Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks

TL;DR

This paper introduces a graph neural network framework using functional brain parcellation for explainable ASD classification from rs-fMRI, achieving state-of-the-art accuracy and identifying key brain regions linked to ASD.

Contribution

It compares anatomical and functional parcellation strategies within a GNN framework, demonstrating the superiority of functional parcellation and providing explainability insights.

Findings

Functional parcellation significantly improves classification accuracy.

Graph Attention Networks outperform baseline GCNs on ABIDE I.

Model explanations highlight key brain regions associated with ASD.

Abstract

Anatomical brain parcellations dominate rs-fMRI-based Autism Spectrum Disorder (ASD) classification, yet their rigid boundaries may fail to capture the idiosyncratic connectivity patterns that characterise ASD. We present a graph-based deep learning framework comparing anatomical (AAL, 116 ROIs) and functionally-derived (MSDL, 39 ROIs) parcellation strategies on the ABIDE I dataset. Our FSL preprocessing pipeline handles multi-site heterogeneity across 400 balanced subjects, with site-stratified 70/15/15 splits to prevent data leakage. Gaussian noise augmentation within training folds expands samples from 280 to 1,680. A three phase pipeline progresses from a baseline GCN with AAL (73.3% accuracy, AUC=0.74), to an optimised GCN with MSDL (84.0%, AUC=0.84), to a Graph Attention Network ensemble achieving 95.0% accuracy (AUC=0.98), outperforming all recent GNN-based benchmarks on ABIDE I. The 10.7-point gain from atlas substitution alone demonstrates that functional parcellation is the most impactful modelling decision. Gradient-based saliency and GNNExplainer analyses converge on the Posterior Cingulate Cortex and Precuneus as core Default Mode Network hubs, validating that model decisions reflect ASD neuropathology rather than acquisition artefacts. All code and datasets will be publicly released upon acceptance.