Residual and Plain Convolutional Neural Networks for 3D Brain MRI Classification

TL;DR

This paper demonstrates that residual and plain 3D CNN architectures can classify Alzheimer's disease, mild cognitive impairment, and normal controls from MRI scans without extensive feature extraction, simplifying neuroimaging analysis.

Contribution

It introduces a deep learning approach using residual and plain 3D CNNs that bypass traditional feature extraction for brain MRI classification.

Findings

Achieved comparable performance to traditional methods

Simplified the neuroimaging analysis pipeline

Validated on ADNI dataset with promising results

Abstract

In the recent years there have been a number of studies that applied deep learning algorithms to neuroimaging data. Pipelines used in those studies mostly require multiple processing steps for feature extraction, although modern advancements in deep learning for image classification can provide a powerful framework for automatic feature generation and more straightforward analysis. In this paper, we show how similar performance can be achieved skipping these feature extraction steps with the residual and plain 3D convolutional neural network architectures. We demonstrate the performance of the proposed approach for classification of Alzheimer's disease versus mild cognitive impairment and normal controls on the Alzheimer's Disease National Initiative (ADNI) dataset of 3D structural MRI brain scans.