Fast brain model predicts complex resting brain activity signals
FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model
Machine Learning
Summary
Understanding how the brain works when it is at rest is difficult because brain signals are complex in both space and time. The authors propose FAST-Brain, which combines a method that predicts clean brain signals, a network that captures spatial brain structure, and a Transformer to handle long-term timing. Their approach is mathematically justified to focus on a simpler underlying brain signal rather than all noisy details. Tests on simulated data and real human brain data show that FAST-Brain can better recover key brain connectivity patterns and signal structures than previous methods.
What this means in practice
- •For neuroimaging data analysts: Model resting brain activity with improved accuracy by using FAST-Brain to infer connectivity and low-dimensional brain states from fMRI data.
- •For medical device developers: Design brain monitoring tools that better predict spatial and temporal dynamics of brain signals during rest using FAST-Brain’s unified spatio-temporal approach.
Authors
Shucheng Liu, Changchun Shi, Kai Zhang, Hongtu Zhu
Abstract
Modeling resting-state functional magnetic resonance imaging (rs-fMRI) data is crucial for understanding brain-wide neural activity. However, traditional methods struggle to capture complex temporal dynamics over long horizons, to account for the brain's anatomical spatial structure, and to model high-dimensional ambient signals that lie on a low-dimensional intrinsic subspace. We propose FAST-Brain, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges. At its core is a flow-aligned generative framework that directly predicts the clean blood-oxygen-level-dependent (BOLD) signal, paired with a graph convolutional network that captures spatial structural constraints and a Transformer that models long-range temporal dependencies. Theoretically, we show that under a low-dimensional subspace assumption, the approximation error of our model scales with the intrinsic dimension rather than the ambient dimension, which justifies our direct modeling of the BOLD signal. Extensive experiments on synthetic and Human Connectome Project datasets demonstrate that FAST-Brain achieves state-of-the-art performance in recovering functional connectivity, effective connectivity, and the implicit low-dimensional signal subspace.