Brain Foundation Models with Hypergraph Dynamic Adapter for Brain Disease Analysis
This work addresses the problem of inefficient and limited generalization in brain disease analysis for clinical applications, representing a new paradigm rather than an incremental improvement.
The authors tackled the limitations of current brain foundation models by proposing SAM-Brain3D, a model trained on over 66,000 brain images across 14 MRI sub-modalities, and the Hypergraph Dynamic Adapter (HyDA) for efficient adaptation, achieving consistent outperformance over state-of-the-art methods in brain disease segmentation and classification tasks.
Brain diseases, such as Alzheimer's disease and brain tumors, present profound challenges due to their complexity and societal impact. Recent advancements in brain foundation models have shown significant promise in addressing a range of brain-related tasks. However, current brain foundation models are limited by task and data homogeneity, restricted generalization beyond segmentation or classification, and inefficient adaptation to diverse clinical tasks. In this work, we propose SAM-Brain3D, a brain-specific foundation model trained on over 66,000 brain image-label pairs across 14 MRI sub-modalities, and Hypergraph Dynamic Adapter (HyDA), a lightweight adapter for efficient and effective downstream adaptation. SAM-Brain3D captures detailed brain-specific anatomical and modality priors for segmenting diverse brain targets and broader downstream tasks. HyDA leverages hypergraphs to fuse complementary multi-modal data and dynamically generate patient-specific convolutional kernels for multi-scale feature fusion and personalized patient-wise adaptation. Together, our framework excels across a broad spectrum of brain disease segmentation and classification tasks. Extensive experiments demonstrate that our method consistently outperforms existing state-of-the-art approaches, offering a new paradigm for brain disease analysis through multi-modal, multi-scale, and dynamic foundation modeling.