HepaKineticNet: Deep Learning of CT-Derived Intratumoral Heterogeneity for Overall Survival Prediction in BCLC Stage B-C Hepatocellular Carcinoma Treated with Locoregional Therapy Plus First-Line TKI and Anti-PD-1 Therapy.
5 affiliations
- 1Department of Interventional Therapy I, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, 250117, People's Republic of China.
- 2Department of Oncology, Yantai Qishan Hospital, Yantai Public Health Clinical Center, Yantai, 264001, People's Republic of China.
- 3Interventional Operating Room, Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, Shandong, 250117, People's Republic of China.
- 4Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, 265400, People's Republic of China.
- 5School of Radiology, Shandong First Medical University and Shandong Academy of Medical Sciences, Tai'an, 271016, People's Republic of China.
Abstract
Purpose
To develop HepaKineticNet, a deep learning framework that models inter-phase kinetic dynamics on multi-phase contrast-enhanced CT (CECT) to generate intratumoral heterogeneity (ITH) maps, and to assess in an independent external cohort whether a clinical-radiomics fusion model improves overall survival (OS) prediction in BCLC stage B-C hepatocellular carcinoma (HCC) treated with locoregional therapy plus first-line TKI and anti-PD-1 agents.Patients and methods
In this bi-institutional retrospective study, HepaKineticNet was developed using 359 patients from one institution (231 training, 128 validation) and evaluated in an independent external test cohort of 95 patients from a second institution. HepaKineticNet integrates a Spatial Kinetic Differential Attention module into an nnU-Net backbone, separately encoding arterial wash-in and delayed wash-out kinetics, with multiscale coefficient-of-variation self-supervision. Ten radiomics features (hierarchical filtering) and three clinical variables selected by LASSO-penalised Cox regression (10-fold cross-validation) were used to build clinical, radiomics, and fusion Cox models.Results
A total of 277 deaths occurred, 128 of them in the development cohort. Baseline characteristics were balanced (all P>0.05). In the external test cohort, the fusion model achieved a C-index of 0.713, exceeding the clinical model (0.651; P=0.012). Time-dependent AUCs at 1, 2, and 3 years were 0.760 (95%CI 0.651-0.864), 0.838 (95%CI 0.736-0.930), and 0.909 (95%CI 0.686-1.000), whereas those of the clinical model were 0.676, 0.742, and 0.772. Kaplan-Meier analysis showed median OS of 9.5 vs 19.0 months for high- vs low-risk strata (HR 3.02, 95%CI 1.86-4.91; P<0.001). Discrimination was consistent across ten prespecified subgroups.Conclusion
HepaKineticNet-derived ITH maps encode kinetic and spatial information that modestly improves individualized OS prediction and risk stratification in this combination-therapy HCC population, and may provide a noninvasive decision-support adjunct pending prospective validation.
Related
- Multi-b-value diffusion-weighted imaging-based habitat imaging for preoperative prediction of histological grade and prognosis in soft tissue sarcoma: focusing on intratumoral heterogeneity
- Machine learning models integrating 2D and 3D intratumoral heterogeneity features from multi-sequence MRI: accurate prediction of perineural invasion in pancreatic ductal adenocarcinoma
- Explainable machine learning integrating CT-derived intratumoral heterogeneity for histological subtype prediction in pure ground-glass lung adenocarcinoma: multicenter validation and transcriptomic characterization
- Magnetic resonance imaging-based radiomics for predicting P53-mutated hepatocellular carcinoma: intratumoral and peritumoral analysis
- Post-transplant oncologic outcomes after locoregional downstaging before living donor liver transplantation for hepatocellular carcinoma beyond Milan criteria: a systematic review and meta-analysis of selected cohorts
BibTeX
@article{li2026hepakineticnet,
title = {{HepaKineticNet: Deep Learning of CT-Derived Intratumoral Heterogeneity for Overall Survival Prediction in BCLC Stage B-C Hepatocellular Carcinoma Treated with Locoregional Therapy Plus First-Line TKI and Anti-PD-1 Therapy.}},
author = {Jinpeng Li and Wenzhe Bu and Xiaotian Hanming and Qianqian Zhang and Jinlong Song and Wei Chen},
journal = {Journal of hepatocellular carcinoma},
year = {2026},
month = oct,
doi = {10.2147/jhc.s636207},
url = {https://europepmc.org/article/MED/42836110},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - HepaKineticNet: Deep Learning of CT-Derived Intratumoral Heterogeneity for Overall Survival Prediction in BCLC Stage B-C Hepatocellular Carcinoma Treated with Locoregional Therapy Plus First-Line TKI and Anti-PD-1 Therapy.
AU - Jinpeng Li
AU - Wenzhe Bu
AU - Xiaotian Hanming
AU - Qianqian Zhang
AU - Jinlong Song
AU - Wei Chen
PY - 2026
DA - 2026/10/01
JO - Journal of hepatocellular carcinoma
DO - 10.2147/jhc.s636207
UR - https://europepmc.org/article/MED/42836110
AB - Purpose To develop HepaKineticNet, a deep learning framework that models inter-phase kinetic dynamics on multi-phase contrast-enhanced CT (CECT) to generate intratumoral heterogeneity (ITH) maps, and to assess in an independent external cohort whether a clinical-radiomics fusion model improves overall survival (OS) prediction in BCLC stage B-C hepatocellular carcinoma (HCC) treated with locoregional therapy plus first-line TKI and anti-PD-1 agents.Patients and methods In this bi-institutional retrospective study, HepaKineticNet was developed using 359 patients from one institution (231 training, 128 validation) and evaluated in an independent external test cohort of 95 patients from a second institution. HepaKineticNet integrates a Spatial Kinetic Differential Attention module into an nnU-Net backbone, separately encoding arterial wash-in and delayed wash-out kinetics, with multiscale coefficient-of-variation self-supervision. Ten radiomics features (hierarchical filtering) and three clinical variables selected by LASSO-penalised Cox regression (10-fold cross-validation) were used to build clinical, radiomics, and fusion Cox models.Results A total of 277 deaths occurred, 128 of them in the development cohort. Baseline characteristics were balanced (all P>0.05). In the external test cohort, the fusion model achieved a C-index of 0.713, exceeding the clinical model (0.651; P=0.012). Time-dependent AUCs at 1, 2, and 3 years were 0.760 (95%CI 0.651-0.864), 0.838 (95%CI 0.736-0.930), and 0.909 (95%CI 0.686-1.000), whereas those of the clinical model were 0.676, 0.742, and 0.772. Kaplan-Meier analysis showed median OS of 9.5 vs 19.0 months for high- vs low-risk strata (HR 3.02, 95%CI 1.86-4.91; P<0.001). Discrimination was consistent across ten prespecified subgroups.Conclusion HepaKineticNet-derived ITH maps encode kinetic and spatial information that modestly improves individualized OS prediction and risk stratification in this combination-therapy HCC population, and may provide a noninvasive decision-support adjunct pending prospective validation.
SN - 2253-5969
ER -