Dual-Stream Neural Architecture for Integrative Analysis of Large Multimodal Model in Mood Disorder Classification

Mood disorders, particularly Bipolar Disorder (BD), present significant challenges in accurate diagnosis due to their complex neurobiological underpinnings. While recent advancements in neuroimaging techniques have provided valuable insights, the integration of multimodal data remains a critical challenge. This paper introduces a novel dual-stream neural architecture that leverages both structural and functional MRI data for mood disorder classification. Our large multimodal model uniquely combines advanced mathematical frameworks with domain adaptation techniques to address the inherent heterogeneity in neuroimaging data across different populations. We propose a theoretical foundation rooted in information geometry and optimal transport theory to formalize the domain adaptation problem in the context of neuroimaging analysis. Our method demonstrates superior performance in cross-domain mood disorder classification. Furthermore, we provide rigorous theoretical guarantees on the convergence and generalization capabilities of our model, establishing a new benchmark for robust and interpretable multimodal neuroimaging analysis in psychiatric diagnostics.