Nature Communications (Feb 2024)
A multicenter clinical AI system study for detection and diagnosis of focal liver lesions
- Hanning Ying,
- Xiaoqing Liu,
- Min Zhang,
- Yiyue Ren,
- Shihui Zhen,
- Xiaojie Wang,
- Bo Liu,
- Peng Hu,
- Lian Duan,
- Mingzhi Cai,
- Ming Jiang,
- Xiangdong Cheng,
- Xiangyang Gong,
- Haitao Jiang,
- Jianshuai Jiang,
- Jianjun Zheng,
- Kelei Zhu,
- Wei Zhou,
- Baochun Lu,
- Hongkun Zhou,
- Yiyu Shen,
- Jinlin Du,
- Mingliang Ying,
- Qiang Hong,
- Jingang Mo,
- Jianfeng Li,
- Guanxiong Ye,
- Shizheng Zhang,
- Hongjie Hu,
- Jihong Sun,
- Hui Liu,
- Yiming Li,
- Xingxin Xu,
- Huiping Bai,
- Shuxin Wang,
- Xin Cheng,
- Xiaoyin Xu,
- Long Jiao,
- Risheng Yu,
- Wan Yee Lau,
- Yizhou Yu,
- Xiujun Cai
Affiliations
- Hanning Ying
- Department of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Xiaoqing Liu
- Deepwise Artificial Intelligence Laboratory
- Min Zhang
- College of Computer Science and Technology, Zhejiang University
- Yiyue Ren
- School of Medicine, Zhejiang University
- Shihui Zhen
- School of Medicine, Zhejiang University
- Xiaojie Wang
- School of Medicine, Zhejiang University
- Bo Liu
- Deepwise Artificial Intelligence Laboratory
- Peng Hu
- Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Lian Duan
- Department of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Mingzhi Cai
- Zhangzhou Municipal Hospital of Fujian Province
- Ming Jiang
- Quzhou People’s Hospital
- Xiangdong Cheng
- Cancer Hospital of the University of Chinese Academy of Sciences (ZheJiang Cancer Hospital)
- Xiangyang Gong
- Zhejiang Provincial People’s Hospital
- Haitao Jiang
- Cancer Hospital of the University of Chinese Academy of Sciences (ZheJiang Cancer Hospital)
- Jianshuai Jiang
- Department of Hepatopancreatobiliary Surgery, Ningbo First Hospital
- Jianjun Zheng
- Hwa Mei Hospital, University of Chinese Academy of Sciences (Ningbo No.2 Hospital)
- Kelei Zhu
- Department of Hepatopancreatobiliary Surgery, Yinzhou People’s Hospital
- Wei Zhou
- Department of Radiology, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou University
- Baochun Lu
- Shaoxing People’s Hospital
- Hongkun Zhou
- The First Hospital of Jiaxing Affiliated Hospital of Jiaxing University
- Yiyu Shen
- The Second Hospital of Jiaxing Affiliated Hospital of Jiaxing University
- Jinlin Du
- Jinhua Municipal Central Hospital
- Mingliang Ying
- Jinhua Municipal Central Hospital
- Qiang Hong
- Jinhua GuangFU Hospital
- Jingang Mo
- Taizhou Municipal Central Hospital
- Jianfeng Li
- The First People’s Hospital of Wenling
- Guanxiong Ye
- Lishui People’s Hospital
- Shizheng Zhang
- Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Hongjie Hu
- Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Jihong Sun
- Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Hui Liu
- Central Laboratory of Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- Yiming Li
- Deepwise Artificial Intelligence Laboratory
- Xingxin Xu
- Deepwise Artificial Intelligence Laboratory
- Huiping Bai
- Deepwise Artificial Intelligence Laboratory
- Shuxin Wang
- Deepwise Artificial Intelligence Laboratory
- Xin Cheng
- Xiamen University
- Xiaoyin Xu
- Brigham and Women’ Hospital, Harvard Medical School
- Long Jiao
- Faculty of Medicine, Imperial College London
- Risheng Yu
- Department of Radiology, Second Affiliated Hospital of Zhejiang University School of Medicine
- Wan Yee Lau
- Faculty of Medicine, the Chinese University of Hong Kong
- Yizhou Yu
- Department of Computer Science, The University of Hong Kong
- Xiujun Cai
- Department of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
- DOI
- https://doi.org/10.1038/s41467-024-45325-9
- Journal volume & issue
-
Vol. 15,
no. 1
pp. 1 – 16
Abstract
Abstract Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists’ F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.
