BrainMAP: Multimodal Graph Learning For Efficient Brain Disease Localization

2025-06-12

AI Summary

Existing graph learning methods struggle to accurately localize critical brain regions driving neurodegenerative disorders in fully connected brain networks, while multimodal fusion models incur prohibitive computational overhead, hindering deployment on edge devices. To address these challenges, we propose an efficient multimodal graph learning framework: first, atlas-guided subgraph selection—leveraging the AAL parcellation—to focus on pathology-relevant brain regions; second, a cross-node attention mechanism coupled with an adaptive multimodal gating module for dynamic fMRI-DTI integration. Our key innovations include (i) the first atlas-driven lesion subgraph extraction paradigm and (ii) a lightweight, interpretable cross-modal fusion architecture. Experiments demonstrate over 50% reduction in computational cost, state-of-the-art localization accuracy, and significantly enhanced real-time neurodegenerative disease analysis under resource-constrained settings.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent years have seen a surge in research focused on leveraging graph learning techniques to detect neurodegenerative diseases. However, existing graph-based approaches typically lack the ability to localize and extract the specific brain regions driving neurodegenerative pathology within the full connectome. Additionally, recent works on multimodal brain graph models often suffer from high computational complexity, limiting their practical use in resource-constrained devices. In this study, we present BrainMAP, a novel multimodal graph learning framework designed for precise and computationally efficient identification of brain regions affected by neurodegenerative diseases. First, BrainMAP utilizes an atlas-driven filtering approach guided by the AAL atlas to pinpoint and extract critical brain subgraphs. Unlike recent state-of-the-art methods, which model the entire brain network, BrainMAP achieves more than 50% reduction in computational overhead by concentrating on disease-relevant subgraphs. Second, we employ an advanced multimodal fusion process comprising cross-node attention to align functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) data, coupled with an adaptive gating mechanism to blend and integrate these modalities dynamically. Experimental results demonstrate that BrainMAP outperforms state-of-the-art methods in computational efficiency, without compromising predictive accuracy.

Problem

• Localize brain regions affected by neurodegenerative diseases
• Reduce computational complexity in multimodal brain graph models
• Improve efficiency without compromising predictive accuracy

Innovation

• Atlas-driven filtering for critical subgraphs extraction
• Cross-node attention for fMRI and DTI alignment
• Adaptive gating for dynamic multimodal fusion