Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Gastroenterol. Apr 14, 2026; 32(14): 116041
Published online Apr 14, 2026. doi: 10.3748/wjg.v32.i14.116041
Published online Apr 14, 2026. doi: 10.3748/wjg.v32.i14.116041
Evidence-based radiologist-supervised automated Liver Imaging Reporting and Data System categorization for the diagnosis of hepatocellular carcinoma
Xue-Qin Xia, Ren-Cheng Zheng, Yu-Xiang Dai, Hui Zhang, Xin-Ran Wu, He Wang, Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 201203, China
Ruo-Fan Sheng, Li Yang, Meng-Su Zeng, Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Ruo-Fan Sheng, Li Yang, Meng-Su Zeng, Shanghai Institute of Medical Imaging, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Ying-Hua Chu, MR Research Collaboration Team, Siemens Healthineers Ltd., Shanghai 200126, China
Nan-Nan Shi, Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai 201508, China
Cheng-Yan Wang, Human Phenome Institute, Fudan University, Shanghai 201203, China
Meng-Su Zeng, Cancer Center, Zhongshan Hospital, Fudan University, Shanghai 200032, China
He Wang, Department of Radiology, Shanghai Fourth People’s Hospital Affiliated to Tongji University School of Medicine, Shanghai 200434, China
He Wang, Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Fudan University, Shanghai 201203, China
Co-first authors: Xue-Qin Xia and Ruo-Fan Sheng.
Co-corresponding authors: Meng-Su Zeng and He Wang.
Author contributions: Xia XQ, Sheng RF, Wang H, Zeng MS, Wang CY, and Yang L participated in the conception and design of the study and were involved in the acquisition, analysis, or interpretation of data; Xia XQ and Sheng RF wrote the manuscript and contributed equally as co-first authors; Zheng RC, Dai YX, Chu YH, Zhang H, and Wu XR accessed and verified the study data; Zeng MS and Wang H contributed equally as co-corresponding authors. All authors critically reviewed and provided final approval of the manuscript.
Supported by National Natural Science Foundation of China, No. 82271956; and Shanghai Municipal Science and Technology Explorer Project, No. 23TS1400500.
Institutional review board statement: This investigation was approved by the Institutional Ethical Committee of Zhongshan Hospital, Fudan University, No. B2021-113R.
Informed consent statement: Written informed consent was waived due to the retrospective nature of the study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
Data sharing statement: The data and technical details that support the findings of this study are available from the corresponding author on reasonable request.
Corresponding author: He Wang, PhD, Professor, Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, No. 825 Zhangheng Road, Shanghai 201203, China. hewang@fudan.edu.cn
Received: November 3, 2025
Revised: December 31, 2025
Accepted: February 6, 2026
Published online: April 14, 2026
Processing time: 153 Days and 5.4 Hours
Revised: December 31, 2025
Accepted: February 6, 2026
Published online: April 14, 2026
Processing time: 153 Days and 5.4 Hours
Core Tip
Core Tip: This study developed transparent classifiers for three of the major Liver Imaging Reporting and Data System (LI-RADS) features: Arterial phase hyper-enhancement, washout, and capsule. Then, LI-RADS categories were assigned in accordance with the LI-RADS v2018 guidelines. By following LI-RADS guidelines and emulating the decision-making process of radiologists, the model achieved radiologist-supervised automated LI-RADS categorization, through specialized feature characterization algorithms that provide explicit evidence for feature classification, thereby improving transparency for radiologists and patients. Categorization among LI-RADS grade 3, 4 and 5 achieved accuracies of 80.6%, 74.1%, and 77.9% for the internal testing set and two external testing sets, respectively.