoring of disease progression. Given that there is substantial intersubject variability, models that attempt to describe marker trajectories for a whole population will likely lack specificity for the representation of individual patients. Therefore, we argue here that individualized models provide a more accurate alternative that can be used for tasks such as population stratification and a subject-specific prognosis. In the work presented here, mixed effects modeling is used to derive global and individual marker trajectories for a training population. Test subject (new patient) specific models are then instantiated using a stratified “marker signature” that defines a subpopulation of similar cases within the training database. From this subpopulation, personalized models of the expected trajectory of several markers are subsequently estimated for unseen patients. These patient specific models of markers are shown to provide better predictions of time-to-conversion to Alzheimer's disease than population based models.},
author = {Guerrero, R and Schmidt-Richberg, A and Ledig, C and Tong, T and Wolz, R and Rueckert, D},
doi = {10.1016/j.neuroimage.2016.06.049},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10959572},
journal = {Neuroimage},
keywords = {AD markers,Alzheimer's disease,Longitudinal modeling,Subject stratification},
mendeley-groups = {PhDThesis/Review},
pages = {113--125},
pmid = {27381077},
title = {{Instantiated mixed effects modeling of Alzheimer's disease markers}},
volume = {142},
year = {2016}
}
@inproceedings{Guerrero2015,
author = {Guerrero, R and Ledig, C and Schmidt-Richberg, A and Rueckert, D},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-24888-2_22},
isbn = {9783319248875},
mendeley-groups = {PhDThesis/Review},
pages = {178--185},
publisher = {Springer International Publishing},
title = {{Group-constrained Laplacian Eigenmaps: Longitudinal AD biomarker learning}},
volume = {9352},
year = {2015}
}
@article{guerrero,
abstract = {The exploration of high-dimensional medical imaging datasets often requires the use of dimensionality reduction techniques. Generally, individual instances in longitudinal studies are not independent as several measurements of the same subjects, acquired at several time points, are included. Most non-linear dimensionality reduction techniques, that rely on defining a neighborhood graph to uncover local geometry, neglect potentially valuable grouping information and thus can lead to a poor estimation of the underlying manifold. Incorporating a-priori grouping knowledge of the data can lead to an improved low-dimensional representation. In this work, an approach to leverage such a-priori information is proposed, with the main interest in generating longitudinal biomarkers to assess a subject's risk of developing Alzheimer's disease (AD), and hence estimate time-to-conversion (TTC) and the mini mental state examination (MMSE) of subjects that develop AD. This is achieved via a novel formulation of the Laplacian Eigenmaps and Isomap manifold learning algorithms, that allows the incorporation of group-constraints. The potential of the proposed formulation was demonstrated on a swiss-roll toy example that clearly illustrates the problems faced by traditional techniques when additional structure is observed in the data. A real data experiment showed that the proposed constrained methods yielded improvements of ???16{\%} and ???6{\%} over the original unconstrained methods in kNN estimation of the TTC and MMSE on the ADNI database.},
annote = {From Duplicate 3 (Group-constrained manifold learning: Application to AD risk assessment - Guerrero, R; Ledig, C; Schmidt-Richberg, A; Rueckert, D)

Longitudinal information.

Extension from famous Guerrero2015 paper.},
author = {Guerrero, R and Ledig, C and Schmidt-Richberg, A and Rueckert, D},
doi = {10.1016/j.patcog.2016.09.023},
issn = {00313203},
journal = {Pattern Recognit.},
keywords = {Alzheimer's disease,Longitudinal,Manifold learning,Neurodegeneration},
mendeley-groups = {PhDThesis/Review},
pages = {570--582},
title = {{Group-constrained manifold learning: Application to AD risk assessment}},
volume = {63},
year = {2017}
}
@article{Gui2017,
abstract = {We propose a geodesic distance on a Grassmannian manifold that can be used to quantify the shape progression patterns of the bilateral hippocampi, amygdalas, and lateral ventricles in healthy control (HC), mild cognitive impairment (MCI), and Alzheimer's disease (AD). Longitudinal magnetic resonance imaging (MRI) scans of 754 subjects (3092 scans in total) were used in this study. Longitudinally, the geodesic distance was found to be proportional to the elapsed time separating the two scans in question. Cross-sectionally, utilizing a linear mixed-effects statistical model, we found that each structure's annualized rate of change in the geodesic distance followed the order of AD{\textgreater}MCI{\textgreater}HC, with statistical significance being reached in every case. In addition, for each of the six structures of interest, within the same time interval (e.g., from baseline to the 6th month), we observed significant correlations between the geodesic distance and the cognitive deterioration as quantified by the ADAS-cog increase and the MMSE decrease. Furthermore, as the disease progresses over time, this linkage between the inter-shape geodesic distance and the cognitive decline becomes considerably stronger and more significant.},
author = {Gui, Liangyan and Tang, Xiaoying and Moura, Jose M F},
doi = {10.1016/j.neuroimage.2016.10.025},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = { 80 and over,80 and over,Aged,Alzheimer Disease,Amygdala,Brain,Brain Mapping,Cognitive Dysfunction,Disease Progression,Female,Hippocampus,Humans,Lateral Ventricles,Linear Models,Magnetic Resonance Imaging,Male,Middle Aged,diagnostic imaging,methods,pathology},
mendeley-groups = {PhDThesis/Review},
month = {feb},
pages = {1016--1024},
pmid = {27756616},
title = {{Geodesic distance on a Grassmannian for monitoring the progression of Alzheimer's disease.}},
volume = {146},
year = {2017}
}
@article{Guillaume2014,
abstract = {Despite the growing importance of longitudinal data in neuroimaging, the standard analysis methods make restrictive or unrealistic assumptions (e.g., assumption of Compound Symmetry-the state of all equal variances and equal correlations-or spatially homogeneous longitudinal correlations). While some new methods have been proposed to more accurately account for such data, these methods are based on iterative algorithms that are slow and failure-prone. In this article, we propose the use of the Sandwich Estimator method which first estimates the parameters of interest with a simple Ordinary Least Square model and second estimates variances/covariances with the "so-called" Sandwich Estimator (SwE) which accounts for the within-subject correlation existing in longitudinal data. Here, we introduce the SwE method in its classic form, and we review and propose several adjustments to improve its behaviour, specifically in small samples. We use intensive Monte Carlo simulations to compare all considered adjustments and isolate the best combination for neuroimaging data. We also compare the SwE method to other popular methods and demonstrate its strengths and weaknesses. Finally, we analyse a highly unbalanced longitudinal dataset from the Alzheimer's Disease Neuroimaging Initiative and demonstrate the flexibility of the SwE method to fit within- and between-subject effects in a single model. Software implementing this SwE method has been made freely available at http://warwick.ac.uk/tenichols/SwE. ?? 2014.},
annote = {-Main method:
- Sandwich estimator (statistical method based on mixed models)
-Type of problem to solve
-Machine learning or statistics?
Statistics, strong prior modelling.
-Other comments
Method not really reviewed in depth},
author = {Guillaume, Bryan and Hua, Xue and Thompson, Paul M and Waldorp, Lourens and Nichols, Thomas E},
doi = {10.1016/j.neuroimage.2014.03.029},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10959572},
journal = {Neuroimage},
keywords = {ADNI,Longitudinal Modelling,Marginal Modelling,Sandwich Estimator},
mendeley-groups = {PhDThesis/Review},
pages = {287--302},
pmid = {24650594},
title = {{Fast and accurate modelling of longitudinal and repeated measures neuroimaging data}},
volume = {94},
year = {2014}
}
@article{Gutman2013,
abstract = {We propose a new method to maximize biomarker efficiency for detecting anatomical change over time in serial MRI. Drug trials using neuroimaging become prohibitively costly if vast numbers of subjects must be assessed, so it is vital to develop efficient measures of brain change. A popular measure of efficiency is the minimal sample size (n80) needed to detect 25{\%} change in a biomarker, with 95{\%} confidence and 80{\%} power. For multivariate measures of brain change, we can directly optimize n80 based on a Linear Discriminant Analysis (LDA). Here we use a supervised learning framework to optimize n80, offering two alternative solutions. With a new medial surface modeling method, we track 3D dynamic changes in the lateral ventricles in 2065 ADNI scans. We apply our LDA-based weighting to the results. Our best average n80-in two-fold nested cross-validation-is 104 MCI subjects (95{\%} CI: [94,139]) for a 1-year drug trial, and 75AD subjects [64,102]. This compares favorably with other MRI analysis methods. The standard "statistical ROI" approach applied to the same ventricular surfaces requires 165 MCI or 94AD subjects. At 2 years, the best LDA measure needs only 67 MCI and 52AD subjects, versus 119 MCI and 80AD subjects for the stat-ROI method. Our surface-based measures are unbiased: they give no artifactual additive atrophy over three time points. Our results suggest that statistical weighting may boost efficiency of drug trials that use brain maps.},
annote = {STATISTICAL AND GROUP TRIAL, NO},
author = {Gutman, Boris A and Hua, Xue and Rajagopalan, Priya and Chou, Yi-Yu and Wang, Yalin and Yanovsky, Igor and Toga, Arthur W and Jack, Clifford R Jr and Weiner, Michael W and Thompson, Paul M},
doi = {10.1016/j.neuroimage.2012.12.052},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = {Aged,Alzheimer Disease,Cerebral Ventricles,Cognitive Dysfunction,Discriminant Analysis,Disease Progression,Female,Humans,Magnetic Resonance Imaging,Male,pathology},
mendeley-groups = {PhDThesis/Review},
pages = {386--401},
pmid = {23296188},
title = {{Maximizing power to track Alzheimer's disease and MCI progression by LDA-based weighting of longitudinal ventricular surface features.}},
volume = {70},
year = {2013}
}
@misc{Henneman,
abstract = {OBJECTIVE: To investigate the added value of hippocampal atrophy rates over whole brain volume measurements on MRI in patients with Alzheimer disease (AD), patients with mild cognitive impairment (MCI), and controls. METHODS: We included 64 patients with AD (67 +/- 9 years; F/M 38/26), 44 patients with MCI (71 +/- 6 years; 21/23), and 34 controls (67 +/- 9 years; 16/18). Two MR scans were performed (scan interval: 1.8 +/- 0.7 years; 1.0 T), using a coronal three-dimensional T1-weighted gradient echo sequence. At follow-up, 3 controls and 23 patients with MCI had progressed to AD. Hippocampi were manually delineated at baseline. Hippocampal atrophy rates were calculated using regional, nonlinear fluid registration. Whole brain baseline volumes and atrophy rates were determined using automated segmentation and registration tools. RESULTS: All MRI measures differed between groups (p {\textless}0.005). For the distinction of MCI from controls, larger effect sizes of hippocampal measures were found compared to whole brain measures. Between MCI and AD, only whole brain atrophy rate differed significantly. Cox proportional hazards models (variables dichotomized by median) showed that within all patients without dementia, hippocampal baseline volume (hazard ratio [HR]: 5.7 [95{\%} confidence interval: 1.5-22.2]), hippocampal atrophy rate (5.2 [1.9-14.3]), and whole brain atrophy rate (2.8 [1.1-7.2]) independently predicted progression to AD; the combination of low hippocampal volume and high atrophy rate yielded a HR of 61.1 (6.1-606.8). Within patients with MCI, only hippocampal baseline volume and atrophy rate predicted progression. CONCLUSION: Hippocampal measures, especially hippocampal atrophy rate, best discriminate mild cognitive impairment (MCI) from controls. Whole brain atrophy rate discriminates Alzheimer disease (AD) from MCI. Regional measures of hippocampal atrophy are the strongest predictors of progression to AD.},
author = {Henneman, W J and Sluimer, J D and Barnes, J and van der Flier, W M and Sluimer, I C and Fox, N C and Scheltens, P and Vrenken, H and Barkhof, F},
booktitle = {Neurology},
mendeley-groups = {PhDThesis/Review},
number = {11{\textless}BR{\textgreater}},
pages = {999----1007{\textless}BR{\textgreater}},
title = {{Hippocampal atrophy rates in Alzheimer disease: added value over whole brain volume measures}},
volume = {72{\textless}BR{\textgreater}}
}
@article{Hett2018,
abstract = {Numerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimer's disease (AD). While anatomical MRI captures structural alterations, studies demonstrated the ability of diffusion MRI to capture microstructural modifications at an earlier stage. Several methods have focused on hippocampus structure to detect AD. To date, the patch-based grading framework provides the best biomarker based on the hippocampus. However, this structure is complex since the hippocampus is divided into several heterogeneous subfields not equally impacted by AD. Former in-vivo imaging studies only investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to study the efficiency of hippocampal subfields compared to the whole hippocampus structure with a multimodal patch-based framework that enables to capture subtler structural and microstructural alterations. To this end, we analyze the significance of the different hippocampal subfields for AD diagnosis and prognosis with volumetric, diffusivity measurements and a novel multimodal patch-based grading framework that combines structural and diffusion MRI. The experiments conducted in this work showed that the whole hippocampus provides the most discriminant biomarkers for advanced AD detection while biomarkers applied into subiculum obtain the best results for AD prediction, improving by 2{\%} the accuracy compared to the whole hippocampus.},
annote = {NOT LONGITUDINAL},
author = {Hett, Kilian and Ta, Vinh Thong and Catheline, Gwenaelle and Tourdias, Thomas and Manjon, Jose and Coupe, Pierrick},
doi = {10.1101/293126},
journal = {bioRxiv},
mendeley-groups = {PhDThesis/Review},
pages = {293126},
publisher = {Cold Spring Harbor Laboratory},
title = {{Multimodal Hippocampal Subfield Grading For Alzheimer's Disease Classification}},
year = {2018}
}
@article{Hinrichs2011,
abstract = {Alzheimer's Disease (AD) and other neurodegenerative diseases affect over 20 million people worldwide, and this number is projected to significantly increase in the coming decades. Proposed imaging-based markers have shown steadily improving levels of sensitivity/specificity in classifying individual subjects as AD or normal. Several of these efforts have utilized statistical machine learning techniques, using brain images as input, as means of deriving such AD-related markers. A common characteristic of this line of research is a focus on either (1) using a single imaging modality for classification, or (2) incorporating several modalities, but reporting separate results for each. One strategy to improve on the success of these methods is to leverage all available imaging modalities together in a single automated learning framework. The rationale is that some subjects may show signs of pathology in one modality but not in another-by combining all available images a clearer view of the progression of disease pathology will emerge. Our method is based on the Multi-Kernel Learning (MKL) framework, which allows the inclusion of an arbitrary number of views of the data in a maximum margin, kernel learning framework. The principal innovation behind MKL is that it learns an optimal combination of kernel (similarity) matrices while simultaneously training a classifier. In classification experiments MKL outperformed an SVM trained on all available features by 3{\%}-4{\%}. We are especially interested in whether such markers are capable of identifying early signs of the disease. To address this question, we have examined whether our multi-modal disease marker (MMDM) can predict conversion from Mild Cognitive Impairment (MCI) to AD. Our experiments reveal that this measure shows significant group differences between MCI subjects who progressed to AD, and those who remained stable for 3. years. These differences were most significant in MMDMs based on imaging data. We also discuss the relationship between our MMDM and an individual's conversion from MCI to AD. {\textcopyright}2010 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Hinrichs, Chris and Singh, Vikas and Xu, Guofan and Johnson, Sterling C},
doi = {10.1016/j.neuroimage.2010.10.081},
eprint = {NIHMS150003},
isbn = {1053-8119},
issn = {10538119},
journal = {Neuroimage},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {574--589},
pmid = {21146621},
title = {{Predictive markers for AD in a multi-modality framework: An analysis of MCI progression in the ADNI population}},
volume = {55},
year = {2011}
}
@article{Huang2016c,
abstract = {Alzheimer's disease (AD) is an irreversible neurodegenerative disease and affects a large population in the world. Cognitive scores at multiple time points can be reliably used to evaluate the progression of the disease clinically. In recent studies, machine learning techniques have shown promising results on the prediction of AD clinical scores. However, there are multiple limitations in the current models such as linearity assumption and missing data exclusion. Here, we present a nonlinear supervised sparse regression–based random forest (RF) framework to predict a variety of longitudinal AD clinical scores. Furthermore, we propose a soft-split technique to assign probabilistic paths to a test sample in RF for more accurate predictions. In order to benefit from the longitudinal scores in the study, unlike the previous studies that often removed the subjects with missing scores, we first estimate those missing scores with our proposed soft-split sparse regression–based RF and then utilize those estimated longitudinal scores at all the previous time points to predict the scores at the next time point. The experiment results demonstrate that our proposed method is superior to the traditional RF and outperforms other state-of-art regression models. Our method can also be extended to be a general regression framework to predict other disease scores.},
author = {Huang, Lei and Jin, Yan and Gao, Yaozong and Thung, Kim Han and Shen, Dinggang},
doi = {10.1016/j.neurobiolaging.2016.07.005},
issn = {15581497},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease,Clinical scores,Longitudinal study,Random forest,Soft-split,Sparse representation},
mendeley-groups = {PhDThesis/Review},
month = {oct},
pages = {180--191},
pmid = {27500865},
publisher = {NIH Public Access},
title = {{Longitudinal clinical score prediction in Alzheimer's disease with soft-split sparse regression based random forest}},
volume = {46},
year = {2016}
}

@article{Ibrahim,
abstract = {Incomplete data are quite common in biomedical and other types of research, especially in longitudinal studies. During the last three decades, a vast amount of work has been done in the area. This has led, on the one hand, to a rich taxonomy of missing-data concepts, issues, and methods and, on the other hand, to a variety of data-analytic tools. Elements of taxonomy include: missing data patterns, mechanisms, and modeling frameworks; inferential paradigms; and sensitivity analysis frameworks. These are described in detail. A variety of concrete modeling devices is presented. To make matters concrete, two case studies are considered. The first one concerns quality of life among breast cancer patients, while the second one examines data from the Muscatine children's obesity study.},
author = {Ibrahim, Joseph G and Molenberghs, Geert},
doi = {10.1007/s11749-009-0138-x},
isbn = {1133-0686},
issn = {1133-0686},
journal = {Test (Madr).},
keywords = {Expectation-maximization algorithm,Incomplete data,Missing at random,Missing completely at random,Missing not at random,Pattern-mixture model,Selection model,Sensitivity analyses,Shared-parameter model},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {1--43},
pmid = {21218187},
title = {{Missing data methods in longitudinal studies: a review.}},
volume = {18},
year = {2009}
}
@article{Ito2011,
abstract = {Background: A mathematical model was developed to describe the longitudinal response in Alzheimer's Disease Assessment Scale-cognitive (ADAS-cog) obtained from the Alzheimer's Disease Neuroimaging Initiative. Methods: The model was fit to the longitudinal ADAS-cog scores from 817 patients. Risk factors (age, apolipoprotein $\epsilon$4 [APOE $\epsilon$4] genotype, gender, family history of AD, years of education) and baseline severity were tested as covariates. Results: Rate of disease progression increased with baseline severity. Age, APOE $\epsilon$4 genotype, and gender were identified as potential covariates influencing disease progression. The rate of disease progression in patients with mild to moderate AD was estimated as approximately 5.5 points/yr. Conclusions: A disease progression model adequately described the natural decline of ADAS-cog observed in Alzheimer's Disease Neuroimaging Initiative. Baseline severity is an important covariate to predict a curvilinear rate of disease progression in normal elderly, mild cognitive impairment, and AD patients. Age, APOE $\epsilon$4 genotype, and gender also influence the rate of disease progression. {\textcopyright}2011 The Alzheimer's Association. All rights reserved.},
author = {Ito, Kaori and Corrigan, Brian and Zhao, Qinying and French, Jonathan and Miller, Raymond and Soares, Holly and Katz, Elyse and Nicholas, Timothy and Billing, Bill and Anziano, Richard and Fullerton, Terence},
doi = {10.1016/j.jalz.2010.03.018},
isbn = {1552-5279},
issn = {15525260},
journal = {Alzheimer's Dement.},
keywords = {ADAS-cog,APOE $\epsilon$4 genotype,Age,Alzheimer's disease,Disease progression model,MCI,Natural history},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {151--160},
pmid = {20810324},
title = {{Disease progression model for cognitive deterioration from Alzheimer's Disease Neuroimaging Initiative database}},
volume = {7},
year = {2011}
}
@article{Jo2019,
abstract = {Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially in the domain of computer vision. The application of deep learning to early detection and automated classification of Alzheimer's disease (AD) has recently gained considerable attention, as rapid progress in neuroimaging techniques has generated large-scale multimodal neuroimaging data. A systematic review of publications using deep learning approaches and neuroimaging data for diagnostic classification of AD was performed. A PubMed and Google Scholar search was used to identify deep learning papers on AD published between January 2013 and July 2018. These papers were reviewed, evaluated, and classified by algorithm and neuroimaging type, and the findings were summarized. Of 16 studies meeting full inclusion criteria, 4 used a combination of deep learning and traditional machine learning approaches, and 12 used only deep learning approaches. The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8{\%} for AD classification and 83.7{\%} for prediction of conversion from mild cognitive impairment (MCI), a prodromal stage of AD, to AD. Deep learning approaches, such as convolutional neural network (CNN) or recurrent neural network (RNN), that use neuroimaging data without pre-processing for feature selection have yielded accuracies of up to 96.0{\%} for AD classification and 84.2{\%} for MCI conversion prediction. The best classification performance was obtained when multimodal neuroimaging and fluid biomarkers were combined. Deep learning approaches continue to improve in performance and appear to hold promise for diagnostic classification of AD using multimodal neuroimaging data. AD research that uses deep learning is still evolving, improving performance by incorporating additional hybrid data types, such as—omics data, increasing transparency with explainable approaches that add knowledge of specific disease-related features and mechanisms.},
archivePrefix = {arXiv},
arxivId = {1905.00931},
author = {Jo, Taeho and Nho, Kwangsik and Saykin, Andrew J.},
doi = {10.3389/fnagi.2019.00220},
eprint = {1905.00931},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Jo, Nho, Saykin - 2019 - Deep Learning in Alzheimer's disease Diagnostic Classification and Prognostic Prediction using Neuroimaging Dat.pdf:pdf},
issn = {16634365},
journal = {Front. Aging Neurosci.},
keywords = {Alzheimer's disease,artificial intelligence,classification,deep learning,machine learning,magnetic resonance imaging,neuroimaging,positron emission tomography},
mendeley-groups = {Review2,PhDThesis/Review},
month = {may},
pmid = {31481890},
title = {{Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data}},
volume = {11},
year = {2019}
}
@article{Mitchell2017,
abstract = {Incluye bibliografía e índices.},
author = {Mitchell, T.M.},
isbn = {1259096955},
journal = {Burr Ridge, McGraw Hill},
mendeley-groups = {PhDThesis/Review},
pages = {pp.870--877},
publisher = {McGraw Hill Education},
title = {{Machine learning}},
volume = {45(37)},
year = {1997}
}
@article{Blennow2010,
abstract = {Intense multidisciplinary research has provided detailed knowledge of the molecular pathogenesis of Alzheimer disease (AD). This knowledge has been translated into new therapeutic strategies with putative disease-modifying effects. Several of the most promising approaches, such as amyloid-beta immunotherapy and secretase inhibition, are now being tested in clinical trials. Disease-modifying treatments might be at their most effective when initiated very early in the course of AD, before amyloid plaques and neurodegeneration become too widespread. Thus, biomarkers are needed that can detect AD in the predementia phase or, ideally, in presymptomatic individuals. In this Review, we present the rationales behind and the diagnostic performances of the core cerebrospinal fluid (CSF) biomarkers for AD, namely total tau, phosphorylated tau and the 42 amino acid form of amyloid-beta. These biomarkers reflect AD pathology, and are candidate markers for predicting future cognitive decline in healthy individuals and the progression to dementia in patients who are cognitively impaired. We also discuss emerging plasma and CSF biomarkers, and explore new proteomics-based strategies for identifying additional CSF markers. Furthermore, we outline the roles of CSF biomarkers in drug discovery and clinical trials, and provide perspectives on AD biomarker discovery and the validation of such markers for use in the clinic.},
author = {Blennow, Kaj and Hampel, Harald and Weiner, Michael and Zetterberg, Henrik},
doi = {10.1038/nrneurol.2010.4},
isbn = {1759-4766 (Electronic)$\backslash$r1759-4758 (Linking)},
issn = {17594758},
journal = {Nat. Rev. Neurol.},
keywords = {Alzheimer's disease,Biomarkers},
mendeley-groups = {PhDThesis/Review},
month = {mar},
number = {3},
pages = {131--144},
pmid = {20157306},
publisher = {Nature Publishing Group},
title = {{Cerebrospinal fluid and plasma biomarkers in Alzheimer's disease}},
volume = {6},
year = {2010}
}
@article{Liu2013a,
abstract = {Apolipoprotein E (Apo-E) is a major cholesterol carrier that supports lipid transport and injury repair in the brain. APOE polymorphic alleles are the main genetic determinants of Alzheimer disease (AD) risk: individuals carrying the $\epsilon$4 allele are at increased risk of AD compared with those carrying the more common $\epsilon$3 allele, whereas the $\epsilon$2 allele decreases risk. Presence of the APOE $\epsilon$4 allele is also associated with increased risk of cerebral amyloid angiopathy and age-related cognitive decline during normal ageing. Apo-E-lipoproteins bind to several cell-surface receptors to deliver lipids, and also to hydrophobic amyloid-$\beta$ (A$\beta$) peptide, which is thought to initiate toxic events that lead to synaptic dysfunction and neurodegeneration in AD. Apo-E isoforms differentially regulate A$\beta$ aggregation and clearance in the brain, and have distinct functions in regulating brain lipid transport, glucose metabolism, neuronal signalling, neuroinflammation, and mitochondrial function. In this Review, we describe current knowledge on Apo-E in the CNS, with a particular emphasis on the clinical and pathological features associated with carriers of different Apo-E isoforms. We also discuss A$\beta$-dependent and A$\beta$-independent mechanisms that link Apo-E4 status with AD risk, and consider how to design effective strategies for AD therapy by targeting Apo-E.},
author = {Liu, Chia Chan and Kanekiyo, Takahisa and Xu, Huaxi and Bu, Guojun},
doi = {10.1038/nrneurol.2012.263},
issn = {17594758},
journal = {Nat. Rev. Neurol.},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {feb},
number = {2},
pages = {106--118},
title = {{Apolipoprotein e and Alzheimer disease: Risk, mechanisms and therapy}},
volume = {9},
year = {2013}
}
@article{Brookmeyer2007,
abstract = {Background: Our goal was to forecast the global burden of Alzheimer's disease and evaluate the potential impact of interventions that delay disease onset or progression. Methods: A stochastic, multistate model was used in conjunction with United Nations worldwide population forecasts and data from epidemiological studies of the risks of Alzheimer's disease. Results: In 2006, the worldwide prevalence of Alzheimer's disease was 26.6 million. By 2050, the prevalence will quadruple, by which time 1 in 85 persons worldwide will be living with the disease. We estimate about 43{\%} of prevalent cases need a high level of care, equivalent to that of a nursing home. If interventions could delay both disease onset and progression by a modest 1 year, there would be nearly 9.2 million fewer cases of the disease in 2050, with nearly the entire decline attributable to decreases in persons needing a high level of care. Conclusions: We face a looming global epidemic of Alzheimer's disease as the world's population ages. Modest advances in therapeutic and preventive strategies that lead to even small delays in the onset and progression of Alzheimer's disease can significantly reduce the global burden of this disease. {\textcopyright}2007 The Alzheimer's Association.},
author = {Brookmeyer, Ron and Johnson, Elizabeth and Ziegler-Graham, Kathryn and Arrighi, H Michael},
doi = {10.1016/j.jalz.2007.04.381},
isbn = {1552-5260},
issn = {15525260},
journal = {Alzheimer's Dement.},
keywords = {Alzheimer's,Forecast,Prediction,Statistics},
mendeley-groups = {PHD/Medical focused Alzheimer,PhDThesis/Review},
month = {jul},
number = {3},
pages = {186--191},
pmid = {19595937},
publisher = {Elsevier},
title = {{Forecasting the global burden of Alzheimer's disease}},
volume = {3},
year = {2007}
}
@article{Wang2003,
abstract = {Rates of hippocampal volume loss have been shown to distinguish subjects with dementia of the Alzheimer type (DAT) from nondemented controls (Jack et al., 2000). In this study, we obtained magnetic resonance scans in 18 subjects with very mild DAT (CDR 0.5) and 26 age-matched nondemented controls (CDR 0) 2 years apart. Large-deformation high-dimensional brain mapping was used to quantify and compare changes in hippocampal shape as well as volume in the two groups of subjects. Hippocampal volume loss over time was significantly greater in the CDR 0.5 subjects (left = 8.3{\%}, right = 10.2{\%}) than in the CDR 0 subjects (left = 4.0{\%}, right = 5.5{\%}) (ANOVA, F = 7.81, P = 0.0078). We used singular-value decomposition and logistic regression models to quantify hippocampal shape change across time within individuals, and this shape change in the CDR 0.5 and CDR 0 subjects was found to be significantly different (Wilks's $\lambda$, P = 0.014). Further, at baseline, CDR 0.5 subjects, in comparison to CDR 0 subjects, showed inward deformation over 38{\%} of the hippocampal surface; after 2 years this difference grew to 47{\%}. Also, within the CDR 0 subjects, shape change between baseline and follow-up was largely confined to the head of the hippocampus and subiculum, while in the CDR 0.5 subjects, shape change involved the lateral body of the hippocampus as well as the head region and subiculum. These results suggest that different patterns of hippocampal shape change in time as well as different rates of hippocampal volume loss distinguish very mild DAT from healthy aging. {\textcopyright} 2003 Elsevier Inc. All rights reserved.},
author = {Wang, Lei and Swank, Jeffrey S. and Glick, Irena E. and Gado, Mokhtar H. and Miller, Michael I. and Morris, John C. and Csernansky, John G.},
doi = {10.1016/S1053-8119(03)00361-6},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wang et al. - 2003 - Changes in hippocampal volume and shape across time distinguish dementia of the Alzheimer type from healthy agin(2).pdf:pdf},
isbn = {1053-8119 (Print)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
mendeley-groups = {PHD/Shape Analysis,PhDThesis/Hippo},
month = {oct},
number = {2},
pages = {667--682},
pmid = {14568443},
publisher = {Academic Press},
title = {{Changes in hippocampal volume and shape across time distinguish dementia of the Alzheimer type from healthy aging}},
volume = {20},
year = {2003}
}

