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.
Development and validation of a deep-learning-based diagnostic model for drug-induced liver injury using computed tomography images
Shu-Yue Wang, Si-Qi Yin, Jie-Ying Yang, Ming-Yan Ji, Xiao-Qing Zeng, Sheng-Xiang Rao, Min-Zhi Lv, Jie Bao, Man-Ning Wang, Hong Gao
Shu-Yue Wang, Jie-Ying Yang, Ming-Yan Ji, Xiao-Qing Zeng, Hong Gao, Department of Gastroenterology and Hepatology, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Si-Qi Yin, Man-Ning Wang, Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China
Si-Qi Yin, Man-Ning Wang, Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention, Shanghai 200032, China
Sheng-Xiang Rao, Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Min-Zhi Lv, Department of Cancer Screening and Prevention, Zhongshan Hospital, Fudan University, Shanghai 200032, China
Jie Bao, Key Laboratory of Clinical Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450000, Henan Province, China
Hong Gao, Evidence-Based Medicine Center, Fudan University, Shanghai 200032, China
Co-first authors: Shu-Yue Wang and Si-Qi Yin.
Co-corresponding authors: Man-Ning Wang and Hong Gao.
Author contributions: Wang SY and Yin SQ made equal contributions as co-first authors; Wang SY, Yin SQ, Yang JY, Zeng XQ, Gao H, and Wang MN contributed to method and model development; Wang SY, Yin SQ, Yang JY, and Ji MY performed experimental validation and data analysis; Yin SQ and Wang MN were responsible for software implementation and visualization; Gao H, Wang MN, Rao SX, Lv MZ, Bao J, and Zeng XQ provided resource support and quality control; Wang SY, Yin SQ, and Yang JY wrote the original draft; Gao H and Wang MN reviewed and edited the manuscript, administered the project, acquired funding, and contributed equally as co-corresponding authors. All authors have read and approve the final manuscript.
Supported by Science and Technique Commission of Shanghai Municipality, No. 21Y11921800; and Shanghai Municipal Health Commission, No. 202540163.
Institutional review board statement: This study was approved by the Ethics Committee of Zhongshan Hospital, Fudan University, No. B2021-171R2.
Informed consent statement: Informed written consent was obtained from all individual participants included in the study prior to their participation. For patients who were unable to provide consent due to clinical conditions, informed consent was obtained from their legally authorized representatives.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Data sharing statement: The datasets generated and/or analyzed during the current study are not publicly available due to privacy and ethical restrictions (e.g., protection of patient medical information) but are available from the corresponding authors upon reasonable request. Researchers seeking access to the data must submit a formal request to the Ethics Committee of Zhongshan Hospital, Fudan University, and provide evidence of approval from their own institutional review board. Data sharing will be conducted in compliance with relevant regulations and after ensuring the anonymity of all participants.
Corresponding author: Hong Gao, MD, PhD, Chief Physician, Department of Gastroenterology and Hepatology, Zhongshan Hospital, Fudan University, No. 180 Fenglin Road, Shanghai 200032, China.
gao.hong@zs-hospital.sh.cn
Received: October 14, 2025
Revised: November 27, 2025
Accepted: February 2, 2026
Published online: April 21, 2026
Processing time: 185 Days and 13.2 Hours
BACKGROUND
Pyrrolizidine-alkaloid induced hepatic sinusoidal obstruction syndrome (PA-HSOS) is a rare and severe drug-induced liver injury with nonspecific manifestations. Its diagnosis currently relies on exclusive strategies and often necessitates invasive examinations, posing significant clinical challenges. The potential role of artificial intelligence algorithms in diagnosing PA-HSOS remains to be established.
AIM
To develop and validate a deep-learning-based diagnostic model for PA-HSOS using computed tomography images.
METHODS
This multicenter case-control study compared PA-HSOS patients with Budd-Chiari syndrome and hepatitis B cirrhosis patients as controls. Patients from Zhongshan Hospital, Fudan University were retrospectively assigned to training or internal test cohorts, while those from the First Affiliated Hospital of Zhengzhou University formed an external cohort. We constructed the diagnostic models using multiscale convolutional modules. Model performance was compared with gastroenterologists and radiologists of varying expertise levels. Additionally, diagnostic outcomes and interpretation time with and without model assistance were evaluated.
RESULTS
Diagnostic models with deep learning methods using computed tomography images for PA-HSOS were developed. In the internal test cohort, models with different input sizes achieved area under the curve ranging from 0.853 to 0.944. Model 96 (96-mm input) demonstrated significantly higher accuracy and specificity than resident physicians (both internal medicine and radiology; P < 0.05) and comparable performance to attending specialists. The area under the curve of model 96 in the external test cohort was 0.873. When assisting clinicians, model 96 significantly improved diagnostic accuracy for internal medicine residents (0.541 to 0.757) and attending gastroenterologists (0.730 to 0.892), while reducing interpretation time across all expertise levels (all P < 0.05).
CONCLUSION
The deep learning model demonstrates promising diagnostic performance for PA-HSOS and can effectively assist clinicians in improving diagnostic accuracy and efficiency.
Core Tip: This study developed the first deep learning model for diagnosing pyrrolizidine-alkaloid induced hepatic sinusoidal obstruction syndrome based on computed tomography images. The model integrates multiscale convolutional modules and an anatomy-based region of interest sampling strategy. Initial validation showed promising diagnostic performance, with potential to improve diagnostic consistency among clinicians and reduce image interpretation time, suggesting its possible utility as a clinical decision-support tool.
