Skip to content

mustafahakkoz/ALZHEIMER-contest

Repository files navigation

Clog Loss: Advance Alzheimer’s Research with Stall Catchers

A submission for drivendata.com 3D-MRI video contest.

team: ru_kola
members: @mustafahakkoz, @Aysenuryilmazz
rank: 44 / 922
score (matthew's correlation coefficient): 0.1564
dataset: Stall Catchers micro dataset 2399 3D-MRI videos with 70/30 class ratio (flowing/stalled)

The main idea of the project is preprocessing videos hardly by blending all frames in to single one with different approaches, then applying a CNN classifier on them.

PROCESSING VIDEOS AND SIMPLE BLENDING METHOD

CONTOUR ORIENTATION METHOD 1: Blending Contours

CONTOUR ORIENTATION METHOD 2: Blending Frames

CNN CLASSIFIER

3 convolution+maxpooling dual layers followed by 1 fully-connected layer just as described in keras.io blog trained on kaggle's gpu kernels.

FOLDER CONTENT

About

Submission for drivendata 3D-MRI video contest

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages