Hierarchical Spatio-Temporal State-Space Modeling for fMRI Analysis

2024-08-23

arXiv.org

AI Summary

To address the challenge of modeling dynamic functional network connectivity (dFNC) from fMRI data for neurobiomarker discovery, this paper introduces the first Mamba architecture adaptation tailored specifically for symmetric FNC matrices. Our method comprises three key innovations: (1) a hierarchical spatiotemporal state-space model that jointly encodes both brain-region topology and temporal dynamics; (2) a component-wise variable-scale aggregation (CVA) module to enhance graph-structure awareness; and (3) symmetric rotary position encoding (SymRope), explicitly respecting the symmetry constraint inherent in FNC matrices. Evaluated on multi-disorder classification and cognitive score regression tasks, our approach significantly outperforms state-of-the-art methods. Interpretability analysis precisely identifies discriminative functional connections and dynamic patterns underlying disease and cognition. The implementation is publicly available.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent advances in deep learning structured state space models, especially the Mamba architecture, have demonstrated remarkable performance improvements while maintaining linear complexity. In this study, we introduce functional spatiotemporal Mamba (FST-Mamba), a Mamba-based model designed for discovering neurological biomarkers using functional magnetic resonance imaging (fMRI). We focus on dynamic functional network connectivity (dFNC) derived from fMRI and propose a hierarchical spatiotemporal Mamba-based network that processes spatial and temporal information separately using Mamba-based encoders. Leveraging the topological uniqueness of the FNC matrix, we introduce a component-wise varied-scale aggregation (CVA) mechanism to aggregate connectivity across individual components within brain networks, enabling the model to capture component-level and network-level information. Additionally, we propose symmetric rotary position encoding (SymRope) to encode the relative positions of each functional connection while considering the symmetric nature of the FNC matrix. Experimental results demonstrate significant improvements in the proposed FST-Mamba model on various brain-based classification and regression tasks. We further show brain connectivities and dynamics that are crucial for the prediction. Our work reveals the substantial potential of attention-free sequence modeling in brain discovery. The codes are publicly available here: url{https://github.com/yuxiangwei0808/FunctionalMamba/tree/main}.

Problem

• fMRI data analysis
• disease-related clues
• dynamic Functional Network Connectivity (dFNC)

Innovation

• FST-Mamba
• CVA method
• SymRope encoding