BrainMAP: Learning Multiple Activation Pathways in Brain Networks

2024-12-23

arXiv.org

AI Summary

Existing graph neural networks (GNNs) struggle to model long-range, dynamic functional connectivity among brain regions, hindering the disentanglement of task-evoked activation pathways. To address this, we propose Graph-Mamba—a novel framework that reformulates brain-region activation pathways derived from fMRI functional connectivity as a sequence learning problem for the first time. Our method integrates graph-structured modeling, state-space sequence modeling, and a sparse-gated mixture-of-experts (MoE) mechanism, featuring a dedicated MoE-based multi-path aggregation module for interpretable, pathway-level functional analysis. Evaluated on multiple neuroimaging benchmarks, Graph-Mamba achieves significant improvements in both classification and regression performance. Moreover, it precisely localizes task-relevant brain regions and generates neuroscientifically meaningful visualizations of dynamic functional pathways. This work establishes a new paradigm for investigating cognitive neural mechanisms through interpretable, sequence-aware graph modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• 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

Abstract

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn Multiple Activation Pathways in Brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks. Our code is provided at https://github.com/LzyFischer/Graph-Mamba.

Problem

• Graph Neural Networks
• Complex Brain Connectivity
• Long-range Interactions

Innovation

• BrainMAP
• Graph Neural Networks
• Long-range Pathways