@article{Wishart2006,
abstract = {OBJECTIVE: To determine whether cognitively intact adults with the APOE epsilon3/epsilon4 genotype show reduced gray matter density on voxel-based morphometry (VBM) vs those homozygous for the epsilon3 allele.$\backslash$n$\backslash$nMETHODS: Participants were healthy, cognitively intact, right-handed adults, age 19 to 80, who completed genotyping, neuropsychological testing, and MRI. Forty-nine participants had the epsilon3/epsilon3 genotype and 27 had the epsilon3/epsilon4 genotype. Gray matter data were analyzed using the general linear model as implemented in the Statistical Parametric Mapping package, adjusting for age and sex.$\backslash$n$\backslash$nRESULTS: The epsilon3/epsilon4 participants showed lower gray matter density than the epsilon3/epsilon3 participants in right medial temporal and bilateral frontotemporal regions as well as other areas. There were no regions in which epsilon3/epsilon4 participants showed higher gray matter density than epsilon3/epsilon3 participants.$\backslash$n$\backslash$nCONCLUSIONS: Regionally reduced gray matter density is detectable in cognitively intact adults with a single copy of the APOE epsilon4 allele.},
author = {Wishart, H. A. and Saykin, A. J. and McAllister, T. W. and Rabin, L. A. and McDonald, B. C. and Flashman, L. A. and Roth, R. M. and Mamourian, A. C. and Tsongalis, G. J. and Rhodes, C. H.},
doi = {10.1212/01.wnl.0000238079.00472.3a},
isbn = {1526-632X (Electronic)},
issn = {00283878},
journal = {Neurology},
mendeley-groups = {PHD/Shape Analysis,PhDThesis/Hippo},
month = {sep},
number = {7},
pages = {1221--1224},
pmid = {17030756},
publisher = {Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology},
title = {{Regional brain atrophy in cognitively intact adults with a single APOE $\epsilon$4 allele}},
volume = {67},
year = {2006}
}
@article{Villemagne2013,
abstract = {BACKGROUND: Similar to most chronic diseases, Alzheimer's disease (AD) develops slowly from a preclinical phase into a fully expressed clinical syndrome. We aimed to use longitudinal data to calculate the rates of amyloid beta (Abeta) deposition, cerebral atrophy, and cognitive decline. METHODS: In this prospective cohort study, healthy controls, patients with mild cognitive impairment (MCI), and patients with AD were assessed at enrolment and every 18 months. At every visit, participants underwent neuropsychological examination, MRI, and a carbon-11-labelled Pittsburgh compound B ((11)C-PiB) PET scan. We included participants with three or more (11)C-PiB PET follow-up assessments. Abeta burden was expressed as (11)C-PiB standardised uptake value ratio (SUVR) with the cerebellar cortex as reference region. An SUVR of 1.5 was used to discriminate high from low Abeta burdens. The slope of the regression plots over 3-5 years was used to estimate rates of change for Abeta deposition, MRI volumetrics, and cognition. We included those participants with a positive rate of Abeta deposition to calculate the trajectory of each variable over time. FINDINGS: 200 participants (145 healthy controls, 36 participants with MCI, and 19 participants with AD) were assessed at enrolment and every 18 months for a mean follow-up of 3.8 (95{\%} CI CI 3.6-3.9) years. At baseline, significantly higher Abeta burdens were noted in patients with AD (2.27, SD 0.43) and those with MCI (1.94, 0.64) than in healthy controls (1.38, 0.39). At follow-up, 163 (82{\%}) of the 200 participants showed positive rates of Abeta accumulation. Abeta deposition was estimated to take 19.2 (95{\%} CI 16.8-22.5) years in an almost linear fashion-with a mean increase of 0.043 (95{\%} CI 0.037-0.049) SUVR per year-to go from the threshold of (11)C-PiB positivity (1.5 SUVR) to the levels observed in AD. It was estimated to take 12.0 (95{\%} CI 10.1-14.9) years from the levels observed in healthy controls with low Abeta deposition (1.2 [SD 0.1] SUVR) to the threshold of (11)C-PiB positivity. As AD progressed, the rate of Abeta deposition slowed towards a plateau. Our projections suggest a prolonged preclinical phase of AD in which Abeta deposition reaches our threshold of positivity at 17.0 (95{\%} CI 14.9-19.9) years, hippocampal atrophy at 4.2 (3.6-5.1) years, and memory impairment at 3.3 (2.5-4.5) years before the onset of dementia (clinical dementia rating score 1). INTERPRETATION: Abeta deposition is slow and protracted, likely to extend for more than two decades. Such predictions of the rate of preclinical changes and the onset of the clinical phase of AD will facilitate the design and timing of therapeutic interventions aimed at modifying the course of this illness. FUNDING: Science and Industry Endowment Fund (Australia), The Commonwealth Scientific and Industrial Research Organisation (Australia), The National Health and Medical Research Council of Australia Program and Project Grants, the Austin Hospital Medical Research Foundation, Victorian State Government, The Alzheimer's Drug Discovery Foundation, and the Alzheimer's Association.},
author = {Villemagne, Victor L and Burnham, Samantha and Bourgeat, Pierrick and Brown, Belinda and Ellis, Kathryn A and Salvado, Olivier and Szoeke, Cassandra and Macaulay, S Lance and Martins, Ralph and Maruff, Paul and Ames, David and Rowe, Christopher C and Masters, Colin L},
doi = {10.1016/S1474-4422(13)70044-9},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Villemagne et al. - 2013 - Amyloid beta deposition, neurodegeneration, and cognitive decline in sporadic Alzheimer's disease a prospecti.pdf:pdf},
institution = {Australian Imaging Biomarkers and Lifestyle (AIBL) Research Group},
isbn = {1474-4465 (Electronic)$\backslash$r1474-4422 (Linking)},
issn = {1474-4465 (Electronic)},
journal = {Lancet. Neurol.},
keywords = {80 and over,Aged,Alzheimer Disease,Amyloid beta-Peptides,Cognition Disorders,Cohort Studies,Disease Progression,Female,Follow-Up Studies,Humans,Male,Middle Aged,Neurodegenerative Diseases,Prospective Studies,epidemiology,metabolism,pathology},
language = {eng},
mendeley-groups = {Review2,PhDThesis/Review},
month = {apr},
number = {4},
pages = {357--367},
pmid = {23477989},
publisher = {Elsevier},
title = {{Amyloid beta deposition, neurodegeneration, and cognitive decline in sporadic Alzheimer's disease: a prospective cohort study.}},
volume = {12},
year = {2013}
}
@article{Wang2018,
abstract = {The number of service visits of Alzheimer's disease (AD) patients is different from each other and their visit time intervals are non-uniform. Although the literature has revealed many approaches in disease progression modeling, they fail to leverage these time-relevant part of patients' medical records in predicting disease's future status. This paper investigates how to predict the AD progression for a patient's next medical visit through leveraging heterogeneous medical data. Data provided by the National Alzheimer's Coordinating Center includes 5432 patients with probable AD from August 31, 2005 to May 25, 2017. Long short-term memory recurrent neural networks (RNN) are adopted. The approach relies on an enhanced “many-to-one” RNN architecture to support the shift of time steps. Hence, the approach can deal with patients' various numbers of visits and uneven time intervals. The results show that the proposed approach can be utilized to predict patients' AD progressions on their next visits with over 99{\%} accuracy, significantly outperforming classic baseline methods. This study confirms that RNN can effectively solve the AD progression prediction problem by fully leveraging the inherent temporal and medical patterns derived from patients' historical visits. More promisingly, the approach can be customarily applied to other chronic disease progression problems.},
author = {Wang, Tingyan and Qiu, Robin G. and Yu, Ming},
doi = {10.1038/s41598-018-27337-w},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wang, Qiu, Yu - 2018 - Predictive Modeling of the Progression of Alzheimer's Disease with Recurrent Neural Networks.pdf:pdf},
issn = {20452322},
journal = {Sci. Rep.},
keywords = {Alzheimer's disease,Prognosis},
mendeley-groups = {Review2,PHD/Machine Learning/Medical deep learning,PHD/Machine Learning/Deep Learning,PhDThesis/Review},
month = {dec},
number = {1},
pages = {9161},
publisher = {Nature Publishing Group},
title = {{Predictive Modeling of the Progression of Alzheimer's Disease with Recurrent Neural Networks}},
volume = {8},
year = {2018}
}
@article{Gower1975,
abstract = {Suppose Pi(i) (i = 1, 2, ..., m, j = 1, 2, ..., n) give the locations of mn points in p-dimensional space. Collectively these may be regarded as m configurations, or scalings, each of n points in p-dimensions. The problem is investigated of translating, rotating, reflecting and scaling the m configurations to minimize the goodness-of-fit criterion $\Sigma$i=1m $\Sigma$i=1n $\Delta$2(Pj(i)Gi), where Gi is the centroid of the m points Pi(i) (i = 1, 2, ..., m). The rotated positions of each configuration may be regarded as individual analyses with the centroid configuration representing a consensus, and this relationship with individual scaling analysis is discussed. A computational technique is given, the results of which can be summarized in analysis of variance form. The special case m = 2 corresponds to Classical Procrustes analysis but the choice of criterion that fits each configuration to the common centroid configuration avoids difficulties that arise when one set is fitted to the other, regarded as fixed. {\textcopyright} 1975 Psychometric Society.},
author = {Gower, J. C.},
doi = {10.1007/BF02291478},
issn = {00333123},
journal = {Psychometrika},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {mar},
number = {1},
pages = {33--51},
publisher = {Springer-Verlag},
title = {{Generalized procrustes analysis}},
volume = {40},
year = {1975}
}
@article{Sabuncu2014,
abstract = {This paper presents a method for the statistical analysis of the associations between longitudinal neuroimaging measurements, e.g., of cortical thickness, and the timing of a clinical event of interest, e.g., disease onset. The proposed approach consists of two steps, the first of which employs a linear mixed effects (LME) model to capture temporal variation in serial imaging data. The second step utilizes the extended Cox regression model to examine the relationship between time-dependent imaging measurements and the timing of the event of interest. We demonstrate the proposed method both for the univariate analysis of image-derived biomarkers, e.g., the volume of a structure of interest, and the exploratory mass-univariate analysis of measurements contained in maps, such as cortical thickness and gray matter density. The mass-univariate method employs a recently developed spatial extension of the LME model. We applied our method to analyze structural measurements computed using FreeSurfer, a widely used brain Magnetic Resonance Image (MRI) analysis software package. We provide a quantitative and objective empirical evaluation of the statistical performance of the proposed method on longitudinal data from subjects suffering from Mild Cognitive Impairment (MCI) at baseline.},
annote = {STATISTICAL AND NO PAPER :(},
author = {Sabuncu, Mert R and Bernal-Rusiel, Jorge L and Reuter, Martin and Greve, Douglas N and Fischl, Bruce},
doi = {10.1016/j.neuroimage.2014.04.015},
institution = {Alzheimer's Disease Neuroimaging Initiative},
issn = {1095-9572 (Electronic)},
journal = {Neuroimage},
keywords = {Benchmarking,Cerebral Cortex,Data Interpretation, Statistical,Hippocampus,Humans,Linear Models,Longitudinal Studies,Magnetic Resonance Imaging,Models, Statistical,Neuroimaging,Proportional Hazards Models,anatomy {\&} histology,statistics {\&} numerical data},
language = {eng},
mendeley-groups = {PhDThesis/Review},
month = {aug},
pages = {9--18},
pmid = {24736175},
title = {{Event time analysis of longitudinal neuroimage data.}},
volume = {97},
year = {2014}
}
@article{Iturria-Medina2016,
abstract = {Multifactorial mechanisms underlying late-onset Alzheimer/'s disease (LOAD) are poorly characterized from an integrative perspective. Here spatiotemporal alterations in brain amyloid-[beta] deposition, metabolism, vascular, functional activity at rest, structural properties, cognitive integrity and peripheral proteins levels are characterized in relation to LOAD progression. We analyse over 7,700 brain images and tens of plasma and cerebrospinal fluid biomarkers from the Alzheimer/'s Disease Neuroimaging Initiative (ADNI). Through a multifactorial data-driven analysis, we obtain dynamic LOAD-abnormality indices for all biomarkers, and a tentative temporal ordering of disease progression. Imaging results suggest that intra-brain vascular dysregulation is an early pathological event during disease development. Cognitive decline is noticeable from initial LOAD stages, suggesting early memory deficit associated with the primary disease factors. High abnormality levels are also observed for specific proteins associated with the vascular system/'s integrity. Although still subjected to the sensitivity of the algorithms and biomarkers employed, our results might contribute to the development of preventive therapeutic interventions.},
archivePrefix = {arXiv},
arxivId = {arXiv:1011.1669v3},
author = {Iturria-Medina, Y and Sotero, R C and Toussaint, P J and Mateos-P{\'{e}}rez, J M and Evans, A C and Weiner, Michael W. and Aisen, Paul and Petersen, Ronald and Jack, Clifford R. and Jagust, William and Trojanowki, John Q. and Toga, Arthur W. and Beckett, Laurel and Green, Robert C. and Saykin, Andrew J. and Morris, John and Shaw, Leslie M. and Khachaturian, Zaven and Sorensen, Greg and Kuller, Lew and Raichle, Marc and Paul, Steven and Davies, Peter and Fillit, Howard and Hefti, Franz and Holtzman, Davie and Mesulam, M Marcel and Potter, William and Snyder, Peter and Schwartz, Adam and Montine, Tom and Thomas, Ronald G. and Donohue, Michael and Walter, Sarah and Gessert, Devon and Sather, Tamie and Jiminez, Gus and Harvey, Danielle and Bernstein, Matthew and Fox, Nick and Thompson, Paul and Schuff, Norbert and Borowski, Bret and Gunter, Jeff and Senjem, Matt and Vemuri, Prashanthi and Jones, David and Kantarci, Kejal and Ward, Chad and Koeppe, Robert A. and Foster, Norm and Reiman, Eric M. and Chen, Kewei and Mathis, Chet and Landau, Susan and Cairns, Nigel J. and Householder, Erin and Taylor-Reinwald, Lisa and Lee, Virginia and Korecka, Magdalena and Figurski, Michal and Crawford, Karen and Neu, Scott and Foroud, Tatiana M. and Potkin, Steven and Shen, Li and Faber, Kelley and Kim, Sungeun and Nho, Kwangsik and Thal, Leon and Buckholtz, Neil and Albert, Marylyn and Frank, Richard and Hsiao, John and Kaye, Jeffrey and Quinn, Joseph and Lind, Betty and Carter, Raina and Dolen, Sara and Schneider, Lon S. and Pawluczyk, Sonia and Beccera, Mauricio and Teodoro, Liberty and Spann, Bryan M. and Brewer, James and Vanderswag, Helen and Fleisher, Adam and Heidebrink, Judith L. and Lord, Joanne L. and Mason, Sara S. and Albers, Colleen S. and Knopman, David and Johnson, Kris and Doody, Rachelle S. and Villanueva-Meyer, Javier and Chowdhury, Munir and Rountree, Susan and Dang, Mimi and Stern, Yaakov and Honig, Lawrence S. and Bell, Karen L. and Ances, Beau and Carroll, Maria and Leon, Sue and Mintun, Mark A. and Schneider, Stacy and Oliver, Angela and Marson, Daniel and Griffith, Randall and Clark, David and Geldmacher, David and Brockington, John and Roberson, Erik and Grossman, Hillel and Mitsis, Effie and de Toledo-Morrell, Leyla and Shah, Raj C. and Duara, Ranjan and Varon, Daniel and Greig, Maria T. and Roberts, Peggy and Albert, Marilyn and Onyike, Chiadi and D'Agostino, Daniel and Kielb, Stephanie and Galvin, James E. and Cerbone, Brittany and Michel, Christina A. and Rusinek, Henry and de Leon, Mony J. and Glodzik, Lidia and {De Santi}, Susan and Doraiswamy, P. Murali and Petrella, Jeffrey R. and Wong, Terence Z. and Arnold, Steven E. and Karlawish, Jason H. and Wolk, David and Smith, Charles D. and Jicha, Greg and Hardy, Peter and Sinha, Partha and Oates, Elizabeth and Conrad, Gary and Lopez, Oscar L. and Oakley, MaryAnn and Simpson, Donna M. and Porsteinsson, Anton P. and Goldstein, Bonnie S. and Martin, Kim and Makino, Kelly M. and Ismail, M. Saleem and Brand, Connie and Mulnard, Ruth A. and Thai, Gaby and Mc-Adams-Ortiz, Catherine and Womack, Kyle and Mathews, Dana and Quiceno, Mary and Diaz-Arrastia, Ramon and King, Richard and Weiner, Myron and Martin-Cook, Kristen and DeVous, Michael and Levey, Allan I. and Lah, James J. and Cellar, Janet S. and Burns, Jeffrey M. and Anderson, Heather S. and Swerdlow, Russell H. and Apostolova, Liana and Tingus, Kathleen and Woo, Ellen and Silverman, Daniel H. S. and Lu, Po H. and Bartzokis, George and Graff-Radford, Neill R. and Parfitt, Francine and Kendall, Tracy and Johnson, Heather and Farlow, Martin R. and Hake, AnnMarie and Matthews, Brandy R. and Herring, Scott and Hunt, Cynthia and van Dyck, Christopher H. and Carson, Richard E. and MacAvoy, Martha G. and Chertkow, Howard and Bergman, Howard and Hosein, Chris and Black, Sandra and Stefanovic, Bojana and Caldwell, Curtis and Hsiung, Ging-Yuek Robin and Feldman, Howard and Mudge, Benita and Assaly, Michele and Kertesz, Andrew and Rogers, John and Bernick, Charles and Munic, Donna and Kerwin, Diana and Mesulam, Marek-Marsel and Lipowski, Kristine and Wu, Chuang-Kuo and Johnson, Nancy and Sadowsky, Carl and Martinez, Walter and Villena, Teresa and Turner, Raymond Scott and Johnson, Kathleen and Reynolds, Brigid and Sperling, Reisa A. and Johnson, Keith A. and Marshall, Gad and Frey, Meghan and Lane, Barton and Rosen, Allyson and Tinklenberg, Jared and Sabbagh, Marwan N. and Belden, Christine M. and Jacobson, Sandra A. and Sirrel, Sherye A. and Kowall, Neil and Killiany, Ronald and Budson, Andrew E. and Norbash, Alexander and Johnson, Patricia Lynn and Allard, Joanne and Lerner, Alan and Ogrocki, Paula and Hudson, Leon and Fletcher, Evan and Carmichael, Owen and Olichney, John and DeCarli, Charles and Kittur, Smita and Borrie, Michael and Lee, T-Y and Bartha, Rob and Johnson, Sterling and Asthana, Sanjay and Carlsson, Cynthia M. and Potkin, Steven G. and Preda, Adrian and Nguyen, Dana and Tariot, Pierre and Reeder, Stephanie and Bates, Vernice and Capote, Horacio and Rainka, Michelle and Scharre, Douglas W. and Kataki, Maria and Adeli, Anahita and Zimmerman, Earl A. and Celmins, Dzintra and Brown, Alice D. and Pearlson, Godfrey D. and Blank, Karen and Anderson, Karen and Santulli, Robert B. and Kitzmiller, Tamar J. and Schwartz, Eben S. and Sink, Kaycee M. and Williamson, Jeff D. and Garg, Pradeep and Watkins, Franklin and Ott, Brian R. and Querfurth, Henry and Tremont, Geoffrey and Salloway, Stephen and Malloy, Paul and Correia, Stephen and Rosen, Howard J. and Miller, Bruce L. and Mintzer, Jacobo and Spicer, Kenneth and Bachman, David and Finger, Elizabether and Pasternak, Stephen and Rachinsky, Irina and Drost, Dick and Pomara, Nunzio and Hernando, Raymundo and Sarrael, Antero and Schultz, Susan K. and Ponto, Laura L. Boles and Shim, Hyungsub and Smith, Karen Elizabeth and Relkin, Norman and Chaing, Gloria and Raudin, Lisa and Smith, Amanda and Fargher, Kristin and Raj, Balebail Ashok and Neylan, Thomas and Grafman, Jordan and Davis, Melissa and Morrison, Rosemary and Hayes, Jacqueline and Finley, Shannon and Friedl, Karl and Fleischman, Debra and Arfanakis, Konstantinos and James, Olga and Massoglia, Dino and Fruehling, J. Jay and Harding, Sandra and Peskind, Elaine R. and Petrie, Eric C. and Li, Gail and Yesavage, Jerome A. and Taylor, Joy L. and Furst, Ansgar J.},
doi = {10.1038/ncomms11934},
eprint = {arXiv:1011.1669v3},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Iturria-Medina et al. - 2016 - Early role of vascular dysregulation on late-onset Alzheimer's disease based on multifactorial data-dr(2).pdf:pdf},
isbn = {9788578110796},
issn = {2041-1723},
journal = {Nat. Commun.},
mendeley-groups = {PHD/Machine Learning/MultimodalLearning,PhDThesis/Review},
pages = {11934},
pmid = {25246403},
title = {{Early role of vascular dysregulation on late-onset Alzheimer's disease based on multifactorial data-driven analysis}},
volume = {7},
year = {2016}
}
@article{Worsley2009,
abstract = {Purpose Non-ST-segment elevation myocardial infarction (NSTEMI) may be associated with total occlusion of the culprit artery, which is frequently not diagnosed on the standard 12-lead ECG. This may lead to missed opportunities for prompt reperfusion therapy. We sought to determine the prevalence of acute artery occlusion and location of culprit lesions involved in NSTEMI. Methods We examined 2219 consecutive patients with NSTEMI enrolled in a multicentre registry of acute percutaneous coronary intervention (PCI). The inclusion criteria were definite myocardial infarction (elevated troponin and/or CKMB with either symptoms and/or ST-segment depression) and invasive strategy within 72 hours of symptom onset. The patients were divided into 2 groups according to the initial TIMI flow (TIMI 0/I, "occluded"; vs TIMI II/ III, "patent"). Baseline characteristics, treatment, culprit artery distribution and in-hospital outcome were compared. Results The prevalence of total occlusion was 33.9{\%} in the entire cohort. In patients with total occlusion, the culprit lesion was more frequently located in the arteries supplying the infero-lateral territory (circumflex, CX; right coronary artery, RCA) compared to patients with patent arteries (CX: 31.2{\%} vs 18.8{\%}, p {\textless} 0.01; RCA: 31.2{\%} vs 22.6{\%}, p {\textless} 0.01; LAD: 26.6{\%} vs 38.2{\%}, p {\textless} 0.01). Patients with total occlusion had significantly shorter delays to PCI (pain to PCI: 951 [460-1730] min. vs 1302 [582-2221] min., p {\textless} 0.01; door to PCI: 360 [125-1138] min. vs 180 [791-1483] min., p {\textless} 0.01). Inhospital mortality, however, was similar in both groups (TIMI I vs TIMI II/III 2.7 vs 1.8; p = n. s.). Conclusion Totally occluded culprit lesions occur in one third of patients with NSTEMI in a real world setting and are more frequently located in CX and RCA, but may also be seen in LAD territories. Early risk stratification needs to be enhanced to improve identification of "Pseudo-NSTEMIs" that would benefit from urgent reperfusion as in STEMI.},
author = {Worsley, KJ and Taylor, JE and Carbonell, F and Chung, MK and Duerden, E and Bernhardt, B and Lyttelton, O and Boucher, M and Evans, AC},
doi = {10.1016/S1053-8119(09)70882-1},
issn = {10538119},
journal = {Neuroimage},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {jul},
pages = {S102},
title = {{SurfStat: A Matlab toolbox for the statistical analysis of univariate and multivariate surface and volumetric data using linear mixed effects models and random field theory}},
volume = {47},
year = {2009}
}
@article{Fletcher2013,
abstract = {Tensor-based morphometry is a powerful tool for automatically computing longitudinal change in brain structure. Because of bias in images and in the algorithm itself, however, a penalty term and inverse consistency are needed to control the over-reporting of nonbiological change. These may force a tradeoff between the intrinsic sensitivity and specificity, potentially leading to an under-reporting of authentic biological change with time. We propose a new method incorporating prior information about tissue boundaries (where biological change is likely to exist) that aims to keep the robustness and specificity contributed by the penalty term and inverse consistency while maintaining localization and sensitivity. Results indicate that this method has improved sensitivity without increased noise. Thus it will have enhanced power to detect differences within normal aging and along the spectrum of cognitive impairment.},
author = {Fletcher, Evan and Knaack, Alexander and Singh, Baljeet and Lloyd, Evan and Wu, Evan and Carmichael, Owen and Decarli, Charles},
doi = {10.1109/TMI.2012.2220153},
isbn = {1558-254X (Electronic)$\backslash$r0278-0062 (Linking)},
issn = {02780062},
journal = {IEEE Trans. Med. Imaging},
keywords = {Biomedical imaging,Kullback-Liebler,brain boundary shift,image matching,image registration,tensor-based morphometry (TBM)},
mendeley-groups = {PhDThesis/Review},
number = {2},
pages = {223--236},
pmid = {23014714},
title = {{Combining boundary-based methods with tensor-based morphometry in the measurement of longitudinal brain change}},
volume = {32},
year = {2013}
}
@inproceedings{Liu2013,
abstract = {Mild cognitive impairment (MCI) patients are at a high risk of turning into Alzheimer's disease (AD) within years. But it is known that not all MCI patients will progress to AD. Therefore, it is of great interest to accurately diagnose whether a MCI patient will convert to AD (namely MCI converter; MCI-C) or not (namely MCI non-converter; MCI-NC), for early diagnosis and proper treatment. In this paper, we propose a multi-task sparse representation classifier to discriminate between MCI-C and MCI-NC utilizing longitudinal neuroimaging data. Unlike the previous methods that explicitly combined the longitudinal information in a feature domain, thus requiring the same number of measurements in time, the proposed method is not limited to the availability of the data. Specifically, by means of multi-task learning, we impose a group constraint that the same training samples, ideally belonging to the same class, are used to represent the longitudinal feature vectors across time points. Then we utilize a sparse representation classifier for label decision. From a machine learning perspective, the proposed method can be considered as the combination of the generative and discriminative methods, which are known to be effective in classification enhancement. In our experiments on magnetic resonance brain images of 349 MCI subjects (164 MCI-C and 185 MCI-NC) from ADNI database, we demonstrate the validity of the proposed method, which also outperforms the competing methods. {\textcopyright}2013 Springer International Publishing.},
annote = {https://link.springer.com/content/pdf/10.1007{\%}2F978-3-319-02267-3{\_}31.pdf},
author = {Liu, Manhua and Suk, Heung Il and Shen, Dinggang},
booktitle = {Mach. Learn. Med. Imaging (MLMI). Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-02267-3_31},
isbn = {9783319022666},
issn = {16113349},
keywords = {MCI diagnosis,longitudinal MR images,multi-task sparse learning,sparse representation classifier},
mendeley-groups = {PhDThesis/Review},
pages = {243--250},
title = {{Multi-task sparse classifier for diagnosis of MCI conversion to AD with longitudinal MR images}},
volume = {8184},
year = {2013}
}
@misc{Sperling2011,
abstract = {The pathophysiological process of Alzheimer's disease (AD) is thought to begin many years before the diagnosis of AD dementia. This long "preclinical" phase of AD would provide a critical opportunity for therapeutic intervention; however, we need to further elucidate the link between the pathological cascade of AD and the emergence of clinical symptoms. The National Institute on Aging and the Alzheimer's Association convened an international workgroup to review the biomarker, epidemiological, and neuropsychological evidence, and to develop recommendations to determine the factors which best predict the risk of progression from "normal" cognition to mild cognitive impairment and AD dementia. We propose a conceptual framework and operational research criteria, based on the prevailing scientific evidence to date, to test and refine these models with longitudinal clinical research studies. These recommendations are solely intended for research purposes and do not have any clinical implications at this time. It is hoped that these recommendations will provide a common rubric to advance the study of preclinical AD, and ultimately, aid the field in moving toward earlier intervention at a stage of AD when some disease-modifying therapies may be most efficacious. {\textcopyright} 2011 The Alzheimer's Association. All rights reserved.},
author = {Sperling, Reisa A and Aisen, Paul S and Beckett, Laurel A and Bennett, David A and Craft, Suzanne and Fagan, Anne M and Iwatsubo, Takeshi and Jack, Clifford R and Kaye, Jeffrey and Montine, Thomas J and Park, Denise C and Reiman, Eric M and Rowe, Christopher C and Siemers, Eric and Stern, Yaakov and Yaffe, Kristine and Carrillo, Maria C and Thies, Bill and Morrison-Bogorad, Marcelle and Wagster, Molly V and Phelps, Creighton H.},
booktitle = {Alzheimer's Dement.},
doi = {10.1016/j.jalz.2011.03.003},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sperling et al. - 2011 - Toward defining the preclinical stages of Alzheimer's disease Recommendations from the National Institute on(2).pdf:pdf},
issn = {15525260},
keywords = {Amyloid,Biomarker,Neurodegeneration,Preclinical Alzheimer's disease,Prevention},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {may},
number = {3},
pages = {280--292},
pmid = {21514248},
publisher = {NIH Public Access},
title = {{Toward defining the preclinical stages of Alzheimer's disease: Recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease}},
volume = {7},
year = {2011}
}
@book{Oxtoby2014,
abstract = {{\textcopyright} Springer International Publishing Switzerland 2014. Characterising the time course of a disease with a protracted incubation period ultimately requires dense longitudinal studies, which can be prohibitively long and expensive. Considering what can be learned in the absence of such data, we estimate cohort-level biomarker trajectories by fitting cross-sectional data to a differential equation model, then integrating the fit. These fits inform our new stochastic differential equation model for synthesising individual-level biomarker trajectories for prognosis support. Our Bayesian multilevel regression model explicitly includes measurement noise estimation to avoid regression dilution bias. Applicable to any disease, here we perform experiments on Alzheimer's disease imaging biomarker data — volumes of regions of interest within the brain. We find that Alzheimer's disease imaging biomarkers are dynamic over timescales from a few years to a few decades.},
author = {Oxtoby, N.P. and Young, A.L. and Fox, N.C. and Daga, P. and Cash, D.M. and Ourselin, S. and Schott, J.M. and Alexander, D.C.},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
mendeley-groups = {PhDThesis/Review},
pages = {85--94},
title = {{Learning imaging biomarker trajectories from noisy Alzheimer's disease data using a Bayesian multilevel model}},
volume = {8677},
year = {2014}
}
@article{Zhang2012,
abstract = {Sparse learning has recently received increasing attentions in neuroimaging research such as brain disease diagnosis and progression. Most existing studies focus on cross-sectional analysis, i.e., learning a sparse model based on single time-point of data. However, in some brain imaging applications, multiple time-points of data are often available, thus longitudinal analysis can be performed to better uncover the underlying disease progression patterns. In this paper, we propose a novel temporally-constrained group sparse learning method aiming for longitudinal analysis with multiple time-points of data. Specifically, for each time-point, we train a sparse linear regression model by using the imaging data and the corresponding responses, and further use the group regularization to group the weights corresponding to the same brain region across different time-points together. Moreover, to reflect the smooth changes between adjacent time-points of data, we also include two smoothness regularization terms into the objective function, i.e., one fused smoothness term which requires the differences between two successive weight vectors from adjacent time-points should be small, and another output smoothness term which requires the differences between outputs of two successive models from adjacent time-points should also be small. We develop an efficient algorithm to solve the new objective function with both group-sparsity and smoothness regularizations. We validate our method through estimation of clinical cognitive scores using imaging data at multiple time-points which are available in the Alzheimer's disease neuroimaging initiative (ADNI) database.},
annote = {important},
author = {Zhang, Daoqiang and Liu, Jun and Shen, Dinggang},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Zhang, Liu, Shen - 2012 - Temporally-constrained group sparse learning for longitudinal data analysis(2).pdf:pdf},
journal = {Int. Conf. Med. Image Comput. Comput. Interv. MICCAI},
keywords = {Aging,Algorithms,Alzheimer Disease,Artificial Intelligence,Automated,Brain,Computer-Assisted,Humans,Image Enhancement,Image Interpretation,Longitudinal Studies,Magnetic Resonance Imaging,Pattern Recognition,Reproducibility of Results,Sensitivity and Specificity,Subtraction Technique,methods,pathology},
language = {eng},
mendeley-groups = {Review2,PhDThesis/Review},
number = {Pt 3},
pages = {264--271},
pmid = {23286139},
title = {{Temporally-constrained group sparse learning for longitudinal data analysis.}},
volume = {15},
year = {2012}
}
@article{Lorenzi2011,
abstract = {Mapping the effects of different clinical conditions on the evolution of the brain structural changes is of central interest in the field of neuroimaging. A reliable description of the cross-sectional longitudinal changes requires the consistent integration of intra and inter-subject variability in order to detect the subtle modifications in populations. In computational anatomy, the changes in the brain are often measured by deformation fields obtained through non rigid registration, and the stationary velocity field (SVF) parametrization provides a computationally efficient registration scheme. The aim of this study is to extend this framework into an efficient and robust multilevel one for accurately modeling the longitudinal changes in populations. This setting is used to investigate the subtle effects of the positivity of the CSF Abeta1-42 levels on brain atrophy in healthy aging. Thanks to the higher sensitivity of our framework, we obtain statistically significant results that highlight the relationship between brain damage and positivity to the marker of Alzheimer's disease and suggest the presence of a presymptomatic pattern of the disease progression.},
author = {Lorenzi, Marco and Ayache, Nicholas and Frisoni, Giovanni B and Pennec, Xavier},
doi = {10.1007/978-3-642-23629-7_81},
isbn = {9783642236280},
issn = {03029743},
journal = {Med. Image Comput. Comput. Assist. Interv.},
keywords = {80 and over,Aged,Aging,Algorithms,Alzheimer Disease,Alzheimer Disease: metabolism,Amyloid beta-Peptides,Amyloid beta-Peptides: metabolism,Brain,Brain Mapping,Brain Mapping: methods,Brain: metabolism,Brain: pathology,Computer-Assisted,Disease Progression,Female,Humans,Image Processing,Male,Models,Normal Distribution,Peptide Fragments,Peptide Fragments: metabolism,Statistical},
mendeley-groups = {PhDThesis/Review},
number = {Pt 2},
pages = {663--70},
pmid = {21995086},
title = {{Mapping the effects of Abeta1-42 levels on the longitudinal changes in healthy aging: hierarchical modeling based on stationary velocity fields.}},
volume = {14},
year = {2011}
}
@article{Zhang2016a,
abstract = {We used a data-driven Bayesian model to automatically identify distinct latent factors of overlapping atrophy patterns from voxelwise structural MRIs of late-onset Alzheimer's disease (AD) dementia patients. Our approach estimated the extent to which multiple distinct atrophy patterns were expressed within each participant rather than assuming that each participant expressed a single atrophy factor. The model revealed a temporal atrophy factor (medial temporal cortex, hippocampus, and amygdala), a subcortical atrophy factor (striatum, thalamus, and cerebellum), and a cortical atrophy factor (frontal, parietal, lateral temporal, and lateral occipital cortices). To explore the influence of each factor in early AD, atrophy factor compositions were inferred in beta-amyloid-positive (A$\beta$+) mild cognitively impaired (MCI) and cognitively normal (CN) participants. All three factors were associated with memory decline across the entire clinical spectrum, whereas the cortical factor was associated with executive function decline in A$\beta$+ MCI participants and AD dementia patients. Direct comparison between factors revealed that the temporal factor showed the strongest association with memory, whereas the cortical factor showed the strongest association with executive function. The subcortical factor was associated with the slowest decline for both memory and executive function compared with temporal and cortical factors. These results suggest that distinct patterns of atrophy influence decline across different cognitive domains. Quantification of this heterogeneity may enable the computation of individual-level predictions relevant for disease monitoring and customized therapies. Factor compositions of participants and code used in this article are publicly available for future research.},
annote = {From Duplicate 2 (Bayesian model reveals latent atrophy factors with dissociable cognitive trajectories in Alzheimer's disease - Zhang, Xiuming; Mormino, Elizabeth C.; Sun, Nanbo; Sperling, Reisa A.; Sabuncu, Mert R.; Yeo, B. T. Thomas)

