AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening

Abstract Hepatocellular carcinoma (HCC) ultrasound screening encounters challenges related to accuracy and the workload of radiologists. This retrospective, multicenter study assessed four artificial intelligence (AI) enhanced strategies using 21,934 liver ultrasound images from 11,960 patients to i...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui-Fang Lu, Chao-Yin She, Dan-Ni He, Mei-Qing Cheng, Ying Wang, Hui Huang, Ya-Dan Lin, Jia-Yi Lv, Si Qin, Ze-Zhi Liu, Zhi-Rong Lu, Wei-Ping Ke, Chao-Qun Li, Han Xiao, Zuo-Feng Xu, Guang-Jian Liu, Hong Yang, Jie Ren, Hai-Bo Wang, Ming-De Lu, Qing-Hua Huang, Li-Da Chen, Wei Wang, Ming Kuang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01892-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761087696666624
author Rui-Fang Lu
Chao-Yin She
Dan-Ni He
Mei-Qing Cheng
Ying Wang
Hui Huang
Ya-Dan Lin
Jia-Yi Lv
Si Qin
Ze-Zhi Liu
Zhi-Rong Lu
Wei-Ping Ke
Chao-Qun Li
Han Xiao
Zuo-Feng Xu
Guang-Jian Liu
Hong Yang
Jie Ren
Hai-Bo Wang
Ming-De Lu
Qing-Hua Huang
Li-Da Chen
Wei Wang
Ming Kuang
author_facet Rui-Fang Lu
Chao-Yin She
Dan-Ni He
Mei-Qing Cheng
Ying Wang
Hui Huang
Ya-Dan Lin
Jia-Yi Lv
Si Qin
Ze-Zhi Liu
Zhi-Rong Lu
Wei-Ping Ke
Chao-Qun Li
Han Xiao
Zuo-Feng Xu
Guang-Jian Liu
Hong Yang
Jie Ren
Hai-Bo Wang
Ming-De Lu
Qing-Hua Huang
Li-Da Chen
Wei Wang
Ming Kuang
author_sort Rui-Fang Lu
collection DOAJ
description Abstract Hepatocellular carcinoma (HCC) ultrasound screening encounters challenges related to accuracy and the workload of radiologists. This retrospective, multicenter study assessed four artificial intelligence (AI) enhanced strategies using 21,934 liver ultrasound images from 11,960 patients to improve HCC ultrasound screening accuracy and reduce radiologist workload. UniMatch was used for lesion detection and LivNet for classification, trained on 17,913 images. Among the strategies tested, Strategy 4, which combined AI for initial detection and radiologist evaluation of negative cases in both detection and classification phases, outperformed others. It not only matched the high sensitivity of original algorithm (0.956 vs. 0.991) but also improved specificity (0.787 vs. 0.698), reduced radiologist workload by 54.5%, and decreased both recall and false positive rates. This approach demonstrates a successful model of human-AI collaboration, not only enhancing clinical outcomes but also mitigating unnecessary patient anxiety and system burden by minimizing recalls and false positives.
format Article
id doaj-art-002a3a72d22c4a7482c2002f1b97c612
institution DOAJ
issn 2398-6352
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-002a3a72d22c4a7482c2002f1b97c6122025-08-20T03:06:08ZengNature Portfolionpj Digital Medicine2398-63522025-08-018111210.1038/s41746-025-01892-9AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screeningRui-Fang Lu0Chao-Yin She1Dan-Ni He2Mei-Qing Cheng3Ying Wang4Hui Huang5Ya-Dan Lin6Jia-Yi Lv7Si Qin8Ze-Zhi Liu9Zhi-Rong Lu10Wei-Ping Ke11Chao-Qun Li12Han Xiao13Zuo-Feng Xu14Guang-Jian Liu15Hong Yang16Jie Ren17Hai-Bo Wang18Ming-De Lu19Qing-Hua Huang20Li-Da Chen21Wei Wang22Ming Kuang23Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversitySchool of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical UniversityDepartment of Medical Ultrasonics, The Seventh Affiliated Hospital of Sun Yat-Sen UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangzhou Medical universityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasonics, The Sixth Affiliated Hospital, Sun Yat-sen UniversityDepartment of Medical Ultrasonics, Sanshui District People’s HospitalDepartment of Medical Ultrasonics, Sanshui District People’s HospitalDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasound, West China Xiamen Hospital of Sichuan UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasonics, The Seventh Affiliated Hospital of Sun Yat-Sen UniversityDepartment of Medical Ultrasonics, The Sixth Affiliated Hospital, Sun Yat-sen UniversityDepartment of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Medical Ultrasonics, The Third Affiliated Hospital of Sun Yat-Sen UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversitySchool of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityDepartment of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, MedAI Collaborative Lab, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-sen UniversityAbstract Hepatocellular carcinoma (HCC) ultrasound screening encounters challenges related to accuracy and the workload of radiologists. This retrospective, multicenter study assessed four artificial intelligence (AI) enhanced strategies using 21,934 liver ultrasound images from 11,960 patients to improve HCC ultrasound screening accuracy and reduce radiologist workload. UniMatch was used for lesion detection and LivNet for classification, trained on 17,913 images. Among the strategies tested, Strategy 4, which combined AI for initial detection and radiologist evaluation of negative cases in both detection and classification phases, outperformed others. It not only matched the high sensitivity of original algorithm (0.956 vs. 0.991) but also improved specificity (0.787 vs. 0.698), reduced radiologist workload by 54.5%, and decreased both recall and false positive rates. This approach demonstrates a successful model of human-AI collaboration, not only enhancing clinical outcomes but also mitigating unnecessary patient anxiety and system burden by minimizing recalls and false positives.https://doi.org/10.1038/s41746-025-01892-9
spellingShingle Rui-Fang Lu
Chao-Yin She
Dan-Ni He
Mei-Qing Cheng
Ying Wang
Hui Huang
Ya-Dan Lin
Jia-Yi Lv
Si Qin
Ze-Zhi Liu
Zhi-Rong Lu
Wei-Ping Ke
Chao-Qun Li
Han Xiao
Zuo-Feng Xu
Guang-Jian Liu
Hong Yang
Jie Ren
Hai-Bo Wang
Ming-De Lu
Qing-Hua Huang
Li-Da Chen
Wei Wang
Ming Kuang
AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
npj Digital Medicine
title AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
title_full AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
title_fullStr AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
title_full_unstemmed AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
title_short AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
title_sort ai enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening
url https://doi.org/10.1038/s41746-025-01892-9
work_keys_str_mv AT ruifanglu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT chaoyinshe aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT dannihe aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT meiqingcheng aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT yingwang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT huihuang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT yadanlin aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT jiayilv aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT siqin aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT zezhiliu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT zhironglu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT weipingke aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT chaoqunli aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT hanxiao aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT zuofengxu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT guangjianliu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT hongyang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT jieren aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT haibowang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT mingdelu aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT qinghuahuang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT lidachen aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT weiwang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening
AT mingkuang aienhanceddiagnosticaccuracyandworkloadreductioninhepatocellularcarcinomascreening