Saved in:
Bibliographic Details
Main Authors: Madani, Syeda Hareem, Bibi, Noureen, Jeraj, Adam Rafiq, Khan, Sumra, Zafar, Anas, Qureshi, Rizwan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.02518
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911481470124032
author Madani, Syeda Hareem
Bibi, Noureen
Jeraj, Adam Rafiq
Khan, Sumra
Zafar, Anas
Qureshi, Rizwan
author_facet Madani, Syeda Hareem
Bibi, Noureen
Jeraj, Adam Rafiq
Khan, Sumra
Zafar, Anas
Qureshi, Rizwan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02518
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks
Madani, Syeda Hareem
Bibi, Noureen
Jeraj, Adam Rafiq
Khan, Sumra
Zafar, Anas
Qureshi, Rizwan
Computer Vision and Pattern Recognition
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.
title Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.02518