Combining graph neural networks and ROI-based convolutional neural networks to infer individualized graphs for Alzheimer's prediction

Kevin Mueller; Anke Meyer-Baese; Gordon Erlebacher

doi:10.1117/12.2654445

10 April 2023 Combining graph neural networks and ROI-based convolutional neural networks to infer individualized graphs for Alzheimer's prediction

Kevin Mueller, Anke Meyer-Baese, Gordon Erlebacher

Author Affiliations +

Proceedings Volume 12468, Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging; 1246806 (2023) https://doi.org/10.1117/12.2654445
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Abstract

A variety of deep learning approaches have been proposed to automatically classify Alzheimer’s disease (AD) from medical images. However, common approaches such as traditional convolutional neural networks (CNNs), lack interpretability and are prone to overfitting when trained on small datasets. As an alternative, significantly less work has explored applying deep learning approaches to region-based features that are commonly attained from atlas partitions of known regions of interest (ROI). In this work, we combine CNNs with graph neural networks (GNNs) to jointly learn an adjacency matrix of connectivity’s between ROIs as a prior for learning meaningful features for AD prediction. We apply our method to the ADNI dataset and systematically inspect the different intermediate layers of our network using t-SNE projections that show strong separation on out-of-sample data. Finally, we show that the edge probabilities alone are sufficient to reach high classification accuracy by training a secondary random forest classifier on the adjacency matrices outputted from our network and illustrate the interpretability properties of the graphs by visualizing the feature importance for all edges.

Conference Presentation

Citation Download Citation

Kevin Mueller, Anke Meyer-Baese, and Gordon Erlebacher "Combining graph neural networks and ROI-based convolutional neural networks to infer individualized graphs for Alzheimer's prediction", Proc. SPIE 12468, Medical Imaging 2023: Biomedical Applications in Molecular, Structural, and Functional Imaging, 1246806 (10 April 2023); https://doi.org/10.1117/12.2654445

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available