SUBTYPING PAPER

uSES LONGITUDINA LFOR VALIDATION, BUT NO FOR THE MAIN METHOD},
author = {Zhang, Xiuming and Mormino, Elizabeth C. and Sun, Nanbo and Sperling, Reisa A. and Sabuncu, Mert R. and Yeo, B.T. Thomas Thomas and Initiative, Alzheimer's Disease Neuroimaging},
doi = {10.1073/pnas.1611073113},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Zhang et al. - 2016 - Bayesian model reveals latent atrophy factors with dissociable cognitive trajectories in Alzheimer's disease(2).pdf:pdf},
isbn = {1573-2509 (Electronic)},
issn = {0027-8424},
journal = {Proc. Natl. Acad. Sci.},
mendeley-groups = {Review2,PhDThesis/Review},
month = {jul},
number = {42},
pages = {E6535--E6544},
pmid = {27702899},
publisher = {Cold Spring Harbor Laboratory},
title = {{Bayesian model reveals latent atrophy factors with dissociable cognitive trajectories in Alzheimer's disease}},
volume = {113},
year = {2016}
}
@misc{DeFlores2015,
abstract = {Hippocampal atrophy, as evidenced using magnetic resonance imaging (MRI), is one of the most validated, easily accessible and widely used biomarkers of Alzheimer's disease (AD). However, its imperfect sensitivity and specificity have highlighted the need to improve the analysis of MRI data. Based on neuropathological data showing a differential vulnerability of hippocampal subfields to AD processes, neuroimaging researchers have tried to capture corresponding morphological changes within the hippocampus. The present review provides an overview of the methodological developments that allow the assessment of hippocampal subfield morphology in vivo, and summarizes the results of studies looking at the effects of AD and normal aging on these structures. Most studies highlighted a focal atrophy of the CA1 subfield in the early (predementia or even preclinical) stages of AD, before atrophy becomes more widespread at the dementia stage, consistent with the pathological literature. Preliminary studies have indicated that looking at this focal atrophy pattern rather than standard whole hippocampus volumetry improves diagnostic accuracy at the mild cognitive impairment (MCI) stage. However, controversies remain regarding changes in hippocampal subfield structure in normal aging and regarding correlations between specific subfield volume and memory abilities, very likely because of the strong methodological variability between studies. Overall, hippocampal subfield analysis has proven to be a promising technique in the study of AD. However, harmonization of segmentation protocols and studies on larger samples are needed to enable accurate comparisons between studies and to confirm the clinical utility of these techniques.},
author = {de Flores, Robin and {La Joie}, Renaud and Ch{\'{e}}telat, Ga{\"{e}}l},
booktitle = {Neuroscience},
doi = {10.1016/j.neuroscience.2015.08.033},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/de Flores, La Joie, Ch{\'{e}}telat - 2015 - Structural imaging of hippocampal subfields in healthy aging and Alzheimer's disease.pdf:pdf},
isbn = {1873-7544 (Electronic) 0306-4522 (Linking)},
issn = {18737544},
keywords = {Aging,Alzheimer's disease,Biomarker,CA1,Hippocampus,Magnetic resonance imaging},
mendeley-groups = {PHD/Shape Analysis,Papers bib/hipppaper/subfields,PhDThesis/Hippo},
month = {nov},
pages = {29--50},
pmid = {26306871},
publisher = {Pergamon},
title = {{Structural imaging of hippocampal subfields in healthy aging and Alzheimer's disease}},
volume = {309},
year = {2015}
}
@inproceedings{Wang2012b,
abstract = {Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions. Regression analysis has been studied to relate neuroimagingmeasures to cognitive status. However, whether these measures have further predictive power to infer a trajectory of cognitive performance over time is still an under-explored but important topic in AD research. We propose a novel high-order multi-task learning model to address this issue. The proposed model explores the temporal correlations existing in imaging and cognitive data by structured sparsity-inducing norms. The sparsity of the model enables the selection of a small number of imaging measures while maintaining high prediction accuracy. The empirical studies, using the longitudinal imaging and cognitive data of the ADNI cohort, have yielded promising results.},
author = {Wang, Hua and Nie, Feiping and Huang, Heng and Yan, Jingwen and Kim, Sungeun and Risacher, Shannon L. and Saykin, Andrew J. and Shen, Li},
booktitle = {Adv. Neural Inf. Process. Syst.},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wang et al. - 2012 - High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer's Disease Progr(2).pdf:pdf},
isbn = {9781627480031},
issn = {10495258},
mendeley-groups = {PhDThesis/Review},
pages = {1277--1285},
title = {{High-order multi-task feature learning to identify longitudinal phenotypic markers for Alzheimer's disease progression prediction}},
volume = {2},
year = {2012}
}

