MAMVCL: Multi-Atlas Guided Multi-View Contrast Learning for Autism Spectrum Disorder Classification
Year: 2025
Type: article
Abstract: BACKGROUND: Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by significant neurological plasticity in early childhood, where timely interventions like behavioral therapy, language training, and social skills development can mitigate symptoms. Contributions: We introduce a novel Multi-Atlas Guided Multi-View Contrast Learning (MAMVCL) framework for ASD classification, leveraging functional connectivity (FC) matrices from multiple brain atlases to enhance diagnostic accuracy. METHODOLOGY: The MAMVCL framework integrates imaging and phenotypic data through a population graph, where node features derive from imaging data, edge indices are based on similarity scoring matrices, and edge weights reflect phenotypic similarities. Graph convolution extracts global field-of-view features. Concurrently, a Target-aware attention aggregator processes FC matrices to capture high-order brain region dependencies, yielding local field-of-view features. To ensure consistency in subject characteristics, we employ a graph contrastive learning strategy that aligns global and local feature representations. RESULTS: Experimental results on the ABIDE-I dataset demonstrate that our model achieves an accuracy of 85.71%, outperforming most existing methods and confirming its effectiveness. IMPLICATIONS: The proposed model demonstrates superior performance in ASD classification, highlighting the potential of multi-atlas and multi-view learning for improving diagnostic precision and supporting early intervention strategies.
Source: Brain Sciences
Authors: Zuohao Yin, Feng Xu, Yue Ma, Shuo Huang, Kai Ren, Li Zhang
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,654
Awards: G804593266, G8350709466
OpenAlex ID: W4414947796