patchlib

A library for working with N-D patches, also including several 2D and 3D examples to illustrate the library applicability.

• See functions for a (non-exhaustive) list of functions.
• See examples for a list of examples to get you started.
• See papers section below for a list of academic papers in which we used this library

Installation

Set up code

Do a git pull or download patchlib as a zip. Unzip the files, and add the folder to your MATLAB path:
>> addpath(genpath('PATH_TO_PATCHLIB'));

Then run setup script:
>> verifypatchlib.m;

Dependencies

Add each of the following toolboxes to your MATLAB path:

The following toolbox is required by all of the code:

• matlib

The MRF-related methods (e.g. for spatial regularization):

• UGM library by Mark Schmidt

Papers

If you find this library useful, please cite one of the following papers for which the library was initially built (download bib):

• Medical Image Imputation from Image Collections
  A.V. Dalca, K.L. Bouman, W.T. Freeman, M.R. Sabuncu, N.S. Rost, P. Golland
  IEEE TMI: Transactions on Medical Imaging 38.2 (2019): 504-514. eprint arXiv:1808.05732

• Population Based Image Imputation
  A.V. Dalca, K.L. Bouman, W.T. Freeman, M.R. Sabuncu, N.S. Rost, P. Golland
  In Proc. IPMI: International Conference on Information Processing and Medical Imaging. LNCS 10265, pp 1-13. 2017.

• Patch-Based Discrete Registration of Clinical Brain Images
  A.V. Dalca, A. Bobu, N.S. Rost, P. Golland
  In Proc. MICCAI-PATCHMI Patch-based Techniques in Medical Imaging, LNCS 9993, pp 60-67, 2016.

Contributors

Adrian Dalca (web | email)
Katie Bouman (web | email)

Contact Please let us know of any questions/suggestions by opening an issue or emailing us at {adalca,klbouman}@csail.mit.edu