@article{Liu2014,
abstract = {The accurate diagnosis of Alzheimer's disease (AD) plays a significant role in patient care, especially at the early stage, because the consciousness of the severity and the progression risks allows the patients to take prevention measures before irreversible brain damages are shaped. Although many studies have applied machine learning methods for computer-aided-diagnosis (CAD) of AD recently, a bottleneck of the diagnosis performance was shown in most of the existing researches, mainly due to the congenital limitations of the chosen learning models. In this study, we design a deep learning architecture, which contains stacked auto-encoders and a softmax output layer, to overcome the bottleneck and aid the diagnosis of AD and its prodromal stage, Mild Cognitive Impairment (MCI). Compared to the previous workflows, our method is capable of analyzing multiple classes in one setting, and requires less labeled training samples and minimal domain prior knowledge. A significant performance gain on classification of all diagnosis groups was achieved in our experiments.},
author = {Liu, Siqi Sidong and Liu, Siqi Sidong and Cai, Weidong and Pujol, Sonia and Kikinis, Ron and Feng, Dagan},
doi = {10.1109/ISBI.2014.6868045},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Liu et al. - 2014 - Early diagnosis of Alzheimer's disease with deep learning(2).pdf:pdf},
isbn = {978-1-4673-1961-4},
issn = {1945-7928},
journal = {2014 IEEE 11th Int. Symp. Biomed. Imaging},
keywords = {Alzheimer disease diagnosis,Alzheimer's disease,Feature extraction,Magnetic resonance imaging,Neurons,Support vector machines,Training,biomedical MRI,brain,classification,cognition,computer-aided-diagnosis,diseases,health care,image classification,image coding,irreversible brain damages,learning (artificial intelligence),machine learning methods,magnetic resonance imaging,medical disorders,medical image processing,mild cognitive impairment,minimal domain prior knowledge,neuroimaging,patient care,stacked auto-encoders},
mendeley-groups = {PHD/Machine Learning/Medical deep learning,Papers bib/deeplearning paper,PHD,PhDThesis/Review},
month = {apr},
pages = {1015--1018},
publisher = {IEEE},
title = {{Early diagnosis of Alzheimer's disease with deep learning}},
year = {2014}
}
@article{Cui2018,
abstract = {{\textcopyright} 2018 IEEE. Alzheimer's disease (AD) is a kind of neurodegenerative disorder with progressive impairment of memory and cognitive functions. Structural magnetic resonance images (MRI) is widely used as an important imaging modality for AD diagnosis. Most of existing methods for MRI classification are based on image data of single time point. However, the longitudinal analysis of sequential MR images is also important to model and measure the progression of the disease along the time axis. In this paper, we present a classification framework based on combination of Multi-Layer Perceptron (MLP) neural network and Recurrent Neural Networks (RNN) for longitudinal analysis of MR images for AD diagnosis. First, MLP is constructed to learn the spatial features of MR images with the task of AD classification. After that, RNN with cascaded two bidirectional gated recurrent units (BGRU) layers is trained on the MLP outputs for extracting the longitudinal features from the imaging data of multiple time points, providing a final classification predicting score. The proposed method can automatically learn the spatial and longitudinal features from the imaging data of multiple time points with variable length for classification. Our method is evaluated using T1-weighted structural MR images on 428 subjects including 198 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show the proposed method achieves an accuracy of 89.7{\%} for AD classification, demonstrating the promising classification performance.},
author = {Cui, Ruoxuan and Liu, Manhua and Li, Gang},
doi = {10.1109/ISBI.2018.8363833},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Cui, Liu, Li - 2018 - Longitudinal analysis for Alzheimer's disease diagnosis using RNN(2).pdf:pdf},
isbn = {9781538636367},
issn = {19458452},
journal = {Proc. - Int. Symp. Biomed. Imaging},
keywords = {Alzheimer's disease,Convolutional neural network,Deep learning,Longitudinal study,Recurrent neural network},
mendeley-groups = {Review2/Scopus,PhDThesis/Review},
pages = {1398--1401},
publisher = {IEEE},
title = {{Longitudinal analysis for Alzheimer's disease diagnosis using RNN}},
volume = {April},
year = {2018}
}
@article{Hayasaka2004,
abstract = {Because of their increased sensitivity to spatially extended signals, cluster-size tests are widely used to detect changes and activations in brain images. However, when images are nonstationary, the cluster-size distribution varies depending on local smoothness. Clusters tend to be large in smooth regions, resulting in increased false positives, while in rough regions, clusters tend to be small, resulting in decreased sensitivity. Worsley et al. proposed a random field theory (RFT) method that adjusts cluster sizes according to local roughness of images [Worsley, K.J., 2002. Nonstationary FWHM and its effect on statistical inference of fMRI data. Presented at the 8th International Conference on Functional Mapping of the Human Brain, June 2-6, 2002, Sendai, Japan. Available on CD-ROM in NeuroImage 16 (2) 779-780; Hum. Brain Mapp. 8 (1999) 98]. In this paper, we implement this method in a permutation test framework, which requires very few assumptions, is known to be exact [J. Cereb. Blood Flow Metab. 16 (1996) 7] and is robust [NeuroImage 20 (2003) 2343]. We compared our method to stationary permutation, stationary RFT, and nonstationary RFT methods. Using simulated data, we found that our permutation test performs well under any setting examined, whereas the nonstationary RFT test performs well only for smooth images under high df. We also found that the stationary RFT test becomes anticonservative under nonstationarity, while both nonstationary RFT and permutation tests remain valid under nonstationarity. On a real PET data set we found that, though the nonstationary tests have reduced sensitivity due to smoothness estimation variability, these tests have better sensitivity for clusters in rough regions compared to stationary cluster-size tests. We include a detailed and consolidated description of Worsley nonstationary RFT cluster-size test. {\textcopyright} 2004 Elsevier Inc. All rights reserved.},
author = {Hayasaka, Satoru and Phan, K. Luan and Liberzon, Israel and Worsley, Keith J. and Nichols, Thomas E.},
doi = {10.1016/j.neuroimage.2004.01.041},
issn = {10538119},
journal = {Neuroimage},
keywords = {Cluster size inference,Permutation,Stationary},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {jun},
number = {2},
pages = {676--687},
pmid = {15193596},
title = {{Nonstationary cluster-size inference with random field and permutation methods}},
volume = {22},
year = {2004}
}
@article{Ikram2017,
abstract = {{\textcopyright} 2017, Springer Science+Business Media B.V. The Rotterdam Study is a prospective cohort study ongoing since 1990 in the city of Rotterdam in The Netherlands. The study targets cardiovascular, endocrine, hepatic, neurological, ophthalmic, psychiatric, dermatological, otolaryngological, locomotor, and respiratory diseases. As of 2008, 14,926 subjects aged 45 years or over comprise the Rotterdam Study cohort. Since 2016, the cohort is being expanded by persons aged 40 years and over. The findings of the Rotterdam Study have been presented in over 1500 research articles and reports (see www.erasmus-epidemiology.nl/rotterdamstudy). This article gives the rationale of the study and its design. It also presents a summary of the major findings and an update of the objectives and methods.},
author = {Ikram, M. Arfan and Brusselle, Guy G.O. and Murad, Sarwa Darwish and van Duijn, Cornelia M. and Franco, Oscar H. and Goedegebure, Andr{\'{e}} and Klaver, Caroline C.W. and Nijsten, Tamar E.C. and Peeters, Robin P. and Stricker, Bruno H. and Tiemeier, Henning and Uitterlinden, Andr{\'{e}} G. and Vernooij, Meike W. and Hofman, Albert},
doi = {10.1007/s10654-017-0321-4},
issn = {15737284},
journal = {Eur. J. Epidemiol.},
keywords = {Biomarkers,Cardiovascular diseases,Cohort study,Dermatological diseases,Endocrine diseases,Epidemiologic methods,Genetic epidemiology,Liver diseases,Neurological diseases,Oncology,Ophthalmic diseases,Otolaryngological diseases,Pharmacoepidemiology,Psychiatric diseases,Renal diseases,Respiratory diseases},
mendeley-groups = {Review2,PhDThesis/Review},
month = {sep},
number = {9},
pages = {807--850},
pmid = {29064009},
title = {{The Rotterdam Study: 2018 update on objectives, design and main results}},
volume = {32},
year = {2017}
}
@article{Yang2018a,
abstract = {Alzheimer's disease (AD) is a neurodegenerative disease with an irreversible and progressive process. Close monitoring of AD is essential for making adjustments in the treatment plan. Since clinical scores can indicate the disease status effectively, the prediction of the scores based on the magnetic resonance imaging (MRI data is highly desirable. Different from previous studies at a single time point, we propose to build a model to explore the relationship between MRI data and scores, thereby predicting longitudinal scores at future time points from the corresponding MRI data. The model incorporates three parts, correntropy regularized joint learning-based feature selection, deep polynomial network based feature encoding, and finally, support vector regression. The regression process is carried out for two scenarios. One is to use baseline data for predictions at future time points, and the other is to combine all the previous data for the prediction at the next time point. Meanwhile, the missing scores are filled in the second scenario to address the incompleteness presented in the data. The simulation results demonstrate that the proposed model accurately describes the relationship between MRI data and scores, and thus it can be effective in predicting longitudinal scores.},
author = {Yang, Mengya and Yang, Peng and Elazab, Ahmed and Hou, Wen and Li, Xia and Wang, Tianfu and Zou, Wenbin and Lei, Baiying},
doi = {10.1109/EMBC.2018.8512549},
isbn = {9781538636466},
issn = {1557170X},
journal = {Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS},
language = {eng},
mendeley-groups = {Review2,PhDThesis/Review},
month = {jul},
pages = {1254--1257},
pmid = {30440618},
title = {{Join and Deep Ensemble Regression of Clinical Scores for Alzheimer's Disease Using Longitudinal and Incomplete Data.}},
volume = {2018-July},
year = {2018}
}
@article{Platero2019,
abstract = {{\textcopyright} 2018 Springer Science+Business Media, LLC, part of Springer Nature Hippocampal atrophy measures from magnetic resonance imaging (MRI) are powerful tools for monitoring Alzheimer's disease (AD) progression. In this paper, we introduce a longitudinal image analysis framework based on robust registration and simultaneous hippocampal segmentation and longitudinal marker classification of brain MRI of an arbitrary number of time points. The framework comprises two innovative parts: a longitudinal segmentation and a longitudinal classification step. The results show that both steps of the longitudinal pipeline improved the reliability and the accuracy of the discrimination between clinical groups. We introduce a novel approach to the joint segmentation of the hippocampus across multiple time points; this approach is based on graph cuts of longitudinal MRI scans with constraints on hippocampal atrophy and supported by atlases. Furthermore, we use linear mixed effect (LME) modeling for differential diagnosis between clinical groups. The classifiers are trained from the average residue between the longitudinal marker of the subjects and the LME model. In our experiments, we analyzed MRI-derived longitudinal hippocampal markers from two publicly available datasets (Alzheimer's Disease Neuroimaging Initiative, ADNI and Minimal Interval Resonance Imaging in Alzheimer's Disease, MIRIAD). In test/retest reliability experiments, the proposed method yielded lower volume errors and significantly higher dice overlaps than the cross-sectional approach (volume errors: 1.55{\%} vs 0.8{\%}; dice overlaps: 0.945 vs 0.975). To diagnose AD, the discrimination ability of our proposal gave an area under the receiver operating characteristic (ROC) curve (AUC) (Formula presented.) 0.947 for the control vs AD, AUC (Formula presented.) 0.720 for mild cognitive impairment (MCI) vs AD, and AUC (Formula presented.) 0.805 for the control vs MCI.},
author = {Platero, Carlos and Lin, Lin and Tobar, M. Carmen},
doi = {10.1007/s12021-018-9380-2},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Platero, Lin, Tobar - 2019 - Longitudinal Neuroimaging Hippocampal Markers for Diagnosing Alzheimer's Disease(2).pdf:pdf},
issn = {15392791},
journal = {Neuroinformatics},
keywords = {Alzheimer's disease,Hippocampal segmentation,Longitudinal analysis,MRI},
mendeley-groups = {Review2/Scopus,Review2/New papers20182019,PhDThesis/Review},
month = {jan},
number = {1},
pages = {43--61},
publisher = {Springer US},
title = {{Longitudinal Neuroimaging Hippocampal Markers for Diagnosing Alzheimer's Disease}},
volume = {17},
year = {2019}
}
@article{Marinescu2019,
abstract = {Current models of progression in neurodegenerative diseases use neuroimaging measures that are averaged across pre-defined regions of interest (ROIs). Such models are unable to recover fine details of atrophy patterns; they tend to impose an assumption of strong spatial correlation within each ROI and no correlation among ROIs. Such assumptions may be violated by the influence of underlying brain network connectivity on pathology propagation – a strong hypothesis e.g. in Alzheimer's Disease. Here we present DIVE: Data-driven Inference of Vertexwise Evolution. DIVE is an image-based disease progression model with single-vertex resolution, designed to reconstruct long-term patterns of brain pathology from short-term longitudinal data sets. DIVE clusters vertex-wise (i.e. point-wise) biomarker measurements on the cortical surface that have similar temporal dynamics across a patient population, and concurrently estimates an average trajectory of vertex measurements in each cluster. DIVE uniquely outputs a parcellation of the cortex into areas with common progression patterns, leading to a new signature for individual diseases. DIVE further estimates the disease stage and progression speed for every visit of every subject, potentially enhancing stratification for clinical trials or management. On simulated data, DIVE can recover ground truth clusters and their underlying trajectory, provided the average trajectories are sufficiently different between clusters. We demonstrate DIVE on data from two cohorts: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Dementia Research Centre (DRC), UK. The DRC cohort contains patients with Posterior Cortical Atrophy (PCA) as well as typical Alzheimer's disease (tAD). DIVE finds similar spatial patterns of atrophy for tAD subjects in the two independent datasets (ADNI and DRC), and further reveals distinct patterns of pathology in different diseases (tAD vs PCA) and for distinct types of biomarker data – cortical thickness from Magnetic Resonance Imaging (MRI) vs amyloid load from Positron Emission Tomography (PET). We demonstrate that DIVE stages have potential clinical relevance, despite being based only on imaging data, by showing that the stages correlate with cognitive test scores. Finally, DIVE can be used to estimate a fine-grained spatial distribution of pathology in the brain using any kind of voxelwise or vertexwise measures including Jacobian compression maps, fractional anisotropy (FA) maps from diffusion tensor imaging (DTI) or other PET measures.},
author = {Marinescu, Răzvan V. and Eshaghi, Arman and Lorenzi, Marco and Young, Alexandra L. and Oxtoby, Neil P. and Garbarino, Sara and Crutch, Sebastian J. and Alexander, Daniel C.},
doi = {10.1016/j.neuroimage.2019.02.053},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Marinescu et al. - 2019 - DIVE A spatiotemporal progression model of brain pathology in neurodegenerative disorders(5).pdf:pdf},
issn = {10959572},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Cortical thickness,Disease progression model,Posterior cortical atrophy,Vertex-wise measures},
mendeley-groups = {PHD/stay{\_}MLorenzi{\_}Papers,PhDThesis/Review},
month = {may},
pages = {166--177},
publisher = {Academic Press},
title = {{DIVE: A spatiotemporal progression model of brain pathology in neurodegenerative disorders}},
volume = {192},
year = {2019}
}
@inproceedings{Young2015a,
abstract = {The event-based model constructs a discrete picture of disease progression from cross-sectional data sets, with each event corresponding to a new biomarker becoming abnormal. However, it relies on the assumption that all subjects follow a single event sequence. This is a major simplification for sporadic disease data sets, which are highly heterogeneous, include distinct subgroups, and contain significant proportions of outliers. In this work we relax this assumption by considering two extensions to the event-based model: a generalised Mallows model, which allows subjects to deviate from the main event sequence, and a Dirichlet process mixture of generalised Mallows models, which models clusters of subjects that follow different event sequences, each of which has a corresponding variance. We develop a Gibbs sampling technique to infer the parameters of the two models from multi-modal biomarker data sets. We apply our technique to data from the Alzheimer's Disease Neuroimaging Initiative to determine the sequence in which brain regions become abnormal in sporadic Alzheimer's disease, as well as the heterogeneity of that sequence in the cohort. We find that the generalised Mallows model estimates a larger variation in the event sequence across subjects than the original event-based model. Fitting a Dirichlet process model detects three subgroups of the population with different event sequences. The Gibbs sampler additionally provides an estimate of the uncertainty in each of the model parameters, for example an individual's latent disease stage and cluster assignment. The distributions and mixtures of sequences that this new family of models introduces offer better characterisation of disease progression of heterogeneous populations, new insight into disease mechanisms, and have the potential for enhanced disease stratification and differential diagnosis.},
author = {Young, Alexandra L. and Oxtoby, Neil P. and Huang, Jonathan and Marinescu, Razvan V. and Daga, Pankaj and Cash, David M. and Fox, Nick C. and Ourselin, Sebastien and Schott, Jonathan M. and Alexander, Daniel C.},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-19992-4_56},
isbn = {3-540-54246-9},
issn = {16113349},
mendeley-groups = {PhDThesis/Review},
pages = {711--722},
pmid = {26221676},
publisher = {Springer, Cham},
title = {{Multiple orderings of events in disease progression}},
volume = {9123},
year = {2015}
}
@article{Yancheva2015,
abstract = {A central issue in cognitive neuroscience today concerns how distributed neural networks in the brain that are used in language learning and processing can be involved in non-linguistic cognitive sequence learning. This issue is informed by a wealth of functional neurophysiology studies of sentence comprehension, along with a number of recent studies that examined the brain processes involved in learning non-linguistic sequences, or artificial grammar learning (AGL). The current research attempts to reconcile these data with several current neurophysiologically based models of sentence processing, through the specification of a neural network model whose architecture is constrained by the known cortico-striato-thalamo-cortical (CSTC) neuroanatomy of the human language system. The challenge is to develop simulation models that take into account constraints both from neuranatomical connectivity, and from functional imaging data, and that can actually learn and perform the same kind of language and artificial syntax tasks. In our proposed model, structural cues encoded in a recurrent cortical network in BA47 activate a CSTC circuit to modulate the flow of lexical semantic information from BA45 to an integrated representation of meaning at the sentence level in BA44/6. During language acquisition, corticostriatal plasticity is employed to allow closed class structure to drive thematic role assignment. From the AGL perspective, repetitive internal structure in the AGL strings is encoded in BA47, and activates the CSTC circuit to predict the next element in the sequence. Simulation results from Caplan's [Caplan, D., Baker, C., {\&} Dehaut, F. (1985). Syntactic determinants of sentence comprehension in aphasia. Cognition, 21, 117-175] test of syntactic comprehension, and from Gomez and Schvaneveldts' [Gomez, R. L., {\&} Schvaneveldt, R. W. (1994). What is learned from artificial grammars?. Transfer tests of simple association. Journal of Experimental Psychology: Learning, Memory and Cognition, 20, 396-410] artificial grammar learning experiments are presented. These results are discussed in the context of a brain architecture for learning grammatical structure for multiple natural languages, and non-linguistic sequences. {\textcopyright}2008 Elsevier Inc. All rights reserved.},
author = {Yancheva, Maria and Fraser, Kathleen and Rudzicz, Frank},
doi = {10.1016/j.bandl.2008.08.002},
isbn = {0093-934X},
issn = {0093934X},
journal = {6th Work. Speech Lang. Process. Assist. Technol.},
keywords = {Basal ganglia,Cortico-striatal system,Language acquisition,Neural network,Non-linguistic sequence,Syntactic comprehension},
mendeley-groups = {PhDThesis/Review},
pages = {134},
pmid = {18835637},
title = {{Using linguistic features longitudinally to predict clinical scores for Alzheimer's disease and related dementias}},
year = {2015}
}
@article{Costafreda2011,
abstract = {The hippocampus is involved at the onset of the neuropathological pathways leading to Alzheimer's disease (AD). Individuals with mild cognitive impairment (MCI) are at increased risk of AD. Hippocampal volume has been shown to predict which MCI subjects will convert to AD. Our aim in the present study was to produce a fully automated prognostic procedure, scalable to high throughput clinical and research applications, for the prediction of MCI conversion to AD using 3D hippocampal morphology. We used an automated analysis for the extraction and mapping of the hippocampus from structural magnetic resonance scans to extract 3D hippocampal shape morphology, and we then applied machine learning classification to predict conversion from MCI to AD. We investigated the accuracy of prediction in 103 MCI subjects (mean age 74.1. years) from the longitudinal AddNeuroMed study. Our model correctly predicted MCI conversion to dementia within a year at an accuracy of 80{\%} (sensitivity 77{\%}, specificity 80{\%}), a performance which is competitive with previous predictive models dependent on manual measurements. Categorization of MCI subjects based on hippocampal morphology revealed more rapid cognitive deterioration in MMSE scores (p{\textless}0.01) and CERAD verbal memory (p{\textless}0.01) in those subjects who were predicted to develop dementia relative to those predicted to remain stable. The pattern of atrophy associated with increased risk of conversion demonstrated initial degeneration in the anterior part of the cornus ammonis 1 (CA1) hippocampal subregion. We conclude that automated shape analysis generates sensitive measurements of early neurodegeneration which predates the onset of dementia and thus provides a prognostic biomarker for conversion of MCI to AD. {\textcopyright} 2011 Elsevier Inc.},
author = {Costafreda, Sergi G. and Dinov, Ivo D. and Tu, Zhuowen and Shi, Yonggang and Liu, Cheng Yi and Kloszewska, Iwona and Mecocci, Patrizia and Soininen, Hilkka and Tsolaki, Magda and Vellas, Bruno and Wahlund, Lars Olof and Spenger, Christian and Toga, Arthur W. and Lovestone, Simon and Simmons, Andrew},
doi = {10.1016/j.neuroimage.2011.01.050},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Costafreda et al. - 2011 - Automated hippocampal shape analysis predicts the onset of dementia in mild cognitive impairment.pdf:pdf},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Automated methods,Hippocampus,Mild cognitive impairment,Neuroimaging,Prognosis},
mendeley-groups = {Papers bib/hipppaper/shape,PhDThesis/Hippo},
month = {may},
number = {1},
pages = {212--219},
publisher = {Academic Press},
title = {{Automated hippocampal shape analysis predicts the onset of dementia in mild cognitive impairment}},
volume = {56},
year = {2011}
}
@article{Jedynak2012,
abstract = {While neurodegenerative diseases are characterized by steady degeneration over relatively long timelines, it is widely believed that the early stages are the most promising for therapeutic intervention, before irreversible neuronal loss occurs. Developing a therapeutic response requires a precise measure of disease progression. However, since the early stages are for the most part asymptomatic, obtaining accurate measures of disease progression is difficult. Longitudinal databases of hundreds of subjects observed during several years with tens of validated biomarkers are becoming available, allowing the use of computational methods. We propose a widely applicable statistical methodology for creating a disease progression score (DPS), using multiple biomarkers, for subjects with a neurodegenerative disease. The proposed methodology was evaluated for Alzheimer's disease (AD) using the publicly available AD Neuroimaging Initiative (ADNI) database, yielding an Alzheimer's DPS or ADPS score for each subject and each time-point in the database. In addition, a common description of biomarker changes was produced allowing for an ordering of the biomarkers. The Rey Auditory Verbal Learning Test delayed recall was found to be the earliest biomarker to become abnormal. The group of biomarkers comprising the volume of the hippocampus and the protein concentration amyloid beta and Tau were next in the timeline, and these were followed by three cognitive biomarkers. The proposed methodology thus has potential to stage individuals according to their state of disease progression relative to a population and to deduce common behaviors of biomarkers in the disease itself. ?? 2012 Elsevier Inc.},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Jedynak, Bruno M. and Lang, Andrew and Liu, Bo and Katz, Elyse and Zhang, Yanwei and Wyman, Bradley T and Raunig, David and Jedynak, Pierre and Caffo, Brian and Prince, Jerry L and Jedynak, C. Pierre and Caffo, Brian and Prince, Jerry L},
doi = {10.1016/j.neuroimage.2012.07.059},
eprint = {NIHMS150003},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Jedynak et al. - 2012 - A computational neurodegenerative disease progression score Method and results with the Alzheimer's disease n(2).pdf:pdf},
isbn = {1095-9572 (Electronic)$\backslash$r1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Biomarkers,Disease progression score,Neurodegenerative diseases,biomarkers,disease progression score},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {1478--1486},
pmid = {22885136},
title = {{A computational neurodegenerative disease progression score: Method and results with the Alzheimer's disease neuroimaging initiative cohort}},
volume = {63},
year = {2012}
}
@article{Venkatraghavan2017,
annote = {NOT LONGITUDINAL},
author = {Venkatraghavan, Vikram and Bron, Esther E and Niessen, Wiro J and Klein, Stefan},
doi = {10.1007/978-3-319-59050-9},
isbn = {978-3-319-59049-3},
mendeley-groups = {PhDThesis/Review},
pages = {121--133},
title = {{A Discriminative Event Based Model for Alzheimer's Disease Progression Modeling}},
volume = {10265},
year = {2017}
}
@article{Liu2015c,
abstract = {Objective: We aimed to examine the association of apolipoprotein E (APOE) $\epsilon$4 genotype with neuroimaging markers of Alzheimer's disease: hippocampal volume, brain amyloid deposition and cerebral metabolism. Methods: We performed a systematic review and metaanalysis of 14 cross-sectional studies identified in Pubmed from 1996 to 2014 (n=1628). The pooled standard mean difference (SMD) was used to estimate the association between APOE and hippocampal volume and amyloid deposition. Meta-analysis was performed using effect size signed differential mapping using coordinates extracted from clusters with statistically significant difference in cerebral metabolic rate for glucose between APOE $\epsilon$4+ and $\epsilon$4- groups. Results: APOE $\epsilon$4 carrier status was associated with atrophic hippocampal volume (pooled SMD: -0.47; 95{\%} CI -0.82 to -0.13; p=0.007) and increased cerebral amyloid positron emission tomography tracer ( pooled SMD: 0.62, 95{\%} CI 0.27 to 0.98, p=0.0006). APOE $\epsilon$4 was also associated with decreased cerebral metabolism, especially in right middle frontal gyrus. Conclusions: APOE $\epsilon$4 was associated with atrophic hippocampal volume in MRI markers, increased cerebral amyloid deposition and cerebral hypometabolism. Theses associations may indicate the potential role of the APOE gene in the pathophysiology of Alzheimer's disease.},
author = {Liu, Ying and Yu, Jin Tai and Wang, Hui Fu and Han, Pei Ran and Tan, Chen Chen and Wang, Chong and Meng, Xiang Fei and Risacher, Shannon L. and Saykin, Andrew J. and Tan, Lan},
doi = {10.1136/jnnp-2014-307719},
issn = {1468330X},
journal = {J. Neurol. Neurosurg. Psychiatry},
mendeley-groups = {Papers bib/cimlr{\_}extension,Papers bib,Papers bib/hipppaper,PhDThesis/Hippo},
month = {feb},
number = {2},
pages = {127--134},
publisher = {BMJ Publishing Group},
title = {{APOE genotype and neuroimaging markers of Alzheimer's disease: Systematic review and meta-analysis}},
volume = {86},
year = {2015}
}

@book{Liu2015b,
author = {Liu, Xian},
booktitle = {Methods Appl. Longitud. Data Anal.},
doi = {10.1016/c2013-0-13082-6},
isbn = {0128014822},
pages = {1 recurs en l{\'{i}}nia},
publisher = {Elsevier},
title = {{Methods and Applications of Longitudinal Data Analysis}},
year = {2016}
}

