CT habitat and peritumoral radiomics for predicting progression after repeat TACE in hepatocellular carcinoma: a multicenter study
4 affiliations
- 1Department of Interventional Radiology, The Second Affiliated Hospital of Harbin Medical University
- 2Department of Central Sterile Supply, The Second Affiliated Hospital of Harbin Medical University
- 3Department of Hepatobiliary Surgery, The First Affiliated Hospital of Harbin Medical University
- 4Department of Radiology, The First Affiliated Hospital of Wenzhou Medical University
Abstract
Background: This study developed and validated an machine-learning-based radiomics model integrating tumor habitat radiomics, peritumoral radiomics, and clinical features to predict progression-free survival (PFS) following repeat transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC).
Methods: This retrospective multicenter study included 270 patients with HCC. Patients from Center 1 were assigned to training (n = 94) and internal validation (n = 41) cohorts, while Centers 2 (n = 82) and 3 (n = 53) served as external validation cohorts. Tumor habitats and 5-mm peritumoral regions were generated from contrast-enhanced CT images. Radiomics features were selected using univariate Cox and LASSO-Cox regression. A fusion model and HPC risk score were constructed by integrating selected radiomics signatures and clinical variables. Performance was assessed using time-dependent ROC, C-index, calibration, decision curve analysis, and Kaplan–Meier analyses.
Results: The optimal habitat cluster number was K = 2. Eleven habitat features, three peritumoral features, and alpha-fetoprotein were retained in the fusion model. The model achieved AUCs of 0.923, 0.921, and 0.897 for 3-, 6-, and 9-month progression-free survival in the training cohort, and 0.932, 0.863, and 0.916 in the internal validation cohort, respectively; all external AUCs exceeded 0.82. The fusion model showed higher C-index values than the clinical model across cohorts. High-risk patients had significantly shorter PFS than low-risk patients (all P < 0.001). Calibration and decision curve analyses demonstrated good agreement and clinical utility.
Conclusion: The CT-based fusion model and HPC risk score effectively predicted progression risk in HCC.
Related
- Magnetic resonance imaging-based radiomics for predicting P53-mutated hepatocellular carcinoma: intratumoral and peritumoral analysis
- Moran’s index habitat and peritumoral radiomics based on digital breast tomosynthesis for predicting Ki-67 status in breast cancer
- Intratumoral and peritumoral radiomics based on multi-parametric magnetic resonance imaging for predicting microsatellite instability in endometrial cancer
- Intratumoral habitat combined with peritumoral radiomics to improve the predictive performance of initial TACE efficacy: a multicenter retrospective study
- Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
BibTeX
@article{wang2026habitat,
title = {{CT habitat and peritumoral radiomics for predicting progression after repeat TACE in hepatocellular carcinoma: a multicenter study}},
author = {Fei Wang and Yue Hu and Zhong-Xing Shi and Xin-Yu He and Yu-Hang Sui and Fu-Kai Wen and Jia-Shan Zhan and Ning-Jing Yang and Xue-Jing Han and Jia-Hui Wang and Jia-Yi Yang and Wen Lv and Hong-Fei Liu and Li-Ming Cui},
journal = {Frontiers in Pharmacology},
year = {2026},
month = oct,
doi = {10.3389/fphar.2026.1942002},
url = {https://www.frontiersin.org/articles/10.3389/fphar.2026.1942002/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - CT habitat and peritumoral radiomics for predicting progression after repeat TACE in hepatocellular carcinoma: a multicenter study
AU - Fei Wang
AU - Yue Hu
AU - Zhong-Xing Shi
AU - Xin-Yu He
AU - Yu-Hang Sui
AU - Fu-Kai Wen
AU - Jia-Shan Zhan
AU - Ning-Jing Yang
AU - Xue-Jing Han
AU - Jia-Hui Wang
AU - Jia-Yi Yang
AU - Wen Lv
AU - Hong-Fei Liu
AU - Li-Ming Cui
PY - 2026
DA - 2026/10/14
JO - Frontiers in Pharmacology
DO - 10.3389/fphar.2026.1942002
UR - https://www.frontiersin.org/articles/10.3389/fphar.2026.1942002/full
AB - Background: This study developed and validated an machine-learning-based radiomics model integrating tumor habitat radiomics, peritumoral radiomics, and clinical features to predict progression-free survival (PFS) following repeat transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC). Methods: This retrospective multicenter study included 270 patients with HCC. Patients from Center 1 were assigned to training (n = 94) and internal validation (n = 41) cohorts, while Centers 2 (n = 82) and 3 (n = 53) served as external validation cohorts. Tumor habitats and 5-mm peritumoral regions were generated from contrast-enhanced CT images. Radiomics features were selected using univariate Cox and LASSO-Cox regression. A fusion model and HPC risk score were constructed by integrating selected radiomics signatures and clinical variables. Performance was assessed using time-dependent ROC, C-index, calibration, decision curve analysis, and Kaplan–Meier analyses. Results: The optimal habitat cluster number was K = 2. Eleven habitat features, three peritumoral features, and alpha-fetoprotein were retained in the fusion model. The model achieved AUCs of 0.923, 0.921, and 0.897 for 3-, 6-, and 9-month progression-free survival in the training cohort, and 0.932, 0.863, and 0.916 in the internal validation cohort, respectively; all external AUCs exceeded 0.82. The fusion model showed higher C-index values than the clinical model across cohorts. High-risk patients had significantly shorter PFS than low-risk patients (all P < 0.001). Calibration and decision curve analyses demonstrated good agreement and clinical utility. Conclusion: The CT-based fusion model and HPC risk score effectively predicted progression risk in HCC.
SN - 1663-9812
ER -