BrainCSD: A Hierarchical Consistency-Driven MoE Foundation Model for Unified Connectome Synthesis and Multitask Brain Trait Prediction

TL;DR

BrainCSD is a hierarchical MoE foundation model that synthesizes brain connectivity biomarkers and supports multitask brain trait prediction, addressing challenges of missing modalities and cross-scale consistency in neuroimaging analysis.

Contribution

It introduces a novel hierarchical MoE framework with neuroanatomically grounded components for unified connectome synthesis and multitask prediction, improving over existing models.

Findings

Achieves 95.6% accuracy in MCI vs. CN classification without FC.

Low synthesis errors for FC and SC biomarkers.

Accurate brain age and MMSE score predictions.

Abstract

Functional and structural connectivity (FC/SC) are key multimodal biomarkers for brain analysis, yet their clinical utility is hindered by costly acquisition, complex preprocessing, and frequent missing modalities. Existing foundation models either process single modalities or lack explicit mechanisms for cross-modal and cross-scale consistency. We propose BrainCSD, a hierarchical mixture-of-experts (MoE) foundation model that jointly synthesizes FC/SC biomarkers and supports downstream decoding tasks (diagnosis and prediction). BrainCSD features three neuroanatomically grounded components: (1) a ROI-specific MoE that aligns regional activations from canonical networks (e.g., DMN, FPN) with a global atlas via contrastive consistency; (2) a Encoding-Activation MOE that models dynamic cross-time/gradient dependencies in fMRI/dMRI; and (3) a network-aware refinement MoE that enforces structural priors and symmetry at individual and population levels. Evaluated on the datasets under complete and missing-modality settings, BrainCSD achieves SOTA results: 95.6\% accuracy for MCI vs. CN classification without FC, low synthesis error (FC RMSE: 0.038; SC RMSE: 0.006), brain age prediction (MAE: 4.04 years), and MMSE score estimation (MAE: 1.72 points). Code is available in \href{https://github.com/SXR3015/BrainCSD}{BrainCSD}