@article{Tondelli2012,
abstract = {Structural brain changes have been described in both mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, less is known about whether structural changes are detectable earlier, in the asymptomatic phase. Using voxel-based morphometry (VBM) and shape analyses of magnetic resonance imaging (MRI) data, we investigated structural brain differences between groups of healthy subjects, stratified by subsequent diagnoses of MCI or AD during a 10-year follow-up. Images taken at baseline, at least 4 years before any cognitive symptoms, showed that subjects with future cognitive impairment (preclinical AD and MCI) had reduced brain volume in medial temporal lobes, posterior cingulate/precuneus, and orbitofrontal cortex, compared with matched subjects who remained cognitively healthy for 10 years (HC). For only those subjects later diagnosed as AD, significantly greater atrophy at baseline was detected in the right medial temporal lobe, which was also confirmed by shape analysis of the right hippocampus in these subjects. Our results demonstrate that structural brain changes occur years before clinical cognitive decline in AD and are localized to regions affected by AD neuropathology. {\textcopyright} 2012 Elsevier Inc.},
author = {Tondelli, Manuela and Wilcock, Gordon K. and Nichelli, Paolo and de Jager, Celeste A. and Jenkinson, Mark and Zamboni, Giovanna},
doi = {10.1016/j.neurobiolaging.2011.05.018},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Tondelli et al. - 2012 - Structural MRI changes detectable up to ten years before clinical Alzheimer's disease.pdf:pdf},
isbn = {0197-4580},
issn = {01974580},
journal = {Neurobiol. Aging},
keywords = {Alzheimer's disease (AD),Mild cognitive impairment (MCI),Preclinical AD,Structural MRI,Voxel-based morphometry (VBM)},
mendeley-groups = {PHD/Shape Analysis,Papers bib/hipppaper,PhDThesis/Hippo},
month = {apr},
number = {4},
pages = {825.e25--825.e36},
pmid = {21782287},
publisher = {Elsevier},
title = {{Structural MRI changes detectable up to ten years before clinical Alzheimer's disease}},
volume = {33},
year = {2012}
}
@article{Zhang2017a,
abstract = {Structural magnetic resonance imaging (MRI) has been proven to be an effective tool for Alzheimer's disease (AD) diagnosis. While conventional MRI-based AD diagnosis typically uses images acquired at a single time point, a longitudinal study is more sensitive in detecting early pathological changes of AD, making it more favorable for accurate diagnosis. In general, there are two challenges faced in MRI-based diagnosis. First, extracting features from structural MR images requires time-consuming nonlinear registration and tissue segmentation, whereas the longitudinal study with involvement of more scans further exacerbates the computational costs. Moreover, the inconsistent longitudinal scans (i.e., different scanning time points and also the total number of scans) hinder extraction of unified feature representations in longitudinal studies. In this paper, we propose a landmark-based feature extraction method for AD diagnosis using longitudinal structural MR images, which does not require nonlinear registration or tissue segmentation in the application stage and is also robust to inconsistencies among longitudinal scans. Specifically, first, the discriminative landmarks are automatically discovered from the whole brain using training images, and then efficiently localized using a fast landmark detection method for testing images, without the involvement of any nonlinear registration and tissue segmentation; and second, high-level statistical spatial features and contextual longitudinal features are further extracted based on those detected landmarks, which can characterize spatial structural abnormalities and longitudinal landmark variations. Using these spatial and longitudinal features, a linear support vector machine is finally adopted to distinguish AD subjects or mild cognitive impairment (MCI) subjects from healthy controls (HCs). Experimental results on the Alzheimer's Disease Neuroimaging Initiative database demonstrate the superior performance and efficiency of the proposed method, with classification accuracies of 88.30{\%} for AD versus HC and 79.02{\%} for MCI versus HC, respectively.},
author = {Zhang, Jun and Liu, Mingxia and An, Le and Gao, Yaozong and Shen, Dinggang},
doi = {10.1109/JBHI.2017.2704614},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Zhang et al. - 2017 - Alzheimer's disease diagnosis using landmark-based features from longitudinal structural MR images(3).pdf:pdf;:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Zhang et al. - 2017 - Alzheimer's disease diagnosis using landmark-based features from longitudinal structural MR images(4).pdf:pdf},
isbn = {9783319611877},
issn = {2168-2208 (Electronic)},
journal = {IEEE J. Biomed. Heal. Informatics},
keywords = {80 and over,Aged,Algorithms,Alzheimer Disease,Alzheimer's disease,Brain,Computer-Assisted,Humans,Image Processing,Longitudinal Studies,Magnetic Resonance Imaging,Male,ROC Curve,diagnostic imaging,landmark-based feature extraction,longitudinal study,methods,structural magnetic resonance imaging},
language = {eng},
mendeley-groups = {Review2,PhDThesis/Review},
month = {nov},
number = {6},
pages = {1607--1616},
pmid = {28534798},
title = {{Alzheimer's disease diagnosis using landmark-based features from longitudinal structural MR images}},
volume = {21},
year = {2017}
}
@article{adaszewski_how_2013,
abstract = {Computational anatomy with magnetic resonance imaging (MRI) is well established as a noninvasive biomarker of Alzheimer's disease (AD); however, there is less certainty about its dependency on the staging of AD. We use classical group analyses and automated machine learning classification of standard structural MRI scans to investigate AD diagnostic accuracy from the preclinical phase to clinical dementia. Longitudinal data from the Alzheimer's Disease Neuroimaging Initiative were stratified into 4 groups according to the clinical statusd(1) AD patients; (2) mild cognitive impairment (MCI) converters; (3) MCI nonconverters; and (4) healthy controlsdand submitted to a support vector machine. The obtained classifier was significantly above the chance level (62{\%}) for detecting AD already 4 years before conversion from MCI. Voxel-based univariate tests confirmed the plausibility of our findings detecting a distributed network of hippocampal-temporoparietal atrophy in AD patients. We also identified a subgroup of control subjects with brain structure and cognitive changes highly similar to those observed in AD. Our results indicate that computational anatomy can detect AD substantially earlier than suggested by current models. The demonstrated differential spatial pattern of atrophy between correctly and incorrectly classified AD patients challenges the assumption of a uniform pathophysiological process underlying clinically identified AD.},
author = {Adaszewski, Stanis{\l}aw and Dukart, Juergen and Kherif, Ferath and Frackowiak, Richard and Draganski, Bogdan},
doi = {10.1016/j.neurobiolaging.2013.06.015},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Adaszewski et al. - 2013 - How early can we predict Alzheimer's disease using computational anatomy(2).pdf:pdf},
issn = {01974580},
journal = {Neurobiol. Aging},
mendeley-groups = {PhDThesis/Review},
number = {12},
pages = {2815--2826},
title = {{How early can we predict {\{}Alzheimer{\}}'s disease using computational anatomy?}},
volume = {34},
year = {2013}
}
@book{Rabeh2017,
abstract = {{\textcopyright} Springer International Publishing AG 2017. In this paper, we will present the system that we designed to track The Alzheimer disease's evolution throughout time using Magnetic Resonance Imaging (MRI) images. The AD makes visible changes in brain structures. We aim to identify the patient category as AD or Normal Control (NC) subject. The paper's contribution relies on realizing a method for longitudinal monitoring of a subject. Our method contains two parts: the first step allows the analysis of two MRI of the same patient in two different times to determine changes in the hippocampus texture descriptors, which are used to move to the second step which is the classification using the SVM method (Support Vector machine) based on a preliminary phase i.e. the learning phase.},
annote = {From Duplicate 2 (Diagnosis of alzheimer disease from MRI images of the brain throughout time - Rabeh, A.B.; Benzarti, F.; Amiri, H.)

basura de paper, ni de conya l'incloc},
author = {Rabeh, A.B. and Benzarti, F. and Amiri, H.},
booktitle = {Adv. Intell. Syst. Comput.},
doi = {10.1007/978-3-319-52941-7_22},
isbn = {9783319529400},
issn = {21945357},
keywords = {Alzheimer diseases (AD),Magnetic resonance imaging (MRI),Normals control (NC),Support vector machine (SVM)},
mendeley-groups = {PhDThesis/Review},
pages = {219--226},
title = {{Diagnosis of alzheimer disease from MRI images of the brain throughout time}},
volume = {552},
year = {2017}
}
@article{Huang2012,
abstract = {Accurate and detailed models of neurodegenerative disease progression are crucially important for reliable early diagnosis and the determination of effective treatments. We introduce the ALPACA (Alzheimer's disease Probabilistic Cascades) model, a generative model linking latent Alzheimer's progression dynamics to observable biomarker data. In contrast with previous works which model disease progression as a fixed event ordering, we explicitly model the variability over such orderings among patients which is more realistic, particularly for highly detailed progression models. We describe efficient learning algorithms for ALPACA and discuss promising experimental results on a real cohort of Alzheimer's patients from the Alzheimer's Disease Neuroimaging Initiative.},
author = {Huang, Jonathan and Alexander, Daniel},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Huang, Alexander - 2012 - Probabilistic Event Cascades for Alzheimer's disease(2).pdf:pdf},
isbn = {9781627480031},
issn = {10495258},
journal = {Adv. Neural Inf. Process. Syst. 25},
mendeley-groups = {PhDThesis/Review},
pages = {3104--3112},
title = {{Probabilistic Event Cascades for Alzheimer's disease}},
year = {2012}
}
@article{Ferri2005,
abstract = {BACKGROUND 100 years after the first description, Alzheimer's disease is one of the most disabling and burdensome health conditions worldwide. We used the Delphi consensus method to determine dementia prevalence for each world region. METHODS 12 international experts were provided with a systematic review of published studies on dementia and were asked to provide prevalence estimates for every WHO world region, for men and women combined, in 5-year age bands from 60 to 84 years, and for those aged 85 years and older. UN population estimates and projections were used to estimate numbers of people with dementia in 2001, 2020, and 2040. We estimated incidence rates from prevalence, remission, and mortality. FINDINGS Evidence from well-planned, representative epidemiological surveys is scarce in many regions. We estimate that 24.3 million people have dementia today, with 4.6 million new cases of dementia every year (one new case every 7 seconds). The number of people affected will double every 20 years to 81.1 million by 2040. Most people with dementia live in developing countries (60{\%} in 2001, rising to 71{\%} by 2040). Rates of increase are not uniform; numbers in developed countries are forecast to increase by 100{\%} between 2001 and 2040, but by more than 300{\%} in India, China, and their south Asian and western Pacific neighbours. INTERPRETATION We believe that the detailed estimates in this paper constitute the best currently available basis for policymaking, planning, and allocation of health and welfare resources.},
author = {Ferri, Cleusa P and Prince, Martin and Brayne, Carol and Brodaty, Henry and Fratiglioni, Laura and Ganguli, Mary and Hall, Kathleen and Hasegawa, Kazuo and Hendrie, Hugh and Huang, Yueqin and Jorm, Anthony and Mathers, Colin and Menezes, Paulo R and Rimmer, Elizabeth and Scazufca, Marcia and {Alzheimer's Disease International}},
doi = {10.1016/S0140-6736(05)67889-0},
issn = {01406736},
journal = {Lancet},
mendeley-groups = {Review2,PhDThesis/Review},
month = {dec},
number = {9503},
pages = {2112--2117},
pmid = {16360788},
title = {{Global prevalence of dementia: a Delphi consensus study}},
volume = {366},
year = {2005}
}
@inproceedings{Lorenzi2015c,
abstract = {Modelling longitudinal changes in organs is fundamental for the understanding of biological and pathological processes. Most of the previous works on spatio-temporal modelling of image time series relies on the assumption of stationarity of the local spatial correlation, and on the separability between spatial and temporal processes. These assumptions are often made in order to lead to computationally tractable approaches to longitudinal modelling, but inevitably lead to an oversimplification of the complex spatial and temporal dynamics underlying the biological processes. In this work we propose a novel spatio-temporal generative model of time series of images based on kernel convolutions of a white noise Gaussian process. The proposed model is parameterised by a sparse set of control points independently identified by specific spatial and temporal parameters. This formulation is highly flexible and can naturally account for spatially and temporally varying dynamics of changes. We demonstrate a preliminary application of our non-parametric method on the modelling of within-subject structural changes in the context of longitudinal analysis in Alzheimer's disease. In particular we show that our method provides an accurate description of the pathological evolution of the brain, while showing high flexibility in modelling and predicting region-specific non-linearity due to accelerated structural decline in dementia.},
author = {Lorenzi, Marco and Ziegler, Gabriel and Alexander, Daniel C. and Ourselin, Sebastien},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-27929-9_4},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Lorenzi et al. - 2015 - Modelling non-stationary and non-separable spatio-temporal changes in neurodegeneration via gaussian process (3).pdf:pdf},
isbn = {9783319279282},
issn = {16113349},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {35--44},
title = {{Modelling non-stationary and non-separable spatio-temporal changes in neurodegeneration via gaussian process convolution}},
volume = {9487},
year = {2015}
}

@article{Huang2016b,
abstract = {Accurate prediction of Alzheimer's disease (AD) is important for the early diagnosis and treatment of this condition. Mild cognitive impairment (MCI) is an early stage of AD. Therefore, patients with MCI who are at high risk of fully developing AD should be identified to accurately predict AD. However, the relationship between brain images and AD is difficult to construct because of the complex characteristics of neuroimaging data. To address this problem, we present a longitudinal measurement of MCI brain images and a hierarchical classification method for AD prediction. Longitudinal images obtained from individuals with MCI were investigated to acquire important information on the longitudinal changes, which can be used to classify MCI subjects as either MCI conversion (MCIc) or MCI non-conversion (MCInc) individuals. Moreover, a hierarchical framework was introduced to the classifier to manage high feature dimensionality issues and incorporate spatial information for improving the prediction accuracy. The proposed method was evaluated using 131 patients with MCI (70 MCIc and 61 MCInc) based on MRI scans taken at different time points. Results showed that the proposed method achieved 79.4{\%} accuracy for the classification of MCIc versus MCInc, thereby demonstrating very promising performance for AD prediction.},
annote = {Nature paper, so good.

Really well written, very focused on clinical application.

Hierarchical classification methodology: late fusion?},
author = {Huang, Meiyan and Yang, Wei and Feng, Qianjin and Chen, Wufan and Weiner, Michael W. and Aisen, Paul and Petersen, Ronald and Jack, Clifford R. and Jagust, William and Trojanowki, John Q. and Toga, Arthur W. and Beckett, Laurel and Green, Robert C. and Saykin, Andrew J. and Morris, John C. and Shaw, Leslie M. and Kaye, Jeffrey and Quinn, Joseph and Silbert, Lisa and Lind, Betty and Carter, Raina and Dolen, Sara and Schneider, Lon S. and Pawluczyk, Sonia and Beccera, Mauricio and Teodoro, Liberty and Spann, Bryan M. and Brewer, James and Vanderswag, Helen and Fleisher, Adam and Heidebrink, Judith L. and Lord, Joanne L. and Mason, Sara S. and Albers, Colleen S. and Knopman, David and Johnson, Kathleen and Doody, Rachelle S. and Villanueva-Meyer, Javier and Chowdhury, Munir and Rountree, Susan and Dang, Mimi and Stern, Yaakov and Honig, Lawrence S. and Bell, Karen L. and Ances, Beau and Carroll, Maria and Creech, Mary L. and Franklin, Erin and Mintun, Mark A. and Schneider, Stacy and Oliver, Angela and Marson, Daniel and Griffith, Randall and Clark, David and Geldmacher, David and Brockington, John and Roberson, Erik and Love, Marissa Natelson and Grossman, Hillel and Mitsis, Effie and Shah, Raj C. and DeToledo-Morrell, Leyla and Duara, Ranjan and Varon, Daniel and Greig, Maria T. and Roberts, Peggy and Albert, Marilyn and Onyike, Chiadi and D'Agostino, Daniel and Kielb, Stephanie and Galvin, James E. and Cerbone, Brittany and Michel, Christina A. and Pogorelec, Dana M. and Rusinek, Henry and {De Leon}, Mony J. and Glodzik, Lidia and {De Santi}, Susan and {Murali Doraiswamy}, P. and Petrella, Jeffrey R. and Borges-Neto, Salvador and Wong, Terence Z. and Coleman, Edward and Smith, Charles D. and Jicha, Greg and Hardy, Peter and Sinha, Partha and Oates, Elizabeth and Conrad, Gary and Porsteinsson, Anton P. and Goldstein, Bonnie S. and Martin, Kim and Makino, Kelly M. and {Saleem Ismail}, M. and Brand, Connie and Mulnard, Ruth A. and Thai, Gaby and Mc-Adams-Ortiz, Catherine and Womack, Kyle and Mathews, Dana and Quiceno, Mary and Levey, Allan I. and Lah, James J. and Cellar, Janet S. and Burns, Jeffrey M. and Swerdlow, Russell H. and Brooks, William M. and Apostolova, Liana and Tingus, Kathleen and Woo, Ellen and Silverman, Daniel H.S. and Lu, Po H. and Bartzokis, George and Graff-Radford, Neill R. and Parfitt, Francine and Kendall, Tracy and Johnson, Heather and Farlow, Martin R. and Hake, Ann Marie and Brosch, Jared R. and Herring, Scott and Hunt, Cynthia and {Van Dyck}, Christopher H. and Carson, Richard E. and MacAvoy, Martha G. and Varma, Pradeep and Chertkow, Howard and Bergman, Howard and Hosein, Chris and Black, Sandra and Stefanovic, Bojana and Caldwell, Curtis and Hsiung, Ging Yuek Robin and Feldman, Howard and Mudge, Benita and Assaly, Michele and Finger, Elizabeth and Pasternack, Stephen and Rachisky, Irina and Trost, Dick and Kertesz, Andrew and Bernick, Charles and Munic, Donna and Mesulam, Marek Marsel and Lipowski, Kristine and Weintraub, Sandra and Bonakdarpour, Borna and Kerwin, Diana and Wu, Chuang Kuo and Johnson, Nancy and Sadowsky, Carl and Villena, Teresa and Turner, Raymond Scott and Reynolds, Brigid and Sperling, Reisa A. and Johnson, Keith A. and Marshall, Gad and Yesavage, Jerome and Taylor, Joy L. and Lane, Barton and Rosen, Allyson and Tinklenberg, Jared and Sabbagh, Marwan N. and Belden, Christine M. and Jacobson, Sandra A. and Sirrel, Sherye A. and Kowall, Neil and Killiany, Ronald and Budson, Andrew E. and Norbash, Alexander and {Lynn Johnson}, Patricia and Obisesan, Thomas O. and Wolday, Saba and Allard, Joanne and Lerner, Alan and Ogrocki, Paula and Tatsuoka, Curtis and Fletcher, Evan and Maillard, Pauline and Olichney, John and DeCarli, Charles and Carmichael, Owen and Kittur, Smita and Borrie, Michael and Lee, T. Y. and Bartha, Rob and Johnson, Sterling and Asthana, Sanjay and Carlsson, Cynthia M. and Potkin, Steven G. and Preda, Adrian and Nguyen, Dana and Tariot, Pierre and Burke, Anna and Trncic, Nadira and Reeder, Stephanie and Bates, Vernice and Capote, Horacio and Rainka, Michelle and Scharre, Douglas W. and Kataki, Maria and Adeli, Anahita and Zimmerman, Earl A. and Celmins, Dzintra and Brown, Alice D. and Pearlson, Godfrey D. and Blank, Karen and Anderson, Karen and Flashman, Laura A. and Seltzer, Marc and Hynes, Mary L. and Santulli, Robert B. and Sink, Kaycee M. and Gordineer, Leslie and Williamson, Jeff D. and Garg, Pradeep and Watkins, Franklin and Ott, Brian R. and Querfurth, Henry and Tremont, Geoffrey and Salloway, Stephen and Malloy, Paul and Correia, Stephen and Rosen, Howard J. and Miller, Bruce L. and Perry, David and Mintzer, Jacobo and Spicer, Kenneth and Bachman, David and Pomara, Nunzio and Hernando, Raymundo and Sarrael, Antero and Relkin, Norman and Chaing, Gloria and Lin, Michael and Ravdin, Lisa and Smith, Amanda and Raj, Balebail Ashok and Fargher, Kristin},
doi = {10.1038/srep39880},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Huang et al. - 2017 - Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer's disease.pdf:pdf},
issn = {20452322},
journal = {Sci. Rep.},
mendeley-groups = {Review2,PhDThesis/Review},
title = {{Longitudinal measurement and hierarchical classification framework for the prediction of Alzheimer's disease}},
volume = {7},
year = {2017}
}
@inproceedings{Aghili2018,
abstract = {In this paper, we study the application of Recurrent Neural Networks (RNNs) to discriminate Alzheimer's disease patients from healthy control individuals using longitudinal neuroimaging data. Distinctions between Alzheimer's Disease (AD), Mild Cognitive Impairment (MCI), and healthy subjects in a multi-modal heterogeneous longitudinal dataset is a challenging problem due to high similarity between brain patterns, high portions of missing data from different modalities and time points, and inconsistent number of test intervals between different subjects. Due to these challenges, to distinguish AD patients from healthy subjects, conventionally researchers use cross-sectional data when applying deep learning methods in neuroimaging applications. Whereas we propose a method based on RNNS to analyze the longitudinal data. After carefully preprocessing the data to alleviate the inconsistency due to different data sources and various protocols of capturing modalities, we arrange the data and feed it into variations of RNNs, i.e., vanilla Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The accuracy, F-score, sensitivity, and specificity of our models are reported and are compared with the most immediate baseline method, multi-layer perceptron (MLP).},
author = {Aghili, Maryamossadat and Tabarestani, Solale and Adjouadi, Malek and Adeli, Ehsan},
booktitle = {Predict. Intell. Med.},
doi = {10.1007/978-3-030-00320-3_14},
mendeley-groups = {PhDThesis/Review},
month = {sep},
pages = {112--119},
publisher = {Springer International Publishing},
title = {{Predictive Modeling of Longitudinal Data for Alzheimer's Disease Diagnosis Using RNNs}},
year = {2018}
}
@article{Jack1992,
abstract = {We evaluated a new magnetic resonance (MR)-based technique for performing volumetric measurements of temporal lobe structures. The technique was designed to assist in making the clinical diagnosis of dementia of the Alzheimer type (DAT). We chose specific anatomic regions of interest because of their known involvement in memory function and in the neuropathology of DAT and used a regression model to assess the effects of age on the volumes of the anterior temporal lobe (ATL) and the hippocampal formation (HF). These measurements were normalized by total intracranial volume (TIV). The volumetric measurements of both the normalized ATL and HF were significantly smaller (p less than 0.001) in DAT patients (N = 20) than in controls (N = 22), but the HF volumes provided much better separation between the two groups. Eighty-five percent of the DAT patients fell below the range of the HF/TIV measurement for the control subjects. This separation held up over the entire age range studied. Normalized volumes of both the HF and ATL decreased with age significantly for both the DAT patients and the controls. These results support the contention that MR-based HF volumetric measurements are accurate in differentiating DAT patients from cognitively normal elderly individuals. This technique may be a useful adjunct in making the clinical diagnosis of DAT.},
author = {Jack, C R and Petersen, R C and O'Brien, P C and Tangalos, E G},
doi = {10.1212/WNL.42.1.183},
issn = {0028-3878},
journal = {Neurology},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {jan},
number = {1},
pages = {183--8},
pmid = {1734300},
publisher = {Wolters Kluwer Health, Inc. on behalf of the American Academy of Neurology},
title = {{MR-based hippocampal volumetry in the diagnosis of Alzheimer's disease.}},
volume = {42},
year = {1992}
}
@article{Ching2018,
abstract = {Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems{\{}$\backslash$textemdash{\}}patient classification, fundamental biological processes and treatment of patients{\{}$\backslash$textemdash{\}}and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network{\{}$\backslash$textquoteright{\}}s prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.},
author = {Ching, Travers and Do, Brian T and Himmelstein, Daniel S and Beaulieu-Jones, Brett K and Kalinin, Alexandr A and Way, Gregory P and Ferrero, Enrico and Agapow, Paul-Michael and Carpenter, Anne E and Zietz, Michael and Hoffman, Michael M and Xie, Wei and Rosen, Gail L and Lanchantin, Jack and Xu, Jinbo and Woloszynek, Stephen and Lu, Zhiyong and Harris, David J and Peng, Yifan and Wiley, Laura K and Do, Brian T and Way, Gregory P and Ferrero, Enrico and Agapow, Paul-Michael and Zietz, Michael and Hoffman, Michael M and Xie, Wei and Rosen, Gail L and Lengerich, Benjamin J and Israeli, Johnny and Lanchantin, Jack and Woloszynek, Stephen and Carpenter, Anne E and Shrikumar, Avanti and Xu, Jinbo and Cofer, Evan M and Lavender, Christopher A and Turaga, Srinivas C and Alexandari, Amr M and Lu, Zhiyong and Harris, David J and DeCaprio, Dave and Qi, Yanjun and Kundaje, Anshul and Peng, Yifan and Wiley, Laura K and Segler, Marwin H S and Boca, Simina M and Swamidass, S Joshua and Huang, Austin and Gitter, Anthony and Greene, Casey S},
doi = {https://doi.org/10.1101/142760},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Ching et al. - 2018 - Opportunities and obstacles for deep learning in biology and medicine.pdf:pdf},
issn = {1742-5689},
journal = {J. R. Soc. Interface},
keywords = {deep learning,genomic,precision medicine,review},
mendeley-groups = {PHD/Reviews,PhDThesis/Review},
number = {141},
pages = {.},
publisher = {The Royal Society},
title = {{Opportunities and obstacles for deep learning in biology and medicine}},
volume = {15},
year = {2018}
}

