AI enhanced diagnostic accuracy and workload reduction in hepatocellular carcinoma screening.

Journal: NPJ digital medicine
Published Date: Aug 2, 2025

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.

Authors

  • Rui-Fang Lu
    Department 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 University, Guangzhou, China.
  • Chao-Yin She
    School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xian, China.
  • Dan-Ni He
    Department of Medical Ultrasonics, The Seventh Affiliated Hospital of Sun Yat-Sen University, Shenzhen, China.
  • Mei-Qing Cheng
    Department 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 University, Guangzhou, China.
  • Ying Wang
    Key Laboratory of Macromolecular Science of Shaanxi Province, School of Chemistry & Chemical Engineering, Shaanxi Normal University, Xi'an, Shaanxi 710062, China.
  • Hui Huang
    Department of Biobank, The Sixth Affiliated People's Hospital of Dalian Medical University, Dalian, Liaoning, China.
  • Ya-Dan Lin
    Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.
  • Jia-Yi Lv
    Department of Medical Ultrasound, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.
  • Si Qin
    Department of Medical Ultrasonics, Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
  • Ze-Zhi Liu
    Department of Medical Ultrasonics, Sanshui District People's Hospital, Foshan, China.
  • Zhi-Rong Lu
    Department of Medical Ultrasonics, Sanshui District People's Hospital, Foshan, China.
  • Wei-Ping Ke
    Department 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 University, Guangzhou, China.
  • Chao-Qun Li
    Department of Medical Ultrasound, West China Xiamen Hospital of Sichuan University, Xiamen, China.
  • Han Xiao
    Department of Radiation Oncology, Zhongshan Hospital, Fudan University, Shanghai, China.
  • Zuo-Feng Xu
    Department of Medical Ultrasonics, The Seventh Affiliated Hospital of Sun Yat-Sen University, Shenzhen, China.
  • Guang-Jian Liu
    Department of Medical Ultrasonics, The Sixth Affiliated Hospital of Sun Yat-sen University (Guangdong Gastrointestinal Hospital), Guangzhou, China.
  • Hong Yang
    Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, China.
  • Jie Ren
    Digital Clinical Measures, Translational Medicine, Merck & Co., Inc., Rahway, NJ, United States.
  • Hai-Bo Wang
    State Key Laboratory of Diarrhea Disease Detection, Zhuhai International Travel Healthcare Center, Zhuhai Entry-Exit Inspection and Quarantine Bureau, Zhuhai 519020, Guangdong, PR China. Electronic address: wanghb1013@hotmail.com.
  • Ming-De Lu
    Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-Sen University, 58 Zhongshan Road 2, Guangzhou, 510080, People's Republic of China.
  • Qing-Hua Huang
    School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xian, China. qhhuang@nwpu.edu.cn.
  • Li-Da Chen
    Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-Sen University, 58 Zhongshan Road 2, Guangzhou, 510080, People's Republic of China. chenlda@mail.sysu.edu.cn.
  • Wei Wang
    State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences, University of Macau, Macau 999078, China.
  • Ming Kuang
    School of Medicine, Jiangsu University, Zhenjiang 212013, China.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals