3D Grid-Attention Networks for Interpretable Age and Alzheimer's Disease Prediction from Structural MRI

TL;DR

This paper introduces a 3D Grid-Attention neural network that predicts age and Alzheimer's disease from MRI scans, providing interpretable brain region importance for clinical diagnosis.

Contribution

It presents a novel 3D attention-based deep learning model that enhances interpretability and accuracy in age and Alzheimer's disease prediction from MRI data.

Findings

The model accurately predicts age and AD with interpretable salience maps.

It outperforms existing methods in distinguishing AD and healthy controls.

Salience maps reveal meaningful brain regions related to the predictions.

Abstract

We propose an interpretable 3D Grid-Attention deep neural network that can accurately predict a person's age and whether they have Alzheimer's disease (AD) from a structural brain MRI scan. Building on a 3D convolutional neural network, we added two attention modules at different layers of abstraction, so that features learned are spatially related to the global features for the task. The attention layers allow the network to focus on brain regions relevant to the task, while masking out irrelevant or noisy regions. In evaluations based on 4,561 3-Tesla T1-weighted MRI scans from 4 phases of the Alzheimer's Disease Neuroimaging Initiative (ADNI), salience maps for age and AD prediction partially overlapped, but lower-level features overlapped more than higher-level features. The brain age prediction network also distinguished AD and healthy control groups better than another state-of-the-art method. The resulting visual analyses can distinguish interpretable feature patterns that are important for predicting clinical diagnosis. Future work is needed to test performance across scanners and populations.