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 Gastrointest Oncol. Oct 15, 2026; 18(10): 122464
Published online Oct 15, 2026. doi: 10.4251/wjgo.122464
Deep learning-enhanced peritumoral radiomics predicts early recurrence after hepatocellular carcinoma ablation: A two-center study
Yong-Hai Li, Ling Yao, Gui-Xiang Qian, Xue-Di Lei, Zi-Qi Tang, Bao-Yun Guo, Rui Du, Yu Zhu, Wei-Dong Jia
Yong-Hai Li, Department of Anorectal Surgery, The Third Affiliated Hospital of Anhui Medical University, The First People’s Hospital of Hefei, Hefei 230001, Anhui Province, China
Ling Yao, Department of Anorectal Surgery, Guang’ Anmen Hospital, China Academy of Chinese Medical Sciences, Beijing 100053, China
Gui-Xiang Qian, Bao-Yun Guo, Rui Du, The Third Affiliated Hospital of Anhui Medical University, The First People’s Hospital of Hefei, Hefei 230001, Anhui Province, China
Xue-Di Lei, Zi-Qi Tang, Department of Colorectal Surgery, Bengbu Medical University, Bengbu 233000, Anhui Province, China
Yu Zhu, Department of Hepatopancreatobiliary Surgery, Taizhou Hospital of Zhejiang Province Affiliated to Wenzhou Medical University, Taizhou 318000, Zhejiang Province, China
Wei-Dong Jia, Department of Hepatic Surgery, The First Affiliated Hospital of University of Science and Technology of China, University of Science and Technology of China, Hefei 230001, Anhui Province, China
Co-first authors: Yong-Hai Li and Ling Yao.
Author contributions: Li YH and Yao L contributed equally to this work as co-first authors; Li YH, Yao L, Qian GX and Jia WD revised the manuscript; Li YH, Yao L, Qian GX, Lei XD, Zi-Qi Tang, and Zhu Y collected the data; Li YH and Jia WD designed the research study; Guo BY and Du R analyzed the data; all authors wrote the manuscript, have read and approve the final manuscript.
AI contribution statement: The authors declare that no AI tools were used in the preparation of this manuscript. All writing, data analysis, and figure preparation were performed solely by the authors. The authors take full responsibility for the integrity, accuracy, and originality of the work.
Supported by The National Key Research and Development Program of China, No. 2022YFA1304504; and Health Science and Technology Projects of Hefei Municipal Health Commission, No. Hwk2025zd005.
Institutional review board statement: This study was approved by approved by the Ethics Management Committee of the First Affiliated Hospital of University of Science and Technology of China, No. 2021-RE-043.
Informed consent statement: The requirement for informed consent was waived owing to the retrospective nature of the study.
Conflict-of-interest statement: All authors declare no conflict of interest in publishing the manuscript.
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 analysed during the current study are not publicly available due to patient privacy and copyright issues but are available from the corresponding author upon reasonable request.
Corresponding author: Wei-Dong Jia, Full Professor, Department of Hepatic Surgery, The First Affiliated Hospital of University of Science and Technology of China, University of Science and Technology of China, No. 17 Lujiang Road, Luyang District, Hefei 230001, Anhui Province, China.
niche118118@sina.com
Received: April 20, 2026
Revised: June 11, 2026
Accepted: July 30, 2026
Published online: October 15, 2026
Processing time: 152 Days and 14.2 Hours
BACKGROUND
Early recurrence (ER) remains a major challenge after ablation therapy for hepatocellular carcinoma (HCC) and is closely associated with poor prognosis. Peritumoral imaging features may reflect tumor microenvironmental alterations related to recurrence. However, the most informative peritumoral range for extracting deep learning (DL) features to predict ER after HCC ablation remains unclear.
AIM
To determine the best-performing peritumoral region for predicting ER after HCC ablation using DL features.
METHODS
This retrospective cohort study enrolled 296 ablation-treated HCC patients from two centers. The patients were divided into a primary cohort (n = 222) and an external cohort (n = 74). The 3D ResNet-18 was used to extract DL features from contrast-enhanced computed tomography images of the tumor and the 3-mm, 5-mm, 10-mm, and 20-mm peritumoral regions. ER-related features were selected with least absolute shrinkage and selection operator regression, recursive feature elimination, and importance ranking. Six machine learning algorithms were used to construct predictive models to determine the region whose features resulted in optimal performance. A combined model incorporating the optimal peritumoral features with clinical imaging features (postoperative neutrophil count, intratumoral necrosis) was also developed. The models were evaluated with receiver operating characteristic curve analysis [including calculation of the area under the curve (AUC)], calibration/decision curve analysis, and Kaplan-Meier survival analysis.
RESULTS
The 10-mm peritumoral model outperformed both the tumor model and the other peritumoral models, with AUC values of 0.818 (95%CI: 0.802-0.833), 0.804 (95%CI: 0.779-0.829) in the training and internal validation sets, respectively. Incorporation of the clinical features into a combined model with the peritumoral features improved the predictive accuracy further, with AUCs of 0.855 (95%CI: 0.841-0.869), 0.852 (95%CI: 0.832-0.871) and 0.841 (95%CI: 0.811-0.871) in the training, internal and external validation sets, respectively. Calibration curve and decision curve analysis also indicated favorable performance with the combined model. Kaplan-Meier analysis demonstrated that the combined model effectively stratified patients in terms of progression-free survival and overall survival probabilities.
CONCLUSION
DL features extracted from the 10-mm peritumoral region showed the best numerical predictive performance for ER in HCC patients after ablation. The combined model demonstrated favorable predictive performance and effectively stratified patients by survival risk and thus could aid in developing personalized treatment strategies.
Core Tip: This study developed a deep learning-enhanced peritumoral radiomics model to predict early recurrence after hepatocellular carcinoma ablation. Among the evaluated peritumoral regions, the 10-mm peritumoral model showed the best numerical performance. The combined model integrating 10-mm peritumoral deep learning features and clinical imaging features enabled individualized recurrence risk stratification and may aid in developing personalized treatment strategies.
