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 21, 2026; 32(15): 116364
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116364
Published online Apr 21, 2026. doi: 10.3748/wjg.v32.i15.116364
Habitat imaging on contrast-enhanced magnetic resonance imaging predicts early response to transarterial chemoembolization in hepatocellular carcinoma
Jun-Bo Lv, Hui-Na Tang, Ji-Bo Hu, Department of Radiology, The Fourth Affiliated Hospital of School of Medicine, International School of Medicine, International Institutes of Medicine, Zhejiang University, Yiwu 322000, Zhejiang Province, China
Wei Liu, Qing-Qing Chen, Hong-Jie Hu, Department of Radiology, Sir Run-Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou 310000, Zhejiang Province, China
Yu-Guo Wei, Department of Medical Affairs, Pharmaceutical Diagnosis, General Electric Healthcare, Hangzhou 310000, Zhejiang Province, China
Co-corresponding authors: Hong-Jie Hu and Ji-Bo Hu.
Author contributions: Lv JB conceived and designed the study, handled multi-center data (collection/preprocessing), performed region of interest segmentation, intratumoral heterogeneity quantification, radiomic feature extraction and model validation, conducted SHapley Additive exPlanations analysis, drafted and revised the manuscript, and coordinated cross-institutional collaboration; Liu W reviewed imaging data, verified region of interest segmentation consistency, and organized patient follow-up information; Tang HN collected clinical data, cross-checked patient records, and managed the study database; Chen QQ assisted with imaging quality control and participated in preliminary radiomic feature screening; Hu HJ guided study design and critically revised the manuscript; Wei YG advised on magnetic resonance imaging scanning parameter standardization and optimized imaging data acquisition; Hu JB supervised the study, and secured funding; Hu HJ and Hu JB made equal contributions as co-corresponding authors; all authors approved the final version to publish.
Institutional review board statement: This study was approved by the Institutional Review Board of The Fourth Affiliated Hospital of Zhejiang University School of Medicine, No. K2025227.
Informed consent statement: Due to the retrospective nature of this study, the requirement for written informed consent was waived by the Institutional Review Boards.
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 ethical restrictions related to patient privacy, but are available from the corresponding author upon reasonable request and with permission of the Institutional Review Board.
Corresponding author: Ji-Bo Hu, MD, PhD, Professor, Department of Radiology, The Fourth Affiliated Hospital of School of Medicine, International School of Medicine, International Institutes of Medicine, Zhejiang University, No. N1 Shangcheng Boulevard, Yiwu 322000, Zhejiang Province, China. 3196008@zju.edu.cn
Received: November 11, 2025
Revised: December 12, 2025
Accepted: January 26, 2026
Published online: April 21, 2026
Processing time: 156 Days and 12.5 Hours
Revised: December 12, 2025
Accepted: January 26, 2026
Published online: April 21, 2026
Processing time: 156 Days and 12.5 Hours
Core Tip
Core Tip: This study builds a combined model integrating magnetic resonance imaging-based intratumoral heterogeneity habitat imaging with clinical/radiomics features to predict early transcatheter arterial chemoembolization response in hepatocellular carcinoma. Multi-center validation (153 cases vs 70 cases) confirms it outperforms single models, supporting per