Towards a general-purpose foundation model for functional MRI analysis.
Authors
Affiliations (21)
Affiliations (21)
- Electronic Engineering Department, The Chinese University of Hong Kong, Hong Kong, China.
- Department of Psychiatry, Yonsei University College of Medicine, Seoul, Republic of Korea.
- Institute of Behavioral Sciences in Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea.
- Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, Republic of Korea.
- School of Computing, University of Georgia, Athens, GA, USA.
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China.
- Sydney Medical School & School of Biomedical Engineering, University of Sydney, Sydney, New South Wales, Australia.
- Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
- Department of Computer Science, Emory University, Atlanta, GA, USA.
- Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA.
- Boston Children's Hospital, Boston, MA, USA.
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA.
- Department of Psychiatry, Brigham and Women's Hospital, Boston, MA, USA.
- Mental Health Research Center, Department of Health Technology and Informatics, Hong Kong Polytechnic University, Hong Kong, China.
- Department of Psychiatry, Massachusetts General Hospital, Boston, MA, USA.
- Yonsei Institute for Digital Health, Yonsei University, Seoul, Republic of Korea.
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China. [email protected].
- Department of Radiology, Peking University Third Hospital, Beijing, China. [email protected].
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA. [email protected].
- Kempner Institute for Natural and Artificial Intelligence, Harvard University, Cambridge, MA, USA. [email protected].
- Electronic Engineering Department, The Chinese University of Hong Kong, Hong Kong, China. [email protected].
Abstract
Functional magnetic resonance imaging (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. Here we introduce the Neuroimaging Foundation Model with Spatial-Temporal Optimized and Representation Modelling (NeuroSTORM), which learns generalizable representations directly from four-dimensional fMRI volumes and enables efficient transfer to diverse downstream applications. Specifically, NeuroSTORM is pretrained on 28.65 million fMRI frames from over 50,000 participants, spanning multiple centres and ages 5-100. It combines an efficient spatiotemporal modelling design and lightweight task adaptation to enable scalable pretraining and fast transfer to downstream applications. 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 multihospital 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.