Hierarchical Multiscale Structure-Function Coupling for Brain Connectome Integration

2026-03-21

AI Summary

This work proposes a hierarchical multiscale structure–function coupling framework to address the challenge of effectively integrating the nonlinear, hierarchically nested relationships between brain structural and functional connectivity. By jointly learning individualized modular organization and cross-modal hierarchical coupling through prototype module pooling, an attention-based hierarchical coupling module, and a coupling-guided clustering loss, the framework achieves interpretable and biologically meaningful multiscale integration. Key technical components include prototype selection, differentiable modularity optimization, attention mechanisms, and coupling-signal regularization. Evaluated across four independent cohorts, the method significantly outperforms existing baselines, achieving state-of-the-art performance in brain age prediction, cognitive score estimation, and disease classification tasks.

Technology Category

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

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Integrating structural and functional connectomes remains challenging because their relationship is non-linear and organized over nested modular hierarchies. We propose a hierarchical multiscale structure-function coupling framework for connectome integration that jointly learns individualized modular organization and hierarchical coupling across structural connectivity (SC) and functional connectivity (FC). The framework includes: (i) Prototype-based Modular Pooling (PMPool), which learns modality-specific multiscale communities by selecting prototypical ROIs and optimizing a differentiable modularity-inspired objective; (ii) an Attention-based Hierarchical Coupling Module (AHCM) that models both within-hierarchy and cross-hierarchy SC-FC interactions to produce enriched hierarchical coupling representations; and (iii) a Coupling-guided Clustering loss (CgC-Loss) that regularizes SC and FC community assignments with coupling signals, allowing cross-modal interactions to shape community alignment across hierarchies. We evaluate the model's performance across four cohorts for predicting brain age, cognitive score, and disease classification. Our model consistently outperforms baselines and other state-of-the-art approaches across three tasks. Ablation and sensitivity analyses verify the contributions of key components. Finally, the visualizations of learned coupling reveal interpretable differences, suggesting that the framework captures biologically meaningful structure-function relationships.

Problem

• structure-function coupling
• brain connectome integration
• multiscale hierarchy
• modular organization
• non-linear relationship

Innovation

• hierarchical multiscale coupling
• structure-function integration
• prototype-based modular pooling
• attention-based hierarchical module
• coupling-guided clustering