BrainCast: A Spatio-Temporal Forecasting Model for Whole-Brain fMRI Time Series Prediction

2026-03-09

AI Summary

This study addresses the challenge of low data quality and insufficient statistical power in clinical fMRI due to short scan durations, which hampers neuroimaging research. To overcome this limitation, the authors propose the first spatiotemporal prediction framework tailored for whole-brain fMRI, formulating time series extension as a multivariate time-series forecasting task that jointly captures both intra-regional dynamics and inter-regional interactions. The method introduces three key innovations: token-based spatial interaction modeling, temporal feature refinement through high- and low-frequency enhancement, and multi-scale spatiotemporal representation fusion. Evaluated on the Human Connectome Project dataset, the proposed approach outperforms existing prediction models, and the synthesized extended data significantly improve performance in downstream cognitive trait prediction tasks.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Functional magnetic resonance imaging (fMRI) enables noninvasive investigation of brain function, while short clinical scan durations, arising from human and non-human factors, usually lead to reduced data quality and limited statistical power for neuroimaging research. In this paper, we propose BrainCast, a novel spatio-temporal forecasting framework specifically tailored for whole-brain fMRI time series forecasting, to extend informative fMRI time series without additional data acquisition. It formulates fMRI time series forecasting as a multivariate time series prediction task and jointly models temporal dynamics within regions of interest (ROIs) and spatial interactions across ROIs. Specifically, BrainCast integrates a Spatial Interaction Awareness module to characterize inter-ROI dependencies via embedding every ROI time series as a token, a Temporal Feature Refinement module to capture intrinsic neural dynamics within each ROI by enhancing both low- and high-energy temporal components of fMRI time series at the ROI level, and a Spatio-temporal Pattern Alignment module to combine spatial and temporal representations for producing informative whole-brain features. Experimental results on resting-state and task fMRI datasets from the Human Connectome Project demonstrate the superiority of BrainCast over state-of-the-art time series forecasting baselines. Moreover, fMRI time series extended by BrainCast improve downstream cognitive ability prediction, highlighting the clinical and neuroscientific impact brought by whole-brain fMRI time series forecasting in scenarios with restricted scan durations.

Problem

• fMRI
• time series forecasting
• short scan duration
• data quality
• statistical power

Innovation

• spatio-temporal forecasting
• fMRI time series
• whole-brain modeling
• neural dynamics
• ROI interaction