Contrasformer: A Brain Network Contrastive Transformer for Neurodegenerative Condition Identification
Open Access
- 21 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2671-2681
Abstract
Understanding neurological disorder is a fundamental problem in neuroscience, which often requires the analysis of brain networks derived from functional magnetic resonance imaging (fMRI) data. Despite the prevalence of Graph Neural Networks (GNNs) and Graph Transformers in various domains, applying them to brain networks faces challenges. Specifically, the datasets are severely impacted by the noises caused by distribution shifts across sub-populations and the neglect of node identities, both obstruct the identification of disease-specific patterns. To tackle these challenges, we propose Contrasformer, a novel contrastive brain network Transformer. It generates a prior-knowledge-enhanced contrast graph to address the distribution shifts across sub-populations by a two-stream attention mechanism. A cross attention with identity embedding highlights the identity of nodes, and three auxiliary losses ensure group consistency. Evaluated on 4 functional brain network datasets over 4 different diseases, Contrasformer outperforms the state-of-the-art methods for brain networks by achieving up to 10.8% improvement in accuracy, which demonstrates its efficacy in neurological disorder identification. Case studies illustrate its interpretability, especially in the context of neuroscience. This paper provides a solution for analyzing brain networks, offering valuable insights into neurological disorders. Our code is available at https://github.com/AngusMonroe/Contrasformer.Keywords
All Related Versions
Funding Information
- National Research Foundation Singapore (MOE-T2EP20220-0006)
- MBIE Catalyst: Strategic Fund NZ-Singapore Data Science Research Programme (UOAX2001)
This publication has 26 references indexed in Scilit:
- A class-aware representation refinement framework for graph classificationInformation Sciences, 2024
- Contrastive Graph Pooling for Explainable Classification of Brain NetworksIEEE Transactions on Medical Imaging, 2024
- MEGACare: Knowledge-guided multi-view hypergraph predictive framework for healthcareInformation Fusion, 2023
- BrainGNN: Interpretable Brain Graph Neural Network for fMRI AnalysisMedical Image Analysis, 2021
- Benchmarking functional connectome-based predictive models for resting-state fMRINeuroImage, 2019
- Neural networks underlying language and social cognition during self-other processing in Autism spectrum disordersNeuropsychologia, 2017
- BrainNetCNN: Convolutional neural networks for brain networks; towards predicting neurodevelopmentNeuroImage, 2017
- Abnormal functional connectivity of default mode sub-networks in autism spectrum disorder patientsNeuroImage, 2010
- A General Statistical Analysis for fMRI DataNeuroImage, 2002
- The Regression Analysis of Binary SequencesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1958