Multimodal hypergraph model improves brain connectivity mapping and speed
Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow Matching
Machine Learning
Summary
Studying brain connections helps us understand how different parts of the brain work together. Structural and functional brain connectivity show different kinds of connections but are hard to get paired data for. The authors propose a new model that uses hypergraphs to capture complex relationships and generate both types of brain connections together, improving accuracy and speed. Their method works better and faster than previous models when tested on brain scan data from young adults.
What this means in practice
- •For neuroimaging data teams: Generate paired structural and functional brain connectivity data to enhance studies of brain disorders where paired data are scarce.
- •For medical imaging software developers: Incorporate faster and more accurate brain connectivity synthesis methods to improve tools for brain network analysis and brain disease diagnosis support.
Tested on one dataset.
Authors
Chyong Yi Poh, Hwa Hui Tew, Junn Yong Loo, Raphaël C. -W. Phan, Fuad Noman, Pew-Thian Yap, Chee-Ming Ting
Abstract
Structural connectivity (SC) and functional connectivity (FC) provide complementary information on interactions between brain regions and are widely used in neuroimaging studies of neuropsychiatric disorders. Generative modelling can alleviate the scarcity of large-scale paired SC-FC data, but existing approaches typically use pairwise graphs that capture only dyadic interactions and often generate SC and FC independently, limiting preservation of higher-order structure-function relationships. We propose a Multimodal Hypergraph Flow Matching (MHG-FM) framework for joint SC-FC connectivity generation and cross-modal translation. MHG-FM constructs modality-specific hypergraphs, learns higher-order representations with Hypergraph Neural Network (HGNN) encoders, and performs bidirectional cross-modal fusion using Dual Cross-Attention (DCA). A variational autoencoder maps the fused representations to a compact latent space, where conditional flow matching enables connectivity synthesis and multimodal translation via latent transport. Experiments on the Human Connectome Project Young Adult (HCP-YA) dataset show that MHG-FM outperforms several state-of-the-art baselines in reconstruction quality, topology preservation, distributional similarity, and SC-FC coupling, while achieving approximately 8x faster sampling than a matched diffusion backbone.