Physics-Guided Multi-view Graph Neural Network for Schizophrenia Classification via Structural-Functional Coupling

2025-05-21

PRIME@MICCAI

AI Summary

Existing schizophrenia (SZ) classification methods often model structural connectivity (SC) and functional connectivity (FC) independently, neglecting their biophysically grounded dynamical coupling and underlying neurophysiological mechanisms. Method: We propose a physics-informed SC–FC coupling framework that explicitly models SC-driven FC dynamics via neural oscillation differential equations. A multi-view graph neural network integrates dual-channel graph convolutions over SC- and FC-derived graphs, while a coupling-aware joint loss function enables simultaneous learning of SC–FC coupling, cross-modal feature fusion, and disease discrimination. Contribution/Results: Evaluated on real clinical datasets, our method achieves significant improvements in SZ classification accuracy and model generalizability. Results demonstrate the efficacy and robustness of incorporating biophysical priors into multimodal coupling modeling for biomarker discovery in neuropsychiatric disorders.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Social Networks and Social Media: Computational social science

Abstract

Clinical studies reveal disruptions in brain structural connectivity (SC) and functional connectivity (FC) in neuropsychiatric disorders such as schizophrenia (SZ). Traditional approaches might rely solely on SC due to limited functional data availability, hindering comprehension of cognitive and behavioral impairments in individuals with SZ by neglecting the intricate SC-FC interrelationship. To tackle the challenge, we propose a novel physics-guided deep learning framework that leverages a neural oscillation model to describe the dynamics of a collection of interconnected neural oscillators, which operate via nerve fibers dispersed across the brain's structure. Our proposed framework utilizes SC to simultaneously generate FC by learning SC-FC coupling from a system dynamics perspective. Additionally, it employs a novel multi-view graph neural network (GNN) with a joint loss to perform correlation-based SC-FC fusion and classification of individuals with SZ. Experiments conducted on a clinical dataset exhibited improved performance, demonstrating the robustness of our proposed approach.

Problem

• Classify schizophrenia using structural-functional brain connectivity coupling
• Overcome limitations of traditional SC-only approaches with SC-FC fusion
• Improve SZ diagnosis via physics-guided multi-view GNN framework

Innovation

• Physics-guided neural oscillation model for SC-FC coupling
• Multi-view GNN with joint loss for SC-FC fusion
• Simultaneous FC generation from SC via dynamics learning