Functional MRI (fMRI) is crucial for studying brain function and diagnosing neurological disorders. However, existing analysis methods suffer from reproducibility and transferability challenges due to complex preprocessing pipelines and task-specific model designs. In this work, we introduce NeuroSTORM (Neuroimaging Foundation Model with Spatial-Temporal Optimized Representation Modeling) that learns generalizable representations directly from 4D fMRI volumes and enables efficient transfer to diverse downstream applications. Specifically, NeuroSTORM is pre-trained on 28.65 million fMRI frames from over 50,000 subjects, spanning multiple centers and ages 5 to 100. It combines an efficient spatiotemporal modeling design and lightweight task adaptation to enable scalable pre-training and fast transfer to downstream applications. Here we show that NeuroSTORM consistently outperforms existing methods across five downstream tasks, including demographic prediction, phenotype prediction, disease diagnosis, re-identification, and state classification. On two multi-hospital clinical cohorts with 17 diagnoses, NeuroSTORM achieves the best diagnosis performance while remaining predictive of psychological and cognitive phenotypes. These results suggest that NeuroSTORM could become a standardized foundation model for reproducible and transferable fMRI analysis.
@article{arxiv.2506.11167,
title = {Towards a general-purpose foundation model for fMRI analysis},
author = {Cheng Wang and Yu Jiang and Zhihao Peng and Chenxin Li and Changbae Bang and Lin Zhao and Wanyi Fu and Jinglei Lv and Jorge Sepulcre and Carl Yang and Lifang He and Tianming Liu and Xue-Jun Kong and Quanzheng Li and Daniel S. Barron and Anqi Qiu and Randy Hirschtick and Byung-Hoon Kim and Hongbin Han and Xiang Li and Yixuan Yuan},
journal= {arXiv preprint arXiv:2506.11167},
year = {2026}
}