An expert-level generalist AI for abdominal CT diagnosis.
Authors
Affiliations (26)
Affiliations (26)
- Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- MOE Joint International Research Laboratory of Pancreatic Diseases, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Alibaba DAMO Academy, Hangzhou, Zhejiang, China.
- Hupan Laboratory, Hangzhou, Zhejiang, China.
- College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China.
- Department of Radiology, Ningbo No. 2 Hospital, Ningbo, Zhejiang, China.
- Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Australian Institute for Machine Learning, Adelaide University, Adelaide SA, Australia.
- Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Masdar City, Abu Dhabi, United Arab Emirates.
- Alibaba DAMO Academy, Washington, DC, USA.
- Department of Radiation Oncology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Department of General Surgery, The First Division Hospital of Xinjiang Production and Construction Corps, Akesu, Xinjiang, China.
- Department of Radiology, The First Division Hospital of Xinjiang Production and Construction Corps, Akesu, Xinjiang, China.
- Department of Surgery, Affiliated Hospital of Jiaxing University, Jiaxing, Zhejiang, China.
- Department of Radiology, Affiliated Hospital of Jiaxing University, Jiaxing, Zhejiang, China.
- Department of General Surgery, Jixi County People's Hospital, Xuancheng, Anhui, China.
- Department of Radiology, People's Hospital of Jingning She Autonomous County, Lishui, Zhejiang, China.
- Department of Radiology, Shengzhou People's Hospital, Shaoxing, Zhejiang, China.
- Department of General Surgery, Haining People's Hospital, Jiaxing, Zhejiang, China.
- Department of Radiology, Anji County People's Hospital, Huzhou, Zhejiang, China.
- Department of Emergency, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Department of General Surgery, The First People's Hospital of Yuhang District, Hangzhou, Zhejiang, China.
- Department of Surgical Oncology, The People's Hospital of Beilun District, Ningbo, Zhejiang, China.
- Department of Gastroenterology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging & Interventional Radiology (Southeast University); Department of Radiology, Zhongda Hospital, Medical School of Southeast University, Nanjing, Jiangsu, China.
Abstract
Artificial intelligence (AI) in radiology aspires to deliver expert-level diagnosis across diverse clinical tasks, yet existing supervised strategies remain limited in scope. We developed RADAR, a generalist vision-language model trained on more than 400,000 contrast-enhanced abdominal computed tomography (CT) examinations and 15 million anatomy-wise image-text pairs, learning directly from clinical reports without manual annotation. Throughout internal and external evaluations across multiple centers and varied clinical scenarios, RADAR achieved high diagnostic performance and robust generalization for 18 anatomical structures and 146 imaging findings. In a reader study, RADAR assistance increased the diagnostic sensitivity of 26 radiologists by ~10%. RADAR offers a scalable, versatile, and interpretable solution for abdominal CT, demonstrating that generalist AI can match human experts in general and complicated radiology tasks.