@inproceedings{Wang2016,
abstract = {Alzheimer's Disease (AD),a severe type of neurodegenerative disorder with progressive impairment of learning and memory,has threatened the health of millions of people. How to recognize AD at early stage is crucial. Multiple models have been presented to predict cognitive impairments by means of neuroimaging data. However,traditional models did not employ the valuable longitudinal information along the progression of the disease. In this paper,we proposed a novel longitudinal feature learning model to simultaneously uncover the interrelations among different cognitive measures at different time points and utilize such interrelated structures to enhance the learning of associations between imaging features and prediction tasks. Moreover,we adopted Schatten p-norm to identify the interrelation structures existing in the low-rank subspace. Empirical results on the ADNI cohort demonstrated promising performance of our model.},
author = {Wang, Xiaoqian and Shen, Dinggang and Huang, Heng},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-46720-7_32},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Wang, Shen, Huang - 2016 - Prediction of Memory Impairment with MRI Data A Longitudinal Study of Alzheimer's Disease.pdf:pdf},
isbn = {9783319467191},
issn = {16113349},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {273--281},
title = {{Prediction of memory impairment with MRI data: A longitudinal study of Alzheimer's disease}},
volume = {9900 LNCS},
year = {2016}
}

@article{Gerardin2009,
abstract = {We describe a new method to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls, based on multidimensional classification of hippocampal shape features. This approach uses spherical harmonics (SPHARM) coefficients to model the shape of the hippocampi, which are segmented from magnetic resonance images (MRI) using a fully automatic method that we previously developed. SPHARM coefficients are used as features in a classification procedure based on support vector machines (SVM). The most relevant features for classification are selected using a bagging strategy. We evaluate the accuracy of our method in a group of 23 patients with AD (10 males, 13 females, age ± standard-deviation (SD) = 73 ± 6 years, mini-mental score (MMS) = 24.4 ± 2.8), 23 patients with amnestic MCI (10 males, 13 females, age ± SD = 74 ± 8 years, MMS = 27.3 ± 1.4) and 25 elderly healthy controls (13 males, 12 females, age ± SD = 64 ± 8 years), using leave-one-out cross-validation. For AD vs controls, we obtain a correct classification rate of 94{\%}, a sensitivity of 96{\%}, and a specificity of 92{\%}. For MCI vs controls, we obtain a classification rate of 83{\%}, a sensitivity of 83{\%}, and a specificity of 84{\%}. This accuracy is superior to that of hippocampal volumetry and is comparable to recently published SVM-based whole-brain classification methods, which relied on a different strategy. This new method may become a useful tool to assist in the diagnosis of Alzheimer's disease. {\textcopyright} 2009 Elsevier Inc. All rights reserved.},
author = {Gerardin, Emilie and Ch{\'{e}}telat, Ga{\"{e}}l and Chupin, Marie and Cuingnet, R{\'{e}}mi and Desgranges, B{\'{e}}atrice and Kim, Ho Sung and Niethammer, Marc and Dubois, Bruno and Leh{\'{e}}ricy, St{\'{e}}phane and Garnero, Line and Eustache, Francis and Colliot, Olivier},
doi = {10.1016/j.neuroimage.2009.05.036},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Hippocampus,MCI,Magnetic resonance imaging,Support vector machines},
mendeley-groups = {Papers bib/hipppaper,PhDThesis/Hippo},
month = {oct},
number = {4},
pages = {1476--1486},
pmid = {19463957},
publisher = {NIH Public Access},
title = {{Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging}},
volume = {47},
year = {2009}
}
@article{Minhas2018,
abstract = {Mild cognitive impairment is a preclinical stage of Alzheimer's disease (AD). For effective treatment of AD, it is important to identify mild cognitive impairment (MCI) patients who are at a high risk of developing AD over the course of time. In this study, autoregressive modelling of multiple heterogeneous predictors of Alzheimer's disease is performed to capture their evolution over time. The models are trained using three different arrangements of longitudinal data. These models are then used to estimate future biomarker readings of individual test subjects. Finally, standard support vector machine classifier is employed for detecting MCI patients at risk of developing AD over the coming years. The proposed models are thoroughly evaluated for their predictive capability using both cognitive scores and MRI-derived measures. In a stratified five-fold cross validation setup, our proposed methodology delivered highest AUC of 88.93{\%} (Accuracy = 84.29{\%}) and 88.13{\%} (Accuracy = 83.26{\%}) for 1 year and 2 year ahead AD conversion prediction, respectively, on the most widely used Alzheimer's disease neuroimaging initiative data. The notable conclusions of this study are: 1) Clinical changes in MRI-derived measures can be better forecasted than cognitive scores, 2) Multiple predictor models deliver better conversion prediction than single biomarker models, 3) Cognitive score boosted by MRI-derived measures delivers better short-term ahead conversion prediction, and 4) Neuropsychological scores alone can deliver good accuracy for long-term conversion prediction.},
author = {Minhas, Sidra and Khanum, Aasia and Riaz, Farhan and Khan, Shoab A and Alvi, Atif},
doi = {10.1109/JBHI.2017.2703918},
issn = {21682194},
journal = {IEEE J. Biomed. Heal. Informatics},
keywords = {Autoregressive,Mild cognitive impairment,biomarkers,classification,correlation,linear,longitudinal,prediction},
mendeley-groups = {PhDThesis/Review},
number = {3},
pages = {818--825},
publisher = {IEEE},
title = {{Predicting progression from mild cognitive impairment to Alzheimer's disease using autoregressive modelling of longitudinal and multimodal biomarkers}},
volume = {22},
year = {2018}
}
@article{Talo2019b,
abstract = {Magnetic resonance imaging (MRI) is the most common imaging technique used to detect abnormal brain tumors. Traditionally, MRI images are analyzed manually by radiologists to detect the abnormal conditions in the brain. Manual interpretation of huge volume of images is time consuming and difficult. Hence, computer-based detection helps in accurate and fast diagnosis. In this study, we proposed an approach that uses deep transfer learning to automatically classify normal and abnormal brain MR images. Convolutional neural network (CNN) based ResNet34 model is used as a deep learning model. We have used current deep learning techniques such as data augmentation, optimal learning rate finder and fine-tuning to train the model. The proposed model achieved 5-fold classification accuracy of 100{\%} on 613 MR images. Our developed system is ready to test on huge database and can assist the radiologists in their daily screening of MR images.},
author = {Talo, Muhammed and Baloglu, Ulas Baran and Yıldırım, {\"{O}}zal and {Rajendra Acharya}, U.},
doi = {10.1016/j.cogsys.2018.12.007},
issn = {13890417},
journal = {Cogn. Syst. Res.},
keywords = {Abnormal brain images,CNN,Deep transfer learning,MRI classification},
mendeley-groups = {Review2,PhDThesis/Review},
month = {may},
pages = {176--188},
publisher = {Elsevier B.V.},
title = {{Application of deep transfer learning for automated brain abnormality classification using MR images}},
volume = {54},
year = {2019}
}

@article{Avants2009,
abstract = {We provide examples and highlights of Advanced Normalization Tools (ANTS) that address practical problems in real data. A variety of image and point similarity metrics and elastic, diffeomorphic, affine and other variations of transformation models are available.},
author = {Avants, Bb and Tustison, Nick and Song, Gang},
file = {:C$\backslash$:/Users/gerar/Downloads/ants2.pdf:pdf},
isbn = {0-7167-3051-0},
issn = {09255273},
journal = {Insight J.},
mendeley-groups = {PhDThesis/Hippo},
pages = {1--35},
pmid = {1000105586},
title = {{Advanced Normalization Tools (ANTS)}},
year = {2009}
}

@article{Avants2008a,
abstract = {One of the most challenging problems in modern neuroimaging is detailed characterization of neurodegeneration. Quantifying spatial and longitudinal atrophy patterns is an important component of this process. These spatiotemporal signals will aid in discriminating between related diseases, such as frontotemporal dementia (FTD) and Alzheimer's disease (AD), which manifest themselves in the same at-risk population. Here, we develop a novel symmetric image normalization method (SyN) for maximizing the cross-correlation within the space of diffeomorphic maps and provide the Euler-Lagrange equations necessary for this optimization. We then turn to a careful evaluation of our method. Our evaluation uses gold standard, human cortical segmentation to contrast SyN's performance with a related elastic method and with the standard ITK implementation of Thirion's Demons algorithm. The new method compares favorably with both approaches, in particular when the distance between the template brain and the target brain is large. We then report the correlation of volumes gained by algorithmic cortical labelings of FTD and control subjects with those gained by the manual rater. This comparison shows that, of the three methods tested, SyN's volume measurements are the most strongly correlated with volume measurements gained by expert labeling. This study indicates that SyN, with cross-correlation, is a reliable method for normalizing and making anatomical measurements in volumetric MRI of patients and at-risk elderly individuals.},
author = {Avants, B. B. and Epstein, C. L. and Grossman, M. and Gee, J. C.},
doi = {10.1016/j.media.2007.06.004},
issn = {13618415},
journal = {Med. Image Anal.},
keywords = {Cross-correlation,Deformable image registration,Dementia,Diffeomorphic,Human cortex,Morphometry},
mendeley-groups = {Papers bib/hipppaper/shape/shape-revision,PhDThesis/Hippo},
month = {feb},
number = {1},
pages = {26--41},
pmid = {17659998},
publisher = {NIH Public Access},
title = {{Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain}},
volume = {12},
year = {2008}
}
@article{Koval2018,
abstract = {Repeated failures in clinical trials for Alzheimer's Disease (AD) have raised a strong interest for the prodromal phase of the disease. A better understanding of the brain alterations during this early phase is crucial to diagnose patients sooner, to estimate an accurate disease stage and to give a reliable prognosis.

According to recent evidence, structural alterations in the brain are likely to be sensitive markers of the disease progression. Neuronal loss translates in specific spatiotemporal patterns of cortical atrophy, starting in the enthorinal cortex and spreading over other cortical regions according to specific propagation pathways.

We developed a digital model $\backslash$textcolor{\{}blue!90{\}}{\{}of the cortical atrophy in the left hemisphere from prodromal to diseased phases{\}}, which is built on the temporal alignment and combination of several short-term observation data to reconstruct the long-term history of the disease. The model not only provides a description of the spatiotemporal patterns of cortical atrophy at the group level, but also shows the variability of these patterns at the individual level in terms of difference in propagation pathways, speed of propagation and age at propagation onset.

Longitudinal MRI datasets of patients with mild cognitive impairments who converted to AD are used to reconstruct the cortical atrophy propagation across all disease stages. Each observation is considered as a signal spatially distributed on a network, such as the cortical mesh, each cortex location being associated to a node. We consider how the temporal profile of the signal varies across the network nodes.

We introduce a statistical mixed-effect model to describe the evolution of the cortex alterations. To ensure a spatiotemporal smooth propagation of the alterations, we introduce a constrain on the propagation signal in the model such that neighboring nodes have similar profiles of the signal changes. Our generative model enables the reconstruction of personalized patterns of the neurodegenerative spread, providing a way to estimate disease progression stages and predict the age at which the disease will be diagnosed. The model shows that, for instance, APOE carriers have a significantly higher pace of cortical atrophy but not earlier atrophy onset.},
author = {Koval, Igor and Schiratti, Jean-Baptiste and Routier, Alexandre and Bacci, Michael and Colliot, Olivier and Allassonni{\`{e}}re, St{\'{e}}phanie and Durrleman, Stanley},
doi = {10.3389/fneur.2018.00235},
issn = {1664-2295},
journal = {Front. Neurol.},
mendeley-groups = {PhDThesis/Review},
pages = {235},
title = {{Spatiotemporal Propagation of the Cortical Atrophy: Population and Individual Patterns}},
volume = {9},
year = {2018}
}
@article{liang1986longitudinal,
author = {Liang, Kung-Yee and Zeger, Scott L},
journal = {Biometrika},
mendeley-groups = {PhDThesis/Review},
number = {1},
pages = {13--22},
publisher = {Oxford University Press},
title = {{Longitudinal data analysis using generalized linear models}},
volume = {73},
year = {1986}
}
@book{Liu,
author = {Liu, Xian},
booktitle = {Methods Appl. Longitud. Data Anal.},
doi = {10.1016/c2013-0-13082-6},
isbn = {0128014822},
mendeley-groups = {PhDThesis/Review},
pages = {1 recurs en l{\'{i}}nia},
title = {{Methods and Applications of Longitudinal Data Analysis}},
year = {2016}
}
@article{Petrella2018,
abstract = {Background: The heterogeneity and complexity of Alzheimer disease (AD) lends itself to dynamic causal modeling, a computational systems biology approach to simulate complex systems. Methods: We implemented a computational dynamic causal model (DCM) to test the common descriptive assumptions of biomarker evolution in AD. We modeled beta-amyloid, tau, neuro-degeneration and cognitive impairment as first order non-linear differential equations to include beta-amyloid dependent and non-dependent neurodegenerative cascades. We tested the DCM, by adjusting its parameters to simulate three specific simulation scenarios in early-onset autosomal dominant AD and late-onset AD, to determine whether computed biomarker trajectories agreed with current assumptions of AD progression. We also simulated the effects of anti-amyloid therapy in late-onset AD. Results: The computational model of early-onset pure AD demonstrated the initial appearance of amyloid, followed by other biomarkers of tau and neurodegeneration, followed by the onset of cognitive decline as predicted by prior literature. The model also showed the ability to vary onset of cognitive decline based on cognitive reserve. Similarly, the late-onset AD computational models demonstrated the first appearance of amyloid-related or non-amyloid-related tauopathy, depending on the magnitude of age-related comorbid pathology, and also closely matched the cascade predicted by prior literature. Forward simulation of anti-amyloid therapy in symptomatic late-onset AD failed to demonstrate any benefit on cognitive decline, consistent with prior failed clinical trials in symptomatic patients. Conclusions: To our knowledge, this is the first computational model of the dynamic biomarker cascade in autosomal dominant and late-onset AD. Such models, with refinement using actual molecular, clinical and genomic data, are an important tool towards developing a systems biology precision medicine approach for understanding and preventing AD.},
annote = {NOT RELATED},
author = {Petrella, Jeffrey R and Hao, Wenrui and Rao, Adithi and Doraiswamy, P Murali},
doi = {https://doi.org/10.1101/313353},
journal = {bioRxiv},
mendeley-groups = {PhDThesis/Review},
month = {may},
pages = {313353},
publisher = {Cold Spring Harbor Laboratory},
title = {{Computational Modeling of the Dynamic Biomarker Cascade in Alzheimer ' s Disease Abstract :}},
year = {2018}
}
@article{Talo2019,
abstract = {The brain disorders may cause loss of some critical functions such as thinking, speech, and movement. So, the early detection of brain diseases may help to get the timely best treatment. One of the conventional methods used to diagnose these disorders is the magnetic resonance imaging (MRI) technique. Manual diagnosis of brain abnormalities is time-consuming and difficult to perceive the minute changes in the MRI images, especially in the early stages of abnormalities. Proper selection of the features and classifiers to obtain the highest performance is a challenging task. Hence, deep learning models have been widely used for medical image analysis over the past few years. In this study, we have employed the AlexNet, Vgg-16, ResNet-18, ResNet-34, and ResNet-50 pre-trained models to automatically classify MR images in to normal, cerebrovascular, neoplastic, degenerative, and inflammatory diseases classes. We have also compared their classification performance with pre-trained models, which are the state-of-art architectures. We have obtained the best classification accuracy of 95.23{\%} ± 0.6 with the ResNet-50 model among the five pre-trained models. Our model is ready to be tested with huge MRI images of brain abnormalities. The outcome of the model will also help the clinicians to validate their findings after manual reading of the MRI images.},
author = {Talo, Muhammed and Yildirim, Ozal and Baloglu, Ulas Baran and Aydin, Galip and Acharya, U. Rajendra},
doi = {10.1016/j.compmedimag.2019.101673},
issn = {18790771},
journal = {Comput. Med. Imaging Graph.},
keywords = {Brain disease,CNN,Deep transfer learning,MRI classification,ResNet},
mendeley-groups = {Review2,PhDThesis/Review},
month = {dec},
publisher = {Elsevier Ltd},
title = {{Convolutional neural networks for multi-class brain disease detection using MRI images}},
volume = {78},
year = {2019}
}
@inproceedings{Ortiz2017,
abstract = {Automatic knowledge extraction from medical images constitutes a key point in the construction of computer aided diagnosis tools (CAD). This takes a special relevance in the case of neurodegenerative diseases such as the Alzheimer's disease (AD), where an early diagnosis makes the treatments easier and more effective. Moreover, the study of the evolution of the illness results crucial to differentiate the neurodegenerative process associated to the disease from the natural degeneration due to the ageing process. In this paper we present a method to construct longitudinal models from subjects using a series of MRI images. Specifically, the method presented here aims to model Gray matter (GM) variation at different brain areas of a subject across subsequent examinations, being possible to relate those regions which degenerate jointly. Hence, it allows determining variation patterns that differentiate controls from AD patients. Additionally, White matter (WM) density is also incorporated to the longitudinal model to complement the information provided by GM. The results obtained demonstrated the effectiveness of the method in the extraction of these patterns, that can be used to classify between Controls (CN) and AD subjects with 94{\%} of accuracy, outperforming other previous methods.},
annote = {From Duplicate 1 (Learning longitudinal MRI patterns by SICE and deep learning: Assessing the Alzheimer's disease progression - Ortiz, Andr{\'{e}}s; Munilla, Jorge; Mart{\'{i}}nez-Murcia, Francisco J.; G{\'{o}}rriz, Juan M.; Ram{\'{i}}rez, Javier)

