Edge-boosted graph learning for functional brain connectivity analysis

2025-04-21

AI Summary

Traditional node-level functional connectivity modeling fails to capture complex brain functional interactions, limiting early diagnosis of Alzheimer’s disease (AD) and Parkinson’s disease (PD). Method: We propose an edge-centric functional brain network paradigm—edge-based Functional Connectivity (eFC)—introducing the first graph learning framework that jointly models edge relationships and edge–edge collaborative embeddings. Our approach integrates edge-level similarity measures derived from fMRI time-series signals, edge-aware graph neural networks, and an end-to-end classification architecture. Contribution/Results: Evaluated on the ADNI and PPMI datasets, eFC achieves significantly higher accuracy than state-of-the-art GNN-based baselines in AD/PD binary classification. Results demonstrate superior sensitivity and discriminative power for neurodegenerative disorders, establishing eFC as a novel granularity and paradigm for functional brain network modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• 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
• Economics, Online Markets and Human Computation: Social networks and social learning
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Predicting disease states from functional brain connectivity is critical for the early diagnosis of severe neurodegenerative diseases such as Alzheimer's Disease and Parkinson's Disease. Existing studies commonly employ Graph Neural Networks (GNNs) to infer clinical diagnoses from node-based brain connectivity matrices generated through node-to-node similarities of regionally averaged fMRI signals. However, recent neuroscience studies found that such node-based connectivity does not accurately capture ``functional connections"within the brain. This paper proposes a novel approach to brain network analysis that emphasizes edge functional connectivity (eFC), shifting the focus to inter-edge relationships. Additionally, we introduce a co-embedding technique to integrate edge functional connections effectively. Experimental results on the ADNI and PPMI datasets demonstrate that our method significantly outperforms state-of-the-art GNN methods in classifying functional brain networks.

Problem

• Improving brain disease diagnosis via edge-focused connectivity analysis
• Addressing inaccuracies in node-based functional brain connectivity models
• Enhancing GNN performance with edge co-embedding techniques

Innovation

• Emphasizes edge functional connectivity (eFC)
• Introduces co-embedding for edge connections
• Outperforms GNNs in brain network classification