Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks

TL;DR

This study employs 3D convolutional neural networks and autoencoders on MRI data to accurately predict Alzheimer's disease, demonstrating superior performance over existing classifiers with state-of-the-art results.

Contribution

The paper introduces a deep learning approach using 3D CNNs and autoencoders for Alzheimer's prediction, achieving improved accuracy on the ADNI dataset.

Findings

3D CNNs outperform other classifiers

Achieved state-of-the-art prediction accuracy

Validated on 2,265 MRI scans

Abstract

Pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease have been the subject of extensive research in recent years. In this paper, we use deep learning methods, and in particular sparse autoencoders and 3D convolutional neural networks, to build an algorithm that can predict the disease status of a patient, based on an MRI scan of the brain. We report on experiments using the ADNI data set involving 2,265 historical scans. We demonstrate that 3D convolutional neural networks outperform several other classifiers reported in the literature and produce state-of-art results.