Health AI Central
Peer-Reviewed Publication
Nat Biomed Eng2026July 13, 2026Journal Article

Large-scale multi-sequence pretraining for generalizable MRI analysis in versatile clinical applications.

Zelin Qiu1, Xi Wang1, Zhuoyao Xie2, Juan Zhou3,4, Yu Wang5, Lingjie Yang5, Xinrui Jiang1, Juyoung Bae1, Moo Hyun Son1, Qiang Ye2, Dexuan Chen2, Rui Zhang2, Tao Li2, Neeraj Ramesh Mahboobani6, Varut Vardhanabhuti7, Xiaohui Duan8, Yinghua Zhao9, Hao Chen10,11,12,13,14
1Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China.
2Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics, Guangdong Province), Guangzhou, China.
3Department of Radiology, 5th Medical Center of Chinese PLA General Hospital, Beijing, China.
4The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China.
5Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
6Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China.
7Department of Diagnostic Radiology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China.
8Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China. duanxh5@mail.sysu.edu.cn.
9Department of Radiology, The Third Affiliated Hospital of Southern Medical University (Academy of Orthopedics, Guangdong Province), Guangzhou, China. zhaoyh@smu.edu.cn.
10Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China. jhc@ust.hk.
11Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong, China. jhc@ust.hk.
12Division of Life Science, The Hong Kong University of Science and Technology, Hong Kong, China. jhc@ust.hk.
13HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Shenzhen, China. jhc@ust.hk.
14State Key Laboratory of Nervous System Disorders, The Hong Kong University of Science and Technology, Hong Kong, China. jhc@ust.hk.
PubMed DOI

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-inva…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.