Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
Computed tomography-based deep learning and multi-instance learning for predicting microvascular invasion and prognosis in hepatocellular carcinoma
Yong-Yi Cen, Hai-Yang Nong, Xiao-Xiao Huang, Xiu-Xian Lu, Chang-Hong Pu, Li-Hong Huang, Xiao-Jun Zheng, Zhao-Lin Pan, Yin Huang, Ke Ding, De-You Huang
Yong-Yi Cen, Hai-Yang Nong, Xiao-Xiao Huang, Xiu-Xian Lu, Chang-Hong Pu, Li-Hong Huang, Xiao-Jun Zheng, De-You Huang, Guangxi Clinical Medical Research Center for Hepatobiliary Diseases, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise 533000, Guangxi Zhuang Autonomous Region, China
Yong-Yi Cen, Hai-Yang Nong, Xiao-Xiao Huang, Xiu-Xian Lu, Chang-Hong Pu, Li-Hong Huang, Xiao-Jun Zheng, De-You Huang, Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise 533000, Guangxi Zhuang Autonomous Region, China
Zhao-Lin Pan, Department of Hepatobiliary Surgery, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise 533000, Guangxi Zhuang Autonomous Region, China
Yin Huang, Department of Pathology, Affiliated Hospital of Youjiang Medical University for Nationalities, Baise 533000, Guangxi Zhuang Autonomous Region, China
Ke Ding, Department of Radiology, The Third Affiliated Hospital of Guangxi Medical University, Nanning 530031, Guangxi Zhuang Autonomous Region, China
Co-first authors: Yong-Yi Cen and Hai-Yang Nong.
Co-corresponding authors: Ke Ding and De-You Huang.
Author contributions: Cen YY, Nong HY, Huang XX, Ding K and Huang DY carried out the studies, participated in collecting data, and drafted the manuscript; Cen YY, Nong HY, Ding K and Huang DY performed the statistical analysis and participated in its design; Lu XX, Pu CH, Huang LH, Zheng XJ, Pan ZL, Huang Y helped to draft the manuscript; All authors read and approved the final manuscript.
Supported by the National Natural Science Foundation of China, No. 81560278; The “Summit Plan (New Departure)” Project for the Development of Doctoral Degree Authorization Points and Professional Disciplines at the Affiliated Hospital of Youjiang Medical University for Nationalities, No. DF20244433; Self-funded Research Project by the Guangxi Health and Wellness Committee, No. Z-L20240824 and No. Z-L20240834; and The Project to Enhance the Research Foundations of Young and Mid-career Faculty in Guangxi Universities, No. 2024KY0562 and No. 2024KY0559.
Institutional review board statement: Following the ethical principles of the Declaration of Helsinki, we conducted a retrospective analysis of 237 patients diagnosed with hepatocellular carcinoma at the Affiliated Hospital of Youjiang Medical University for Nationalities from January 2019 to May 2024. We obtained approval from the Institutional Review Board and received a waiver of informed consent for all patients from the institution (No. YYFY-LL-2024-038).
Informed consent statement: In accordance with the Helsinki Declaration and our institution’s ethical review guidelines, the ethics committee granted a waiver of informed consent due to the non-interventional nature of the study and the de-identification of patient information.
Conflict-of-interest statement: The authors declare that they have no conflict of interest.
Data sharing statement: The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
https://creativecommons.org/Licenses/by-nc/4.0/ Corresponding author: De-You Huang, Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, No. 2 Zhongshan Road, Baise 533000, Guangxi Zhuang Autonomous Region, China.
fzxyh2012@126.com
Received: May 6, 2025
Revised: June 13, 2025
Accepted: July 21, 2025
Published online: August 14, 2025
Processing time: 97 Days and 16.1 Hours
BACKGROUND
Microvascular invasion (MVI) is an important prognostic factor in hepatocellular carcinoma (HCC), but its preoperative prediction remains challenging.
AIM
To develop and validate a 2.5-dimensional (2.5D) deep learning-based multi-instance learning (MIL) model (MIL signature) for predicting MVI in HCC, evaluate and compare its performance against the radiomics signature and clinical signature, and assess its prognostic predictive value in both surgical resection and transcatheter arterial chemoembolization (TACE) cohorts.
METHODS
A retrospective cohort consisting of 192 patients with pathologically confirmed HCC was included, of whom 68 were MVI-positive and 124 were MVI-negative. The patients were randomly assigned to a training set (134 patients) and a validation set (58 patients) in a 7:3 ratio. An additional 45 HCC patients undergoing TACE treatment were included in the TACE validation cohort. A modeling strategy based on computed tomography arterial phase images was implemented, utilizing 2.5D deep learning in combination with a MIL framework for the prediction of MVI in HCC. Moreover, this method was compared with the radiomics signature and clinical signatures, and the predictive performance of the various models was evaluated using receiver operating characteristic curves and decision curve analysis (DCA), with DeLong’s test applied to compare the area under the curve (AUC) between models. Kaplan-Meier curves were utilized to analyze differences in recurrence-free survival (RFS) or progression-free survival (PFS) among different HCC treatment cohorts stratified by MIL signature risk.
RESULTS
MIL signature demonstrated superior performance in the validation set (AUC = 0.877), significantly surpassing the radiomics signature (AUC = 0.727, P = 0.047) and clinical signature (AUC = 0.631, P = 0.004). DCA curves indicated that the MIL signature provided a greater clinical net benefit across the full spectrum of risk thresholds. In the prognostic analysis, high- and low-risk groups stratified by the MIL signature exhibited significant differences in RFS within the surgical resection cohort (training set P = 0.0058, validation set P = 0.031) and PFS within the TACE treatment cohort (P = 0.045).
CONCLUSION
MIL signature demonstrates more accurate MVI prediction in HCC, surpassing radiomics signature and clinical signature, and offers precise prognostic stratification, thereby providing new technical support for personalized HCC treatment strategies.
Core Tip: This study developed a 2.5-dimensional deep learning-based multi-instance learning (MIL) model (MIL signature) to predict microvascular invasion (MVI) in hepatocellular carcinoma (HCC) using computed tomography arterial phase images. The model outperformed traditional radiomics and clinical models, offering accurate MVI prediction and prognostic stratification for surgical resection and transcatheter arterial chemoembolization cohorts, supporting personalized HCC treatment.
