Large-scale multi-sequence pretraining for generalizable MRI analysis in versatile clinical applications.
Authors
Affiliations (14)
Affiliations (14)
- Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China.
- Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics, Guangdong Province), Guangzhou, China.
- Department of Radiology, 5th Medical Center of Chinese PLA General Hospital, Beijing, China.
- The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China.
- Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
- Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China.
- Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China.
- Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China. [email protected].
- Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics, Guangdong Province), Guangzhou, China. [email protected].
- Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China. [email protected].
- Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong, China. [email protected].
- Division of Life Science, The Hong Kong University of Science and Technology, Hong Kong, China. [email protected].
- HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, China. [email protected].
- State Key Laboratory of Nervous System Disorders, The Hong Kong University of Science and Technology, Hong Kong, China. [email protected].
Abstract
Multi-sequence magnetic resonance imaging (MRI) is essential for clinical diagnosis because it enables comprehensive characterization of complex anatomy. However, its substantial heterogeneity limits the generalizability of deep learning models and hinders clinical translation. Here we present MARS, a large-scale MRI foundation model with a novel pretraining strategy that disentangles anatomy-invariant features from sequence-specific variations to learn robust and generalizable representations for diverse clinical applications. We collected 64 datasets spanning 10 anatomical structures and multiple MRI sequences. Among these, 336,476 volumetric scans from 34 datasets (8 public and 26 private) were curated to build a large multi-organ, multi-sequence MRI pretraining corpus. We further established a benchmark of 44 downstream tasks covering diagnosis, segmentation, registration, progression prediction and report generation. MARS ranked first in 41 of 44 benchmarks, with statistically significant improvements. Its strong performance on heterogeneous and external datasets underscores MARS as a scalable foundation for versatile real-world multi-sequence MRI analysis.