A Brain-to-Population Graph Learning Framework for Diagnosing Brain Disorders
This work provides a more reliable and personalized approach for diagnosing brain disorders, advancing clinical applicability, though it appears incremental as it builds on existing graph-based methods.
The paper tackles the problem of diagnosing brain disorders using functional connectivity graphs by addressing limitations like reliance on predefined atlases and confounding effects from site and phenotype variability, resulting in a framework that outperforms state-of-the-art methods in prediction accuracy on datasets such as ABIDE I, ADHD-200, and Rest-meta-MDD.
Recent developed graph-based methods for diagnosing brain disorders using functional connectivity highly rely on predefined brain atlases, but overlook the rich information embedded within atlases and the confounding effects of site and phenotype variability. To address these challenges, we propose a two-stage Brain-to-Population Graph Learning (B2P-GL) framework that integrates the semantic similarity of brain regions and condition-based population graph modeling. In the first stage, termed brain representation learning, we leverage brain atlas knowledge from GPT-4 to enrich the graph representation and refine the brain graph through an adaptive node reassignment graph attention network. In the second stage, termed population disorder diagnosis, phenotypic data is incorporated into population graph construction and feature fusion to mitigate confounding effects and enhance diagnosis performance. Experiments on the ABIDE I, ADHD-200, and Rest-meta-MDD datasets show that B2P-GL outperforms state-of-the-art methods in prediction accuracy while enhancing interpretability. Overall, our proposed framework offers a reliable and personalized approach to brain disorder diagnosis, advancing clinical applicability.