Novel correlation analysis to compute covariance values and stacked autoencoders for classification.},
author = {Ortiz, Andr{\'{e}}s and Munilla, Jorge and Mart{\'{i}}nez-Murcia, Francisco J. and G{\'{o}}rriz, Juan M. and Ram{\'{i}}rez, Javier},
booktitle = {Commun. Comput. Inf. Sci.},
doi = {10.1007/978-3-319-60964-5_36},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Ortiz et al. - 2017 - Learning longitudinal MRI patterns by SICE and deep learning Assessing the Alzheimer's disease progression(2).pdf:pdf},
isbn = {9783319609638},
issn = {18650929},
mendeley-groups = {Review2,PhDThesis/Review},
month = {jul},
pages = {413--424},
publisher = {Springer, Cham},
title = {{Learning longitudinal MRI patterns by SICE and deep learning: Assessing the Alzheimer's disease progression}},
volume = {723},
year = {2017}
}
@article{Morra2009,
abstract = {As one of the earliest structures to degenerate in Alzheimer's disease (AD), the hippocampus is the target of many studies of factors that influence rates of brain degeneration in the elderly. In one of the largest brain mapping studies to date, we mapped the 3D profile of hippocampal degeneration over time in 490 subjects scanned twice with brain MRI over a 1-year interval (980 scans). We examined baseline and 1-year follow-up scans of 97 AD subjects (49 males/48 females), 148 healthy control subjects (75 males/73 females), and 245 subjects with mild cognitive impairment (MCI; 160 males/85 females). We used our previously validated automated segmentation method, based on AdaBoost, to create 3D hippocampal surface models in all 980 scans. Hippocampal volume loss rates increased with worsening diagnosis (normal = 0.66{\%}/year; MCI = 3.12{\%}/year; AD = 5.59{\%}/year), and correlated with both baseline and interval changes in Mini-Mental State Examination (MMSE) scores and global and sum-of-boxes Clinical Dementia Rating scale (CDR) scores. Surface-based statistical maps visualized a selective profile of ongoing atrophy in all three diagnostic groups. Healthy controls carrying the ApoE4 gene atrophied faster than non-carriers, while more educated controls atrophied more slowly; converters from MCI to AD showed faster atrophy than non-converters. Hippocampal loss rates can be rapidly mapped, and they track cognitive decline closely enough to be used as surrogate markers of Alzheimer's disease in drug trials. They also reveal genetically greater atrophy in cognitively intact subjects.},
author = {Morra, Jonathan H. and Tu, Zhuowen and Apostolova, Liana G. and Green, Amity E. and Avedissian, Christina and Madsen, Sarah K. and Parikshak, Neelroop and Toga, Arthur W. and Jack, Clifford R. and Schuff, Norbert and Weiner, Michael W. and Thompson, Paul M.},
doi = {10.1016/j.neuroimage.2008.10.043},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Morra et al. - 2009 - Automated mapping of hippocampal atrophy in 1-year repeat MRI data from 490 subjects with Alzheimer's disease, (2).pdf:pdf},
issn = {10959572},
journal = {Neuroimage},
mendeley-groups = {Papers bib/hipppaper/shape,PhDThesis/Hippo},
month = {mar},
number = {1},
pages = {S3--S15},
publisher = {Academic Press},
title = {{Automated mapping of hippocampal atrophy in 1-year repeat MRI data from 490 subjects with Alzheimer's disease, mild cognitive impairment, and elderly controls}},
volume = {45},
year = {2009}
}
@inproceedings{Schmidt-Richberg2015,
abstract = {The estimation of disease progression in Alzheimer's disease (AD) based on a vector of quantitative biomarkers is of high interest to clinicians, patients, and biomedical researchers alike. In this work, quantile regression is employed to learn statistical models describing the evolution of such biomarkers. Two separate models are constructed using (1) subjects that progress from a cognitively normal (CN) stage to mild cognitive impairment (MCI) and (2) subjects that progress from MCI to AD during the observation window of a longitudinal study. These models are then automatically combined to develop a multi-stage disease progression model for the whole disease course. A probabilistic approach is derived to estimate the current disease progress (DP) and the disease progression rate (DPR) of a given individual by fitting any acquired biomarkers to these models. A particular strength of this method is that it is applicable even if individual biomarker measurements are missing for the subject. Employing cognitive scores and image-based biomarkers, the presented method is used to estimate DP and DPR for subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Further, the potential use of these values as features for different classification tasks is demonstrated. For example, accuracy of 64{\%} is reached for CN vs. MCI vs. AD classification.},
annote = {Verd: data
Red: missing dadta policy
Blue: model},
author = {Schmidt-Richberg, Alexander and Guerrero, Ricardo and Ledig, Christian and Molina-Abril, Helena and Frangi, Alejandro F. and Rueckert, Daniel},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-19992-4_30},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Schmidt-Richberg et al. - 2015 - Multi-stage biomarker models for progression estimation in Alzheimer's disease(2).pdf:pdf},
isbn = {1011-2499 (Print)$\backslash$r1011-2499},
issn = {16113349},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {387--398},
pmid = {26221689},
publisher = {Springer, Cham},
title = {{Multi-stage biomarker models for progression estimation in Alzheimer's disease}},
volume = {9123},
year = {2015}
}
@article{Shi2017,
abstract = {In this study, we develop a novel nonlinear metric learning method to improve biomarker identification for Alzheimer's Disease (AD) and Mild Cognitive Impairment (MCI). Formulated under a constrained optimization framework, the proposed method learns a smooth nonlinear feature space transformation that makes the mapped data more linearly separable for SVMs. The thin-plate spline (TPS) is chosen as the geometric model due to its remarkable versatility and representation power in generating sophisticated yet smooth deformations. In addition, a deep network based feature fusion strategy through stacked denoising sparse auto-encoder (DSAE) is adopted to integrate cross-sectional and longitudinal features estimated from MR brain images. Using the ADNI dataset, we evaluate the effectiveness of the proposed feature transformation and feature fusion strategies and demonstrate the improvements over the state-of-the-art solutions within the same category.},
author = {Shi, Bibo and Chen, Yani and Zhang, Pin and Smith, Charles D and Liu, Jundong},
doi = {https://doi.org/10.1016/j.patcog.2016.09.032},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Shi et al. - 2017 - Nonlinear feature transformation and deep fusion for Alzheimer's Disease staging analysis(2).pdf:pdf},
issn = {0031-3203},
journal = {Pattern Recognit.},
keywords = {Alzheimer's Disease (AD),Deep neural networks,Feature fusion,Metric learning,Mild Cognitive Impairment (MCI),SVM classifier},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {487--498},
title = {{Nonlinear feature transformation and deep fusion for Alzheimer's Disease staging analysis}},
volume = {63},
year = {2017}
}
@article{Aksman2019,
abstract = {Longitudinal imaging biomarkers are invaluable for understanding the course of neurodegeneration, promising the ability to track disease progression and to detect disease earlier than cross-sectional biomarkers. To properly realize their potential, biomarker trajectory models must be robust to both under-sampling and measurement errors and should be able to integrate multi-modal information to improve trajectory inference and prediction. Here we present a parametric Bayesian multi-task learning based approach to modeling univariate trajectories across subjects that addresses these criteria. Our approach learns multiple subjects' trajectories within a single model that allows for different types of information sharing, i.e. coupling , across subjects. It optimizes a combination of uncoupled, fully coupled and kernel coupled models. Kernel-based coupling allows linking subjects' trajectories based on one or more biomarker measures. We demonstrate this using Alzheimer's Disease Neuroimaging Initiative (ADNI) data, where we model longitudinal trajectories of MRI-derived cortical volumes in neurodegeneration, with coupling based on APOE genotype, cerebrospinal fluid (CSF) and amyloid PET-based biomarkers. In addition to detecting established disease effects, we detect disease related changes within the insula that have not received much attention within the literature. Due to its sensitivity in detecting disease effects, its competitive predictive performance and its ability to learn the optimal parameter covariance from data rather than choosing a specific set of random and fixed effects a priori, we propose that our model can be used in place of or in addition to linear mixed effects models when modeling biomarker trajectories. A software implementation of the method is publicly available.},
author = {Aksman, Leon M. and Scelsi, Marzia A. and Marquand, Andre F. and Alexander, Daniel C. and Ourselin, Sebastien and Altmann, Andre},
doi = {10.1002/hbm.24682},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Aksman et al. - 2019 - Modeling longitudinal imaging biomarkers with parametric Bayesian multi-task learning(3).pdf:pdf},
issn = {10970193},
journal = {Hum. Brain Mapp.},
keywords = {Alzheimer's disease,Bayesian analysis,biomarkers,longitudinal analysis,machine learning,multimodal analysis,structural MRI},
mendeley-groups = {Review2/Scopus,PhDThesis/Review},
month = {jun},
pages = {hbm.24682},
publisher = {John Wiley {\&} Sons, Ltd},
title = {{Modeling longitudinal imaging biomarkers with parametric Bayesian multi-task learning}},
year = {2019}
}
@article{Pathan2018,
abstract = {In this paper, we propose a predictive regression model for longitudinal images with missing data based on large deformation diffeomorphic metric mapping (LDDMM) and deep neural networks. Instead of directly predicting image scans, our model predicts a vector momentum sequence associated with a baseline image. This momentum sequence parameterizes the original image sequence in the LDDMM framework and lies in the tangent space of the baseline image, which is Euclidean. A recurrent network with long term-short memory (LSTM) units encodes the time-varying changes in the vector-momentum sequence, and a convolutional neural network (CNN) encodes the baseline image of the vector momenta. Features extracted by the LSTM and CNN are fed into a decoder network to reconstruct the vector momentum sequence, which is used for the image sequence prediction by deforming the baseline image with LDDMM shooting. To handle the missing images at some time points, we adopt a binary mask to ignore their reconstructions in the loss calculation. We evaluate our model on synthetically generated images and the brain MRIs from the OASIS dataset. Experimental results demonstrate the promising predictions of the spatiotemporal changes in both datasets, irrespective of large or subtle changes in longitudinal image sequences.},
archivePrefix = {arXiv},
arxivId = {1808.07553},
author = {Pathan, Sharmin and Hong, Yi},
eprint = {1808.07553},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Pathan - 2018 - Predictive Image Regression for Longitudinal Studies with Missing Data.pdf:pdf},
mendeley-groups = {PHD/Machine Learning/Deep Learning,PhDThesis/Review},
number = {Midl},
pages = {1--8},
title = {{Predictive Image Regression for Longitudinal Studies with Missing Data}},
year = {2018}
}
@article{Adhikari2019,
abstract = {We study regularized estimation in high-dimensional longitudinal classification problems, using the lasso and fused lasso regularizers. The constructed coefficient estimates are piecewise constant across the time dimension in the longitudinal problem, with adaptively selected change points (break points). We present an efficient algorithm for computing such estimates, based on proximal gradient descent. We apply our proposed technique to a longitudinal data set on Alzheimer's disease from the Cardiovascular Health Study Cognition Study. Using data analysis and a simulation study, we motivate and demonstrate several practical considerations such as the selection of tuning parameters and the assessment of model stability. While race, gender, vascular and heart disease, lack of caregivers, and deterioration of learning and memory are all important predictors of dementia, we also find that these risk factors become more relevant in the later stages of life.},
author = {Adhikari, Samrachana and Lecci, Fabrizio and Becker, James T and Junker, Brian W and Kuller, Lewis H and Lopez, Oscar L and Tibshirani, Ryan J},
doi = {10.1002/sim.8100},
journal = {Stat. Med.},
keywords = {Alzheimer's disease,cardiovascular health study,cognition study,longitudinal observational data,regularization},
mendeley-groups = {PhDThesis/Review},
number = {12},
pages = {2184--2205},
title = {{High-dimensional longitudinal classification with the multinomial fused lasso}},
volume = {38},
year = {2019}
}
@article{Zhao2018,
abstract = {Apolipoprotein E (apoE) is a lipid carrier in both the peripheral and the central nervous systems. Lipid-loaded apoE lipoprotein particles bind to several cell surface receptors to support membrane homeostasis and injury repair in the brain. Considering prevalence and relative risk magnitude, the $\epsilon$4 allele of the APOE gene is the strongest genetic risk factor for late-onset Alzheimer's disease (AD). ApoE4 contributes to AD pathogenesis by modulating multiple pathways, including but not limited to the metabolism, aggregation, and toxicity of amyloid-$\beta$ peptide, tauopathy, synaptic plasticity, lipid transport, glucose metabolism, mitochondrial function, vascular integrity, and neuroinflammation. Emerging knowledge on apoE-related pathways in the pathophysiology of AD presents new opportunities for AD therapy. We describe the biochemical and biological features of apoE and apoE receptors in the central nervous system. We also discuss the evidence and mechanisms addressing differential effects of apoE isoforms and the role of apoE receptors in AD pathogenesis, with a particular emphasis on the clinical and preclinical studies related to amyloid-$\beta$ pathology. Finally, we summarize the current strategies of AD therapy targeting apoE, and postulate that effective strategies require an apoE isoform-specific approach.},
author = {Zhao, Na and Liu, Chia-Chen and Qiao, Wenhui and Bu, Guojun},
doi = {10.1016/j.biopsych.2017.03.003},
issn = {00063223},
journal = {Biol. Psychiatry},
keywords = {Alzheimer's disease,Amyloid-$\beta$,Apolipoprotein E,Low-density lipoprotein receptor family,Synaptic plasticity,Tauopathy},
mendeley-groups = {PhDThesis/Hippo},
month = {feb},
number = {4},
pages = {347--357},
pmid = {28434655},
title = {{Apolipoprotein E, Receptors, and Modulation of Alzheimer's Disease}},
volume = {83},
year = {2018}
}
@article{Litjens2017,
abstract = {Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research.},
annote = {From Duplicate 2 (A survey on deep learning in medical image analysis - Litjens, Geert; Kooi, Thijs; Bejnordi, Babak Ehteshami; Setio, Arnaud Arindra Adiyoso; Ciompi, Francesco; Ghafoorian, Mohsen; van der Laak, Jeroen A.W.M.; van Ginneken, Bram; S{\'{a}}nchez, Clara I.)

This structure is similar to what we have: But they classify it by interest area or by feature, not by method. I was doing it by method all the time. Could it be better to use it that way?},
archivePrefix = {arXiv},
arxivId = {1702.05747},
author = {Litjens, Geert and Kooi, Thijs and Bejnordi, Babak Ehteshami and Setio, Arnaud Arindra Adiyoso and Ciompi, Francesco and Ghafoorian, Mohsen and van der Laak, Jeroen A.W.M. and van Ginneken, Bram and S{\'{a}}nchez, Clara I.},
doi = {10.1016/j.media.2017.07.005},
eprint = {1702.05747},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Litjens et al. - 2017 - A survey on deep learning in medical image analysis(2).pdf:pdf},
isbn = {978-1-5386-3220-8},
issn = {13618423},
journal = {Med. Image Anal.},
keywords = {Convolutional neural networks,Deep learning,Medical imaging,Survey},
mendeley-groups = {PHD/Reviews,PHD/stay{\_}MLorenzi{\_}Papers,Pensem/Article1,TRENDS,PhDThesis/Review},
month = {dec},
number = {1995},
pages = {60--88},
pmid = {28778026},
publisher = {Elsevier},
title = {{A survey on deep learning in medical image analysis}},
volume = {42},
year = {2017}
}
@article{Franke2012,
annote = {Longitudinal BrainAGE},
author = {Franke, Katja and Gaser, Christian},
doi = {10.1024/1662-9647/a000074},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Franke, Gaser - 2012 - Longitudinal Changes in Individual BrainAGE in Healthy Aging, Mild Cognitive Impairment, and Alzheimer's Disea(2).pdf:pdf},
issn = {1662-9647},
journal = {GeroPsych (Bern).},
mendeley-groups = {Review2,PhDThesis/Review},
number = {4},
pages = {235--245},
title = {{Longitudinal Changes in Individual BrainAGE in Healthy Aging, Mild Cognitive Impairment, and Alzheimer's Disease}},
volume = {25},
year = {2012}
}
@article{Thompson2004,
abstract = {We developed an anatomical mapping technique to detect hippocampal and ventricular changes in Alzheimer disease (AD). The resulting maps are sensitive to longitudinal changes in brain structure as the disease progresses. An anatomical surface modeling approach was combined with surface-based statistics to visualize the region and rate of atrophy in serial MRI scans and isolate where these changes link with cognitive decline. Fifty-two high-resolution MRI scans were acquired from 12 AD patients (age: 68.4 ± 1.9 years) and 14 matched controls (age: 71.4 ± 0.9 years), each scanned twice (2.1 ± 0.4 years apart). 3D parametric mesh models of the hippocampus and temporal horns were created in sequential scans and averaged across subjects to identify systematic patterns of atrophy. As an index of radial atrophy, 3D distance fields were generated relating each anatomical surface point to a medial curve threading down the medial axis of each structure. Hippocampal atrophic rates and ventricular expansion were assessed statistically using surface-based permutation testing and were faster in AD than in controls. Using color-coded maps and video sequences, these changes were visualized as they progressed anatomically over time. Additional maps localized regions where atrophic changes linked with cognitive decline. Temporal horn expansion maps were more sensitive to AD progression than maps of hippocampal atrophy, but both maps correlated with clinical deterioration. These quantitative, dynamic visualizations of hippocampal atrophy and ventricular expansion rates in aging and AD may provide a promising measure to track AD progression in drug trials. {\textcopyright} 2004 Elsevier Inc. All rights reserved.},
author = {Thompson, Paul M and Hayashi, Kiralee M and {De Zubicaray}, Greig I. and Janke, Andrew L and Rose, Stephen E and Semple, James and Hong, Michael S and Herman, David H and Gravano, David and Doddrell, David M and Toga, Arthur W},
doi = {10.1016/j.neuroimage.2004.03.040},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Thompson et al. - 2004 - Mapping hippocampal and ventricular change in Alzheimer disease.pdf:pdf},
issn = {10538119},
journal = {Neuroimage},
keywords = {Alzheimer disease,Atrophy,Brain mapping,Dementia,Longitudinal imaging,MRI},
mendeley-groups = {Papers bib/hipppaper/shape,PhDThesis/Hippo},
month = {aug},
number = {4},
pages = {1754--1766},
publisher = {Academic Press},
title = {{Mapping hippocampal and ventricular change in Alzheimer disease}},
volume = {22},
year = {2004}
}
@inproceedings{Eshaghi2017,
abstract = {We present a disease progression model with single vertex resolution that we apply to cortical thickness data. Our model works by clustering together vertices on the cortex that have similar temporal dynamics and building a common trajectory for vertices in the same cluster. The model estimates optimal stages and progression speeds for every subject. Simulated data show that it is able to accurately recover the vertex clusters and the underlying parameters. Moreover, our clustering model finds similar patterns of atrophy for typical Alzheimer's disease (tAD) subjects on two independent datasets: the Alzheimer's Disease Neuroimaging Initiative (ADNI) and a cohort from the Dementia Research Centre (DRC), UK. Using a separate set of subjects with Posterior Cortical Atrophy (PCA) from the DRC dataset, we also show that the model finds different patterns of atrophy in PCA compared to tAD. Finally, our model provides a novel way to parcellate the brain based on disease dynamics.},
address = {Cham},
author = {Marinescu, Ruazvan Valentin and Eshaghi, Arman and Lorenzi, Marco and Young, Alexandra L and Oxtoby, Neil P and Garbarino, Sara and Shakespeare, Timothy J and Crutch, Sebastian J and Alexander, Daniel C},
booktitle = {Inf. Process. Med. Imaging(IPMI). Lect. Notes Comput. Sci.},
isbn = {978-3-319-59050-9},
mendeley-groups = {PhDThesis/Review},
pages = {134--145},
publisher = {Springer International Publishing},
title = {{A Vertex Clustering Model for Disease Progression: Application to Cortical Thickness Images}},
year = {2017}
}
@inproceedings{Sadeghi2014,
abstract = {The term prediction implies expected outcome in the future, often based on a model and statistical inference. Longitudinal imaging studies offer the possibility to model temporal change trajectories of anatomy across populations of subjects. In the spirit of subject-specific analysis, such normative models can then be used to compare data from new subjects to the norm and to study progression of disease or to predict outcome. This paper follows a statistical inference approach and presents a framework for prediction of future observations based on past measurements and population statistics. We describe prediction in the context of nonlinear mixed effects modeling (NLME) where the full reference population's statistics (estimated fixed effects, variance-covariance of random effects, variance of noise) is used along with the individual's available observations to predict its trajectory. The proposed methodology is generic in regard to application domains. Here, we demonstrate analysis of early infant brain maturation from longitudinal DTI with up to three time points. Growth as observed in DTI-derived scalar invariants is modeled with a parametric function, its parameters being input to NLME population modeling. Trajectories of new subject's data are estimated when using no observation, only the first or the first two time points. Leave-one-out experiments result in statistics on differences between actual and predicted observations. We also simulate a clinical scenario of prediction on multiple categories, where trajectories predicted from multiple models are classified based on maximum likelihood criteria.},
annote = {Stadistical paper, not machine learning

Use stadistics from the population as reference to predict the trajectory of a new subject.},
author = {Sadeghi, Neda and Fletcher, P Thomas and Prastawa, Marcel and Gilmore, John H and Gerig, Guido},
booktitle = {Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)},
doi = {10.1007/978-3-319-10443-0_5},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sadeghi et al. - 2014 - Subject-specific prediction using nonlinear population modeling Application to early brain maturation from DTI.pdf:pdf},
isbn = {9783319104423},
issn = {16113349},
mendeley-groups = {PHD/Machine Learning/Longitudinal related,PhDThesis/Review},
number = {PART 3},
pages = {33--40},
pmid = {25320779},
title = {{Subject-specific prediction using nonlinear population modeling: Application to early brain maturation from DTI}},
volume = {8675 LNCS},
year = {2014}
}
@article{Desikan2011,
abstract = {The relationship between neurodegeneration and the 2 hallmark proteins of Alzheimer's disease, amyloid-$\beta$ (A$\beta$) and tau, is still unclear. Here, we examined 286 nondemented participants (107 cognitively normal older adults and 179 memory impaired individuals) who underwent longitudinal magnetic resonance (MR) imaging and lumbar puncture. Using mixed effects models, we investigated the relationship between longitudinal entorhinal cortex atrophy rate, cerebrospinal fluid (CSF) p-tau(181p) and CSF A$\beta$(1-42) . We found a significant relationship between elevated entorhinal cortex atrophy rate and decreased CSF A$\beta$(1-42) only with elevated CSF p-tau(181p) . Our findings indicate that A$\beta$-associated volume loss occurs only in the presence of phospho-tau in humans at risk for dementia.},
author = {Desikan, Rahul S and McEvoy, Linda K and Thompson, Wesley K and Holland, Dominic and Rddey, J. Cooper and Blennow, Kaj and Aisen, Paul S and Brewer, James B and Hyman, Bradley T and Dale, Anders M},
doi = {10.1002/ana.22509},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Desikan et al. - 2011 - Amyloid-$\beta$ associated volume loss occurs only in the presence of phospho-tau(2).pdf:pdf},
isbn = {0364-5134},
issn = {03645134},
journal = {Ann. Neurol.},
mendeley-groups = {PhDThesis/Review},
month = {oct},
number = {4},
pages = {657--661},
pmid = {22002658},
publisher = {NIH Public Access},
title = {{Amyloid-$\beta$ associated volume loss occurs only in the presence of phospho-tau}},
volume = {70},
year = {2011}
}
@article{Shi2015,
abstract = {Identifying neuroimaging biomarkers of Alzheimer's disease (AD) is of great im-portance for diagnosis and prognosis of the disease. In this study, we develop a novel nonlinear metric learning method to improve biomarker identification for Alzheimer's disease and its early stage Mild Cognitive Impairment (MCI). Formulated under a con-strained optimization framework, the proposed method learns a smooth nonlinear feature space transformation that pulls the samples of the same class closer to each other while pushing different classes further away. The thin-plate spline (TPS) is chosen as the geo-metric model due to its remarkable versatility and representation power in accounting for sophisticated deformations. In addition, a multi-resolution patch-based feature selection strategy is proposed to extract both cross-sectional and longitudinal features from MR brain images. Using the ADNI dataset, we evaluate the effectiveness of the proposed metric learning and feature extraction strategies and demonstrate the improvements over the state-of-the-art solutions within the same category.},
author = {Shi, Bibo and Chen, Yani and Science, Computer and Hobbs, Kevin and Smith, Charles D and Liu, Jundong},
doi = {10.5244/C.29.138},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Shi et al. - 2015 - Nonlinear Metric Learning for Alzheimer's Disease Diagnosis with Integration of Longitudinal Neuroimaging Features.pdf:pdf},
journal = {BMVC2015},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {1--13},
title = {{Nonlinear Metric Learning for Alzheimer ' s Disease Diagnosis with Integration of Longitudinal Neuroimaging Features}},
year = {2015}
}
@article{Prince2013,
abstract = {BACKGROUND The evidence base on the prevalence of dementia is expanding rapidly, particularly in countries with low and middle incomes. A reappraisal of global prevalence and numbers is due, given the significant implications for social and public policy and planning. METHODS In this study we provide a systematic review of the global literature on the prevalence of dementia (1980-2009) and metaanalysis to estimate the prevalence and numbers of those affected, aged ≥60 years in 21 Global Burden of Disease regions. RESULTS Age-standardized prevalence for those aged ≥60 years varied in a narrow band, 5{\%}-7{\%} in most world regions, with a higher prevalence in Latin America (8.5{\%}), and a distinctively lower prevalence in the four sub-Saharan African regions (2{\%}-4{\%}). It was estimated that 35.6 million people lived with dementia worldwide in 2010, with numbers expected to almost double every 20 years, to 65.7 million in 2030 and 115.4 million in 2050. In 2010, 58{\%} of all people with dementia lived in countries with low or middle incomes, with this proportion anticipated to rise to 63{\%} in 2030 and 71{\%} in 2050. CONCLUSION The detailed estimates in this study constitute the best current basis for policymaking, planning, and allocation of health and welfare resources in dementia care. The age-specific prevalence of dementia varies little between world regions, and may converge further. Future projections of numbers of people with dementia may be modified substantially by preventive interventions (lowering incidence), improvements in treatment and care (prolonging survival), and disease-modifying interventions (preventing or slowing progression). All countries need to commission nationally representative surveys that are repeated regularly to monitor trends.},
author = {Prince, Martin and Bryce, Renata and Albanese, Emiliano and Wimo, Anders and Ribeiro, Wagner and Ferri, Cleusa P.},
doi = {10.1016/j.jalz.2012.11.007},
issn = {15525260},
journal = {Alzheimer's Dement.},
mendeley-groups = {PhDThesis/Review},
month = {jan},
number = {1},
pages = {63--75.e2},
pmid = {23305823},
title = {{The global prevalence of dementia: A systematic review and metaanalysis}},
volume = {9},
year = {2013}
}
@incollection{Cates2017,
abstract = {The ShapeWorks software is an open-source implementation of a methodology for constructing compact statistical point-based models of shape called Particle-Based Modeling (PBM). PBM represents shape surface geometry using dynamic particle systems, thus avoiding reliance on any specific shape parameterization. Correspondence-point positions are optimized using an entropy-based minimization that balances the simplicity of the model (compactness) with the accuracy of the surface representations. The entropy-minimization model may also include image- and surface-based features, such as surface curvature information, in order to find better correspondence in complex and varied anatomy. PBM requires very little preprocessing or parameter tuning and has been applied to a wide variety of biomedical shape analysis problems, including neurobiology, genetic phenotyping, orthopedics, and cardiology. The ShapeWorks software includes extensions to the basic PBM optimization to construct joint models of multiple anatomical shapes, regression models, and to specify surface boundaries on shapes, such as cutting planes. ShapeWorks also includes software for visualization and analysis of correspondence models, including a method for estimating very dense correspondence models that are suitable for biomechanical simulation and other computational applications.},
author = {Cates, Joshua and Elhabian, Shireen and Whitaker, Ross},
booktitle = {Stat. Shape Deform. Anal. Methods, Implement. Appl.},
doi = {10.1016/B978-0-12-810493-4.00012-2},
isbn = {9780128104941},
keywords = {Anatomy,Biomedical imaging,Image analysis,Open source software,Statistical modeling,Statistical shape analysis},
mendeley-groups = {Papers bib/hipppaper/shape/shape-revision,PhDThesis/Hippo},
month = {mar},
pages = {257--298},
publisher = {Elsevier Inc.},
title = {{ShapeWorks: Particle-Based Shape Correspondence and Visualization Software}},
year = {2017}
}
@article{Lane2018,
abstract = {Alzheimer's disease, the commonest cause of dementia, is a growing global health concern with huge implications for individuals and society. In this review, current understanding of the epidemiology, genetics, pathology and pathogenesis of Alzheimer's disease is outlined, before its clinical presentation and current treatment strategies are discussed. Finally, the review discusses how our enhanced understanding of Alzheimer pathogenesis, including the recognition of a protracted preclinical phase, is informing new therapeutic strategies with the aim of moving from treatment to prevention.},
author = {Lane, C. A. and Hardy, J. and Schott, J. M.},
doi = {10.1111/ene.13439},
issn = {14681331},
journal = {Eur. J. Neurol.},
keywords = {Alzheimer's disease,epidemiology,genetics,pathogenesis,pathology,treatment},
mendeley-groups = {Review2,PhDThesis/Review},
month = {jan},
number = {1},
pages = {59--70},
pmid = {28872215},
title = {{Alzheimer's disease}},
volume = {25},
year = {2018}
}

@inproceedings{Bone2017,
abstract = {{\textcopyright} Springer International Publishing AG 2017. We propose a method to predict the subject-specific longitudinal progression of brain structures extracted from baseline MRI, and evaluate its performance on Alzheimer's disease data. The disease progression is modeled as a trajectory on a group of diffeomorphisms in the context of large deformation diffeomorphic metric mapping (LDDMM). We first exhibit the limited predictive abilities of geodesic regression extrapolation on this group. Building on the recent concept of parallel curves in shape manifolds, we then introduce a second predictive protocol which personalizes previously learned trajectories to new subjects, and investigate the relative performances of two parallel shifting paradigms. This design only requires the baseline imaging data. Finally, coefficients encoding the disease dynamics are obtained from longitudinal cognitive measurements for each subject, and exploited to refine our methodology which is demonstrated to successfully predict the follow-up visits.},
author = {B{\^{o}}ne, Alexandre and Louis, Maxime and Routier, Alexandre and Samper, Jorge and Bacci, Michael and Charlier, Benjamin and Colliot, Olivier and Durrleman, Stanley},
booktitle = {Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-67675-3_10},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/B{\^{o}}ne et al. - 2017 - Prediction of the progression of subcortical brain structures in Alzheimer's disease from baseline(2).pdf:pdf},
isbn = {9783319676746},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {101--113},
title = {{Prediction of the Progression of Subcortical Brain Structures in Alzheimer's Disease from Baseline}},
volume = {10551},
year = {2017}
}

@book{Vardhan2015,
abstract = {Early brain maturational processes such asmyelinationman- ifest as changes in the relative appearance of white-gray matter tissue classes in MR images. Imaging modalities such as T1W (T1-Weighted) and T2W (T2-Weighted) MRI each display specific patterns of appear- ance change associated with distinct neurobiological components of these maturational processes. In this paper we present a framework to jointly model multimodal appearance changes across time for a longitudinal imaging dataset, resulting in quantitative assessment of the patterns of early brain maturation not yet available to clinicians. We measure appearance by quantifying contrast between white and gray matter in terms of the distance between their intensity distributions, a method demonstrated to be relatively stable to interscan variability. A multi- variate nonlinear mixed effects (NLME) model is used for joint statis- tical modeling of this contrast measure across multiple imaging modal- ities. The multivariate NLME procedure considers correlations between modalities in addition to intra-modal variability. The parameters of the logistic growth function used in NLME modeling provide useful quanti- tative information about the timing and progression of contrast change in multimodal datasets. Inverted patterns of relative white-gray matter intensity gradient that are observable in T1W scans with respect to T2W scans are characterized by the SIR (Signal Intensity Ratio). The CON- TDIR (Contrast Direction) which measures the direction of the gradient at each time point relative to that in the adult-like scan adds a direc- tional attribute to contrast. The major contribution of this paper is a framework for joint multimodal temporal modeling of white-gray matter MRI contrast change and estimation of subject-specific and population This growth trajectories. Results confirm qualitative descriptions of growth patterns in pediatric radiology studies and our new quantitative mod- eling scheme has the potential to advance understanding of variability of brain tissue maturation and to eventually differentiate normal from abnormal growth for early diagnosis of pathology.},
annote = {Stadistical study of longitudinal data. 

