Hierarchical Characterization of Brain Dynamics via State Space-based Vector Quantization

TL;DR

This paper introduces a hierarchical vector quantization approach for modeling brain dynamics from fMRI data, capturing metastable states and transitions to improve understanding and diagnosis of brain function.

Contribution

The paper presents a novel hierarchical state space-based tokenization network (HST) with a refined VQ-VAE for better quantization and metastability modeling in brain dynamics.

Findings

Effective quantification of hierarchical brain dynamics demonstrated on public fMRI datasets.

Improved reconstruction and predictive performance over existing methods.

Potential applications in disease diagnosis and brain state analysis.

Abstract

Understanding brain dynamics through functional Magnetic Resonance Imaging (fMRI) remains a fundamental challenge in neuroscience, particularly in capturing how the brain transitions between various functional states. Recently, metastability, which refers to temporarily stable brain states, has offered a promising paradigm to quantify complex brain signals into interpretable, discretized representations. In particular, compared to cluster-based machine learning approaches, tokenization approaches leveraging vector quantization have shown promise in representation learning with powerful reconstruction and predictive capabilities. However, most existing methods ignore brain transition dependencies and lack a quantification of brain dynamics into representative and stable embeddings. In this study, we propose a Hierarchical State space-based Tokenization network, termed HST, which quantizes brain states and transitions in a hierarchical structure based on a state space-based model. We introduce a refined clustered Vector-Quantization Variational AutoEncoder (VQ-VAE) that incorporates quantization error feedback and clustering to improve quantization performance while facilitating metastability with representative and stable token representations. We validate our HST on two public fMRI datasets, demonstrating its effectiveness in quantifying the hierarchical dynamics of the brain and its potential in disease diagnosis and reconstruction performance. Our method offers a promising framework for the characterization of brain dynamics, facilitating the analysis of metastability.