A Comparative Study of Population-Graph Construction Methods and Graph Neural Networks for Brain Age Regression

TL;DR

This study evaluates how different methods of constructing population graphs affect the performance of various Graph Neural Networks in brain age estimation, emphasizing the importance of meaningful graph structures.

Contribution

It systematically compares multiple population-graph construction methods and analyzes their impact on GNN performance in brain age regression tasks.

Findings

GCN and GAT perform poorly on low homophily graphs.

GraphSage and Chebyshev are more robust across homophily levels.

Static graph construction may be insufficient for accurate brain age estimation.

Abstract

The difference between the chronological and biological brain age of a subject can be an important biomarker for neurodegenerative diseases, thus brain age estimation can be crucial in clinical settings. One way to incorporate multimodal information into this estimation is through population graphs, which combine various types of imaging data and capture the associations among individuals within a population. In medical imaging, population graphs have demonstrated promising results, mostly for classification tasks. In most cases, the graph structure is pre-defined and remains static during training. However, extracting population graphs is a non-trivial task and can significantly impact the performance of Graph Neural Networks (GNNs), which are sensitive to the graph structure. In this work, we highlight the importance of a meaningful graph construction and experiment with different population-graph construction methods and their effect on GNN performance on brain age estimation. We use the homophily metric and graph visualizations to gain valuable quantitative and qualitative insights on the extracted graph structures. For the experimental evaluation, we leverage the UK Biobank dataset, which offers many imaging and non-imaging phenotypes. Our results indicate that architectures highly sensitive to the graph structure, such as Graph Convolutional Network (GCN) and Graph Attention Network (GAT), struggle with low homophily graphs, while other architectures, such as GraphSage and Chebyshev, are more robust across different homophily ratios. We conclude that static graph construction approaches are potentially insufficient for the task of brain age estimation and make recommendations for alternative research directions.