Useful for the longitudinal review.},
archivePrefix = {arXiv},
arxivId = {9780201398298},
author = {Vardhan, Avantika and Prastawa, Marcel and Sadeghi, Neda and Vachet, Clement and Piven, Joseph and Gerig, Guido},
booktitle = {LNCS},
doi = {10.1007/978-3-319-14905-9},
eprint = {9780201398298},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Vardhan et al. - 2015 - Joint Longitudinal Modeling of Brain Appearance in Multimodal MRI for the Characterization of Early Brain Develo.pdf:pdf},
isbn = {978-3-319-14904-2},
issn = {03029743},
mendeley-groups = {PHD/Machine Learning/Longitudinal related,PhDThesis/Review},
pages = {49--63},
pmid = {4520227},
publisher = {Springer International Publishing},
title = {{Joint Longitudinal Modeling of Brain Appearance in Multimodal MRI for the Characterization of Early Brain Developmental Processes}},
volume = {8682},
year = {2015}
}
@article{Al-Qazzaz2014,
abstract = {The early detection and classification of dementia are important clinical support tasks for medical practitioners in customizing patient treatment programs to better manage the development and progression of these diseases. Efforts are being made to diagnose these neurodegenerative disorders in the early stages. Indeed, early diagnosis helps patients to obtain the maximum treatment benefit before significant mental decline occurs. The use of electroencephalogram as a tool for the detection of changes in brain activities and clinical diagnosis is becoming increasingly popular for its capabilities in quantifying changes in brain degeneration in dementia. This paper reviews the role of electroencephalogram as a biomarker based on signal processing to detect dementia in early stages and classify its severity. The review starts with a discussion of dementia types and cognitive spectrum followed by the presentation of the effective preprocessing denoising to eliminate possible artifacts. It continues with a description of feature extraction by using linear and nonlinear techniques, and it ends with a brief explanation of vast variety of separation techniques to classify EEG signals. This paper also provides an idea from the most popular studies that may help in diagnosing dementia in early stages and classifying through electroencephalogram signal processing and analysis.},
author = {Al-Qazzaz, Noor Kamal and Ali, Sawal Hamid Bin Md and Ahmad, Siti Anom and Chellappan, Kalaivani and Islam, Md Shabiul and Escudero, Javier},
doi = {10.1155/2014/906038},
edition = {2014/06/30},
issn = {1537-744X},
journal = {ScientificWorldJournal.},
keywords = {Dementia/*diagnosis,Electroencephalography/*methods,Humans,Signal Processing, Computer-Assisted},
language = {eng},
mendeley-groups = {Review2,PhDThesis/Review},
pages = {906038},
publisher = {Hindawi Publishing Corporation},
title = {{Role of EEG as biomarker in the early detection and classification of dementia}},
volume = {2014},
year = {2014}
}
@article{Lorenzi2019,
abstract = {Disease progression modeling (DPM) of Alzheimer's disease (AD) aims at revealing long term pathological trajectories from short term clinical data. Along with the ability of providing a data-driven description of the natural evolution of the pathology, DPM has the potential of representing a valuable clinical instrument for automatic diagnosis, by explicitly describing the biomarker transition from normal to pathological stages along the disease time axis. In this work we reformulated DPM within a probabilistic setting to quantify the diagnostic uncertainty of individual disease severity in an hypothetical clinical scenario, with respect to missing measurements, biomarkers, and follow-up information. We show that the staging provided by the model on 582 amyloid positive testing individuals has high face validity with respect to the clinical diagnosis. Using follow-up measurements largely reduces the prediction uncertainties, while the transition from normal to pathological stages is mostly associated with the increase of brain hypo-metabolism, temporal atrophy, and worsening of clinical scores. The proposed formulation of DPM provides a statistical reference for the accurate probabilistic assessment of the pathological stage of de-novo individuals, and represents a valuable instrument for quantifying the variability and the diagnostic value of biomarkers across disease stages.},
author = {Lorenzi, Marco and Filippone, Maurizio and Frisoni, Giovanni B. and Alexander, Daniel C. and Ourselin, Sebastien},
doi = {10.1016/j.neuroimage.2017.08.059},
issn = {10959572},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Clinical trials,Diagnosis,Disease progression modeling,Gaussian process},
mendeley-groups = {Review2,PhDThesis/Review},
month = {apr},
pages = {56--68},
publisher = {Academic Press Inc.},
title = {{Probabilistic disease progression modeling to characterize diagnostic uncertainty: Application to staging and prediction in Alzheimer's disease}},
volume = {190},
year = {2019}
}
@article{Gordon2016,
abstract = {IMPORTANCEPreclinicalAlzheimerdisease(AD)canbestagedusinga2-factormodeldenotingthepresenceorabsenceof$\beta$-amyloid(A$\beta$+/−)andneurodegeneration(ND+/−).Theassociationofthesestageswithlongitudinalbiomarkeroutcomesisunknown.OBJECTIVEToexaminewhetherlongitudinalA$\beta$accumulationandhippocampalatrophydifferbasedoninitialpreclinicalstaging.DESIGN,SETTING,ANDPARTICIPANTSThislongitudinalpopulation-basedcohortstudyuseddatacollectedattheKnightAlzheimerDiseaseResearchCenter,WashingtonUniversity,StLouis,Missouri,fromDecember1,2006,toJune31,2015.Cognitivelynormalolderadults(n=174)wererecruitedfromthelongitudinalAdultChildrenStudyandHealthyAgingandSenileDementiaStudyattheKnightAlzheimerDiseaseResearchCenter.Atbaseline,allparticipantshadmagneticresonanceimaging(MRI)scans,positronemissiontomography(PET)scanswithcarbon11–labeledPittsburghCompoundB(PiB),andcerebrospinalfluidassaysoftauandphosphorylatedtau(ptau)acquiredwithin12months.Usingthebaselinebiomarkers,individualswereclassifiedintopreclinicalstage0(A$\beta$−/ND−),1(A$\beta$+/ND−),or2+(A$\beta$+/ND+)orsuspectednon-ADpathophysiology(SNAP;A$\beta$−/ND+).MAINOUTCOMESANDMEASURESSubsequentlongitudinalaccumulationofA$\beta$assessedwithPiBPETandlossofhippocampalvolumeassessedwithMRIineachgroup.RESULTSAmongthe174participants(81men[46.6{\%}];93women[53.4{\%}];mean[SD]age,65.7[8.9]years),aproportion(14{\%}-17{\%})ofindividualswithneurodegenerationalone(SNAP)laterdemonstratedA$\beta$+.TheratesofA$\beta$accumulationandlossofhippocampalvolumeinindividualswithSNAPwereindistinguishablefromthosewithoutanypathologicfeaturesatbaseline(forA$\beta$accumulation:whenhippocampalvolumewasusedtodefineND,t=0.00[P{\textgreater}.99];whentauandptauwereusedtodefineND,t=−0.02[P=.98];forlossofhippocampalvolume:whenhippocampalvolumewasusedtodefineND,t=–1.34[P=.18];whentauandptauwereusedtodefineND,t=0.84[P=.40]).Laterpreclinicalstages(stages1and2+)hadelevatedA$\beta$accumulation.UsinghippocampalvolumetodefineND,individualswithstage1hadacceleratedA$\beta$accumulationrelativetostage0(t=11.06;P{\textless}.001),stage2+(t=2.10;P=.04),andSNAP(t=9.32;P{\textless}.001),andthosewithstage2+hadacceleratedA$\beta$accumulationrelativetostage0(t=4.38;P{\textless}.001)andSNAP(t=4.08;P{\textless}.001).WhenNDwasdefinedusingtauandptau,individualswithstage2+hadacceleratedA$\beta$accumulationrelativetostage0(t=4.96)andSNAP(t=4.06),andthosewithstage1hadacceleratedA$\beta$accumulationrelativetostage0(t=8.44)andSNAP(t=6.61)(P{\textless}.001forallcomparisons).WhenNDwasdefinedusingcerebrospinalfluidbiomarkers,individualswithstage2+hadacceleratedhippocampalatrophyrelativetostage0(t=–3.41;P{\textless}.001),stage1(t=–2.48;P=.03),andSNAP(t=–2.26;P=.03).CONCLUSIONSANDRELEVANCEMoreadvancedpreclinicalstagesofADhavegreaterlongitudinalA$\beta$accumulation.SNAPappearsmostlikelytocaptureinherentindividualvariabilityinbrainstructureortorepresentcomorbidpathologicfeaturesratherthanearlyemergingAD.Lowhippocampalvolumesorelevatedlevelsoftauorptauinisolationmaynotaccuratelyrepresentongoingneurodegenerativeprocesses.},
annote = {STATISTICAL},
author = {Gordon, Brian A and Blazey, Tyler and Su, Yi and Fagan, Anne M and Holtzman, David M and Morris, John C and Benzinger, Tammie L S},
doi = {10.1001/jamaneurol.2016.2642},
issn = {21686149},
journal = {JAMA Neurol.},
mendeley-groups = {PhDThesis/Review},
number = {10},
pages = {1192--1200},
pmid = {27548756},
title = {{Longitudinal $\beta$-amyloid deposition and hippocampal volume in preclinical Alzheimer disease and suspected non-Alzheimer disease pathophysiology}},
volume = {73},
year = {2016}
}
@inproceedings{Sanroma2017,
abstract = {{\textcopyright} Springer International Publishing AG 2017. Alzheimer's disease (AD) is characterized by a progressive decline in the cognitive functions accompanied by an atrophic process which can already be observed in the early stages using magnetic resonance images (MRI). Individualized prediction of future progression to AD, when patients are still in the mild cognitive impairment (MCI) stage, has potential impact for preventive treatment. Atrophy patterns extracted from longitudinal MRI sequences provide valuable information to identify MCI patients at higher risk of developing AD in the future. We present a novel descriptor that uses the similarity between local image patches to encode local displacements due to atrophy between a pair of longitudinal MRI scans. Using a conventional logistic regression classifier, our descriptor achieves 76{\%} accuracy in predicting which MCI patients will progress to AD up to 3 years before conversion.},
author = {Sanroma, Gerard and Andrea, V{\'{i}}ctor and Benkarim, Oualid M. and Manj{\'{o}}n, Jos{\'{e}} V. and Coup{\'{e}}, Pierrick and Camara, Oscar and Piella, Gemma and {Gonz{\'{a}}lez Ballester}, Miguel A.},
booktitle = {Lect. Notes Comput. Sci.},
doi = {10.1007/978-3-319-67434-6_9},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Sanroma et al. - 2017 - Patch-Based Techniques in Medical Imaging(3).pdf:pdf},
isbn = {9783319674339},
issn = {16113349},
keywords = {Early AD prediction,Longitudinal analysis,Non-local patch-based label fusion},
mendeley-groups = {Review2,PhDThesis/Hippo},
month = {sep},
pages = {74--81},
publisher = {Springer, Cham},
title = {{Early prediction of alzheimer's disease with non-local patch-based longitudinal descriptors}},
volume = {10530},
year = {2017}
}
@article{Samper-Gonzalez2018,
abstract = {A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimer's disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS. All the code of the framework and the experiments is publicly available: general-purpose tools have been integrated into the Clinica software (www.clinica.run) and the paper-specific code is available at: https://gitlab.icm-institute.org/aramislab/AD-ML.},
author = {Samper-Gonz{\'{a}}lez, Jorge and Burgos, Ninon and Bottani, Simona and Fontanella, Sabrina and Lu, Pascal and Marcoux, Arnaud and Routier, Alexandre and Guillon, J{\'{e}}r{\'{e}}my and Bacci, Michael and Wen, Junhao and Bertrand, Anne and Bertin, Hugo and Habert, Marie-Odile and Durrleman, Stanley and Evgeniou, Theodoros and Colliot, Olivier},
doi = {https://doi.org/10.1016/j.neuroimage.2018.08.042},
issn = {1053-8119},
journal = {Neuroimage},
keywords = {Alzheimer's disease,Classification,Magnetic resonance imaging,Open-source,Positron emission tomography,Reproducibility},
mendeley-groups = {PhDThesis/Review},
pages = {504--521},
title = {{Reproducible evaluation of classification methods in Alzheimer's disease: Framework and application to MRI and PET data}},
volume = {183},
year = {2018}
}
@article{Oxtoby2018,
abstract = {Dominantly-inherited Alzheimer's disease is widely hoped to hold the key to developing interventions for sporadic late onset Alzheimer's disease. We use emerging techniques in generative data-driven disease-progression modelling to characterise dominantly-inherited Alzheimer's disease progression with unprecedented resolution, and without relying upon familial estimates of years until symptom onset (EYO). We retrospectively analysed biomarker data from the sixth data freeze of the Dominantly Inherited Alzheimer Network observational study, including measures of amyloid proteins and neurofibrillary tangles in the brain, regional brain volumes and cortical thicknesses, brain glucose hypometabolism, and cognitive performance from the Mini-Mental State Examination (all adjusted for age, years of education, sex, and head size, as appropriate). Data included 338 participants with known mutation status (211 mutation carriers: 163 PSEN1; 17 PSEN2; and 31 APP) and a baseline visit (age 19-66; up to four visits each, 1.1±1.9 years in duration; spanning 30 years before, to 21 years after, parental age of symptom onset). We used an event-based model to estimate sequences of biomarker changes from baseline data across disease subtypes (mutation groups), and a differential-equation model to estimate biomarker trajectories from longitudinal data (up to 66 mutation carriers, all subtypes combined). The two models concur that biomarker abnormality proceeds as follows: amyloid deposition in cortical then sub-cortical regions (approximately 24±11 years before onset); CSF p-tau (17±8 years), tau and A$\beta$42 changes; neurodegeneration first in the putamen and nucleus accumbens (up to 6±2 years); then cognitive decline (7±6 years), cerebral hypometabolism (4±4 years), and further regional neurodegeneration. Our models predicted symptom onset more accurately than EYO: root-mean-squared error of 1.35 years versus 5.54 years. The models reveal hidden detail on dominantly-inherited Alzheimer's disease progression, as well as providing data-driven systems for fine-grained patient staging and prediction of symptom onset with great potential utility in clinical trials.},
author = {Oxtoby, Neil P and Young, Alexandra L and Cash, David M and Benzinger, Tammie L S and Fagan, Anne M and Morris, John C and Bateman, Randall J and Fox, Nick C and Schott, Jonathan M and Alexander, Daniel C},
doi = {10.1093/brain/awy050},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Oxtoby et al. - 2018 - Data-driven models of dominantly-inherited Alzheimer's disease progression(2).pdf:pdf},
issn = {0006-8950},
journal = {Brain A J. Neurol.},
mendeley-groups = {Review2,PhDThesis/Review},
month = {jan},
number = {5},
pages = {1529 -- 1544},
publisher = {Cold Spring Harbor Laboratory},
title = {{Data-driven models of dominantly-inherited Alzheimer's disease progression}},
volume = {141},
year = {2018}
}
@article{Lim2017,
abstract = {Background: The association between the apolipoprotein E (APOE) ϵ4 allele and high risk of developing Alzheimer's disease (AD) dementia before the age of 80 has been recognized for over 30 years. However, the timing and mode of action of APOE is not understood, nor has there been a detailed analysis of the effect of APOE genotype on memory, hippocampal volume, and amyloid-$\beta$ (A$\beta$) levels in cognitively normal adults. Objective: Examine the effect of APOE allelic genotype on the relationship between A$\beta$ levels, hippocampal volume, and memory in cognitively normal adults. Methods: This is a cross-sectional study of 989 cognitively normal older adults enrolled in the Australian Imaging, Biomarkers and Lifestyle (AIBL) study, all of whom underwent APOE genotyping and memory assessment. A subset of this group underwent PET neuroimaging for A$\beta$ (n = 585) and MRI for hippocampal volume (n = 303). Results: APOE ϵ4 homozygotes (ϵ4/ϵ4) showed significantly worse episodic memory and higher A$\beta$ levels than ϵ4 heterozygotes. The relationship between increasing A$\beta$ levels and worse episodic memory was significant for ϵ3 homozygotes (ϵ3/ϵ3), ϵ4 heterozygotes, and strongest for ϵ4 homozygotes. There were no differences in hippocampal volume between APOE groups; the relationship between smaller hippocampal volume and worse episodic memory was significant only for ϵ4 homozygotes. Conclusion: APOE acts in a co-dominant fashion on A$\beta$ levels, episodic memory, and hippocampal volume in cognitively normal older adults. APOE ϵ4 is central to the events that lead to AD in cognitively normal older adults, likely through a quantitative role in the disruption of A$\beta$ clearance.},
author = {Lim, Yen Ying and Williamson, Robert and Laws, Simon M. and Villemagne, Victor L. and Bourgeat, Pierrick and Fowler, Christopher and Rainey-Smith, Stephanie and Salvado, Olivier and Martins, Ralph N. and Rowe, Christopher C. and Masters, Colin L. and Maruff, Paul and Chambers, Brian and Chiu, Edmond and Clarnette, Roger and Darby, David and Davison, Mary and Drago, John and Drysdale, Peter and Gilbert, Jacqueline and Lim, Kwang and Lautenschlager, Nicola and LoGiudice, Dina and McCardle, Peter and McFarlane, Steve and Mander, Alastair and Merory, John and O'Connor, Daniel and Scholes, Ron and Samuel, Mathew and Trivedi, Darshan and Woodward, Michael},
doi = {10.3233/JAD-170072},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {Alzheimer's disease,amyloid,apolipoprotein E,hippocampal volume,memory,mild cognitive impairment},
mendeley-groups = {Papers bib/cimlr{\_}extension,Papers bib,Papers bib/hipppaper,PhDThesis/Hippo},
number = {4},
pages = {1293--1302},
publisher = {IOS Press},
title = {{Effect of APOE Genotype on Amyloid Deposition, Brain Volume, and Memory in Cognitively Normal Older Individuals}},
volume = {58},
year = {2017}
}
@article{Marti-Juan2019,
abstract = {Alzheimer's disease (AD) affects millions of people and is a major rising problem in health care worldwide. Recent research suggests that AD could have different subtypes, presenting differences in how the disease develops. Characterizing those subtypes could be key to deepen the understanding of this complex disease. In this paper, we used a multivariate, non-supervised clustering method over blood-based markers to find subgroups of patients defined by distinctive blood profiles. Our analysis on ADNI database identified 4 possible subgroups, each with a different blood profile. More importantly, we show that subgroups with different profiles have a different relationship between brain phenotypes detected in magnetic resonance imaging and disease condition.},
author = {Mart{\'{i}}-Juan, Gerard and Sanroma, Gerard and Piella, Gemma},
doi = {10.1371/journal.pone.0211121},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Mart{\'{i}}-Juan, Sanroma, Piella - 2019 - Revealing heterogeneity of brain imaging phenotypes in Alzheimer's disease based on unsupervised(2).pdf:pdf},
issn = {19326203},
journal = {PLoS One},
mendeley-groups = {PhDThesis/Hippo},
number = {3},
title = {{Revealing heterogeneity of brain imaging phenotypes in Alzheimer's disease based on unsupervised clustering of blood marker profiles}},
volume = {14},
year = {2019}
}
@article{Bernal-Rusiel2013,
abstract = {Longitudinal neuroimaging (LNI) studies are rapidly becoming more prevalent and growing in size. Today, no standardized computational tools exist for the analysis of LNI data and widely used methods are sub-optimal for the types of data encountered in real-life studies. Linear Mixed Effects (LME) modeling, a mature approach well known in the statistics community, offers a powerful and versatile framework for analyzing real-life LNI data. This article presents the theory behind LME models, contrasts it with other popular approaches in the context of LNI, and is accompanied with an array of computational tools that will be made freely available through FreeSurfer - a popular Magnetic Resonance Image (MRI) analysis software package.Our core contribution is to provide a quantitative empirical evaluation of the performance of LME and competing alternatives popularly used in prior longitudinal structural MRI studies, namely repeated measures ANOVA and the analysis of annualized longitudinal change measures (e.g. atrophy rate). In our experiments, we analyzed MRI-derived longitudinal hippocampal volume and entorhinal cortex thickness measurements from a public dataset consisting of Alzheimer's patients, subjects with mild cognitive impairment and healthy controls. Our results suggest that the LME approach offers superior statistical power in detecting longitudinal group differences. ?? 2012 Elsevier Inc.},
annote = {Aqui hi ha molt de state of the art},
archivePrefix = {arXiv},
arxivId = {NIHMS150003},
author = {Bernal-Rusiel, Jorge L. and Greve, Douglas N. and Reuter, Martin and Fischl, Bruce and Sabuncu, Mert R.},
doi = {10.1016/j.neuroimage.2012.10.065},
eprint = {NIHMS150003},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Bernal-Rusiel et al. - 2013 - Statistical analysis of longitudinal neuroimage data with Linear Mixed Effects models(2).pdf:pdf},
isbn = {1095-9572 (Electronic) 1053-8119 (Linking)},
issn = {10538119},
journal = {Neuroimage},
keywords = {Linear Mixed Effects Models,Linear Mixed Effects models,Longitudinal Studies,Longitudinal studies,Statistical Analysis,Statistical analysis},
mendeley-groups = {PHD/Machine Learning/Longitudinal related,PhDThesis/Review},
number = {0},
pages = {249--260},
pmid = {23123680},
title = {{Statistical analysis of longitudinal neuroimage data with Linear Mixed Effects models}},
volume = {66},
year = {2013}
}
@article{Lawrence2017,
abstract = {Alzheimer's disease (AD) is a progressive and fatal neurodegenerative disease, with no effective treatment or cure. A gold standard therapy would be treatment to slow or halt disease progression; however, knowledge of causation in the early stages of AD is very limited. In order to determine effective endpoints for possible therapies, a number of quantitative surrogate markers of disease progression have been suggested, including biochemical and imaging biomarkers. The dynamics of these various surrogate markers over time, particularly in relation to disease development, are, however, not well characterized. We reviewed the literature for studies that measured cerebrospinal fluid or plasma amyloid-$\beta$ and tau, or took magnetic resonance image or fluorodeoxyglucose/Pittsburgh compound B-positron electron tomography scans, in longitudinal cohort studies. We summarized the properties of the major cohort studies in various countries, commonly used diagnosis methods and study designs. We have concluded that additional studies with repeat measures over time in a representative population cohort are needed to address the gap in knowledge of AD progression. Based on our analysis, we suggest directions in which research could move in order to advance our understanding of this complex disease, including repeat biomarker measurements standardization and increased sample sizes.},
annote = {From Duplicate 1 (A Systematic Review of Longitudinal Studies Which Measure Alzheimer's Disease Biomarkers - Lawrence, Emma; Vegvari, Carolin; Ower, Alison; Hadjichrysanthou, Christoforos; De Wolf, Frank; Anderson, Roy M)

Review important.

Focus on medical STUDIES (aka, datasets) for longitudinal DATA of progression.},
author = {Lawrence, Emma and Vegvari, Carolin and Ower, Alison and Hadjichrysanthou, Christoforos and {De Wolf}, Frank and Anderson, Roy M},
doi = {10.3233/JAD-170261},
file = {:C$\backslash$:/Users/gerar/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Lawrence et al. - 2017 - A systematic review of longitudinal studies which measure Alzheimer's disease biomarkers(2).pdf:pdf},
issn = {18758908},
journal = {J. Alzheimer's Dis.},
keywords = {Alzheimer's disease,biomarker,cross-sectional,dementia,longitudinal},
mendeley-groups = {PHD/Reviews,PhDThesis/Review},
number = {4},
pages = {1359--1379},
pmid = {28759968},
publisher = {IOS Press},
title = {{A systematic review of longitudinal studies which measure Alzheimer's disease biomarkers}},
volume = {59},
year = {2017}
}