Neurobridge: Bridging functional and structural brain networks via neural coupling and consistency-Guided dynamic...

Area of Science:

• Neuroscience
• Medical Imaging
• Computational Biology

Background:

• Functional brain networks map connectivity in resting or task states.
• Structural brain networks reveal macro-scale pathway integrity.
• Integrating these modalities presents challenges due to differing data structures and resolutions.

Purpose of the Study:

• To develop a method for effective fusion of functional and structural brain network data.
• To extract discriminative joint representations for enhanced brain network analysis.
• To improve prediction accuracy in tasks like disease classification.

Main Methods:

• Proposed NeuroBridge framework for multimodal brain network analysis.
• Introduced Neural Synergy Coupling Module (NeuSCM) for structural-functional coupling.
• Developed Consistency Anchor Guidance Module (CAGM) for semantic coherence.
• Utilized Dynamic Association Parsing Module (DAP) for relationship capture and prediction.

Main Results:

• NeuroBridge achieved superior prediction accuracy compared to state-of-the-art single and multimodal methods.
• Demonstrated effectiveness in disease prediction and gender classification tasks.
• Provided new insights into multimodal brain network analysis.

Conclusions:

• NeuroBridge effectively fuses multimodal brain network data.
• The proposed method enhances the analysis of brain networks for clinical applications.
• This approach offers a promising direction for future research in brain network analysis.