An expert-level generalist AI for abdominal CT diagnosis
Science · 17.09.2026 · 393 (6817)
DOI: 10.1126/science.aec6129 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science, erschienen am 17.09.2026. Verfasst von Qi Zhang und 39 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Artificial Intelligence, Radiography, Abdominal, Abdomen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Provincial Medical and Health Technology Project, Noncommunicable Chronic Diseases National Science and Technology Major Project.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- 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.
ORCID-Profile: Qi Zhang, Jianpeng Zhang, Weiwei Cao, Zilin Lu, Wanxing Chang, Haonan Ding, Xing Xue, Shaoteng Zhang, Yutong Xie, Yong Xia, Zhongyi Shui, Tony C W Mok, Xianghua Ye, Jian Ding, Zhaomin Ni, Jianwen Ning, Chaohui Yu, Shenghong Ju, Wenbo Xiao, Ling Zhang, Tingbo Liang
Förderung
- National Natural Science Foundation of China
- Zhejiang Provincial Medical and Health Technology Project
- Noncommunicable Chronic Diseases National Science and Technology Major Project
- Zhejiang Province Postdoctoral Research Excellence Funding Program
Zitieren
APA
Zhang, Q., Zhang, J., Cao, W., Lu, Z., Chang, W., Ding, H., Chen, C., Li, Z., Xue, X., Wang, S., Zhang, S., Xie, Y., Xia, Y., Wu, Q., Shui, Z., Li, X., Zheng, Z., Zhou, Y., Mok, T. C. W., …, & Liang, T. (2026). An expert-level generalist AI for abdominal CT diagnosis. Science, 393(6817). https://doi.org/10.1126/science.aec6129
Vancouver
Zhang Q, Zhang J, Cao W, Lu Z, Chang W, Ding H, et al. An expert-level generalist AI for abdominal CT diagnosis. Science. 2026;393(6817). doi:10.1126/science.aec6129
BibTeX
@article{Zhang2026,
author = {Zhang, Qi and Zhang, Jianpeng and Cao, Weiwei and Lu, Zilin and Chang, Wanxing and Ding, Haonan and Chen, Cao and Li, Zhi and Xue, Xing and Wang, Sinuo and Zhang, Shaoteng and Xie, Yutong and Xia, Yong and Wu, Qi and Shui, Zhongyi and Li, Xi and Zheng, Zhilin and Zhou, Yanjie and Mok, Tony C W and Xia, Yingda and Wang, Hongkan and Ye, Xianghua and Ma, Tao and Peng, Jie and Wang, Xiaoguang and Ding, Jian and Gao, Yuming and Ye, Huazhen and Liu, Yiping and Chen, Dongjie and Ni, Zhaomin and Ning, Jianwen and Zhang, Wei and Liu, Jian and Yu, Chaohui and Ju, Shenghong and Zhang, Jianfeng and Xiao, Wenbo and Zhang, Ling and Liang, Tingbo},
title = {An expert-level generalist AI for abdominal CT diagnosis},
journal = {Science},
year = {2026},
volume = {393},
number = {6817},
doi = {10.1126/science.aec6129}
}
EUVIMED