A multicenter clinical AI system study for detection and diagnosis of focal liver lesions
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,...
Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-02-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-024-45325-9 |
_version_ | 1797247117150912512 |
---|---|
author | 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 |
author_facet | 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 |
author_sort | Hanning Ying |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-07T14:50:19Z |
format | Article |
id | doaj.art-2c32cc08247b432eb68a343ccb858ec6 |
institution | Directory Open Access Journal |
issn | 2041-1723 |
language | English |
last_indexed | 2024-04-24T19:53:35Z |
publishDate | 2024-02-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Nature Communications |
spelling | doaj.art-2c32cc08247b432eb68a343ccb858ec62024-03-24T12:27:01ZengNature PortfolioNature Communications2041-17232024-02-0115111610.1038/s41467-024-45325-9A multicenter clinical AI system study for detection and diagnosis of focal liver lesionsHanning Ying0Xiaoqing Liu1Min Zhang2Yiyue Ren3Shihui Zhen4Xiaojie Wang5Bo Liu6Peng Hu7Lian Duan8Mingzhi Cai9Ming Jiang10Xiangdong Cheng11Xiangyang Gong12Haitao Jiang13Jianshuai Jiang14Jianjun Zheng15Kelei Zhu16Wei Zhou17Baochun Lu18Hongkun Zhou19Yiyu Shen20Jinlin Du21Mingliang Ying22Qiang Hong23Jingang Mo24Jianfeng Li25Guanxiong Ye26Shizheng Zhang27Hongjie Hu28Jihong Sun29Hui Liu30Yiming Li31Xingxin Xu32Huiping Bai33Shuxin Wang34Xin Cheng35Xiaoyin Xu36Long Jiao37Risheng Yu38Wan Yee Lau39Yizhou Yu40Xiujun Cai41Department of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineDeepwise Artificial Intelligence LaboratoryCollege of Computer Science and Technology, Zhejiang UniversitySchool of Medicine, Zhejiang UniversitySchool of Medicine, Zhejiang UniversitySchool of Medicine, Zhejiang UniversityDeepwise Artificial Intelligence LaboratoryDepartment of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineDepartment of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineZhangzhou Municipal Hospital of Fujian ProvinceQuzhou People’s HospitalCancer Hospital of the University of Chinese Academy of Sciences (ZheJiang Cancer Hospital)Zhejiang Provincial People’s HospitalCancer Hospital of the University of Chinese Academy of Sciences (ZheJiang Cancer Hospital)Department of Hepatopancreatobiliary Surgery, Ningbo First HospitalHwa Mei Hospital, University of Chinese Academy of Sciences (Ningbo No.2 Hospital)Department of Hepatopancreatobiliary Surgery, Yinzhou People’s HospitalDepartment of Radiology, Huzhou Central Hospital, Affiliated Central Hospital of Huzhou UniversityShaoxing People’s HospitalThe First Hospital of Jiaxing Affiliated Hospital of Jiaxing UniversityThe Second Hospital of Jiaxing Affiliated Hospital of Jiaxing UniversityJinhua Municipal Central HospitalJinhua Municipal Central HospitalJinhua GuangFU HospitalTaizhou Municipal Central HospitalThe First People’s Hospital of WenlingLishui People’s HospitalDepartment of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineDepartment of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineDepartment of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineCentral Laboratory of Sir Run Run Shaw Hospital, Zhejiang University School of MedicineDeepwise Artificial Intelligence LaboratoryDeepwise Artificial Intelligence LaboratoryDeepwise Artificial Intelligence LaboratoryDeepwise Artificial Intelligence LaboratoryXiamen UniversityBrigham and Women’ Hospital, Harvard Medical SchoolFaculty of Medicine, Imperial College LondonDepartment of Radiology, Second Affiliated Hospital of Zhejiang University School of MedicineFaculty of Medicine, the Chinese University of Hong KongDepartment of Computer Science, The University of Hong KongDepartment of General Surgery, Sir Run Run Shaw Hospital, Zhejiang University School of MedicineAbstract 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.https://doi.org/10.1038/s41467-024-45325-9 |
spellingShingle | 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 A multicenter clinical AI system study for detection and diagnosis of focal liver lesions Nature Communications |
title | A multicenter clinical AI system study for detection and diagnosis of focal liver lesions |
title_full | A multicenter clinical AI system study for detection and diagnosis of focal liver lesions |
title_fullStr | A multicenter clinical AI system study for detection and diagnosis of focal liver lesions |
title_full_unstemmed | A multicenter clinical AI system study for detection and diagnosis of focal liver lesions |
title_short | A multicenter clinical AI system study for detection and diagnosis of focal liver lesions |
title_sort | multicenter clinical ai system study for detection and diagnosis of focal liver lesions |
url | https://doi.org/10.1038/s41467-024-45325-9 |
work_keys_str_mv | AT hanningying amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaoqingliu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT minzhang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yiyueren amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shihuizhen amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaojiewang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT boliu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT penghu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT lianduan amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingzhicai amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingjiang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiangdongcheng amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiangyanggong amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT haitaojiang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianshuaijiang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianjunzheng amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT keleizhu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT weizhou amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT baochunlu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT hongkunzhou amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yiyushen amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jinlindu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingliangying amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT qianghong amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jingangmo amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianfengli amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT guanxiongye amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shizhengzhang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT hongjiehu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jihongsun amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT huiliu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yimingli amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xingxinxu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT huipingbai amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shuxinwang amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xincheng amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaoyinxu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT longjiao amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT rishengyu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT wanyeelau amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yizhouyu amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiujuncai amulticenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT hanningying multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaoqingliu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT minzhang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yiyueren multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shihuizhen multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaojiewang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT boliu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT penghu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT lianduan multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingzhicai multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingjiang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiangdongcheng multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiangyanggong multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT haitaojiang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianshuaijiang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianjunzheng multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT keleizhu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT weizhou multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT baochunlu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT hongkunzhou multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yiyushen multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jinlindu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT mingliangying multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT qianghong multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jingangmo multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jianfengli multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT guanxiongye multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shizhengzhang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT hongjiehu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT jihongsun multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT huiliu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yimingli multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xingxinxu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT huipingbai multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT shuxinwang multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xincheng multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiaoyinxu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT longjiao multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT rishengyu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT wanyeelau multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT yizhouyu multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions AT xiujuncai multicenterclinicalaisystemstudyfordetectionanddiagnosisoffocalliverlesions |