Home

Awesome

<h1 align="center"> Convolutional neural networks for classification of Alzheimer's disease: Overview and reproducible evaluation </h1>

:warning: Note: :warning:

This project evolved in a python package for the processing of neuroimaging data with deep learning methods. Please use the ClinicaDL library to benefit from the last updates!

About the project

This repository hosts the code source for reproducible experiments on automatic classification of Alzheimer's disease (AD) using anatomical MRI data. It allows training autoencoders and convolutional neural networks. The journal version of the paper describing this work is available here and an Open Access version is available here.

Pretrained models

Some pretrained CNNs can be obtained here: https://zenodo.org/record/3491003. These models were obtained during the experiments for publication.

Bibliography

All the papers described in the "State of the art" section of the manuscript may be found at this URL address: https://www.zotero.org/groups/2337160/ad-dl.