AI and Cancer Research ── Liver ── 2026-11-16
Liver cancer: treatment, trials and AI
- Abstract
Immunotherapy rechallenge is considered for patients with hepatocellular carcinoma (HCC) after failure or discontinuation of prior PD-1 inhibitor–based therapy. However, reliable pretreatment tools for patient selection remain lacking. In this multicenter retrospective study, 200 patients with HCC who underwent PD-1 inhibitor rechallenge between January 2020 and June 2025 were consecutively enrolled from two centers. Among them, 157 patients from the development center were stratified-randomly assigned in a 7:3 ratio to a training cohort ( n = 109) and testing cohort ( n = 48), while 43 patients from another center served as an independent external validation cohort. The primary endpoint was objective response according to modified Response Evaluation Criteria in Solid Tumors. Three pretreatment models were developed and compared: a clinical model, a 3D deep learning (DL) feature model, and a combined clinical–3D DL model. Model performance was assessed using receiver operating characteristic and precision–recall analyses, calibration, and decision curve analysis. The ability of the models to stratify overall survival and progression-free survival was also explored. The development cohort included 157 patients (training, n = 109; testing, n = 48), of whom 26 (16.56%) achieved an objective response. Among the three models, the combined clinical–3D DL LR model showed favorable overall performance, with AUCs of 0.881, 0.853, and 0.804 and Brier scores of 0.088, 0.095, and 0.130 in the training, testing, and external validation cohorts, respectively. In the external validation cohort, the combined model achieved an accuracy of 0.814, sensitivity of 0.556, specificity of 0.882, and positive predictive value of 0.556. It significantly outperformed the clinical model in both the training ( P = 0.007) and testing ( P = 0.028) cohorts and showed favorable calibration and clinical net benefit. The combined clinical–3D DL model also significantly stratified patients according to both PFS (HR = 0.54, P = 0.008) and OS (HR = 0.55, P = 0.031) and achieved higher discriminative performance than conventional clinical staging and scoring systems. SHAP analysis identified AFP as the most influential predictor, together with multiple arterial- and venous-phase 3D DL features. Pretreatment models integrating clinical variables with CECT-derived 3D DL features showed promising performance for noninvasive prediction of response and survival stratification after PD-1 inhibitor rechallenge in HCC. These findings suggest that the integrated clinical–3D DL model may serve as a potential decision-support tool for patient selection and risk stratification in clinical practice. Further prospective multicenter validation is warranted before clinical implementation.
Journal IF-equivalent: 7.6 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Li Z, Lu Z, Ye C, Huang R, Zhang L. Pretreatment CT-based 3D deep learning feature model for predicting treatment response and stratifying survival after immunotherapy rechallenge in hepatocellular carcinoma. BMC Med Inform Decis Mak. 2026 Nov 14 [Epub ahead of print]. doi:10.1186/s12911-026-03978-0.Checked: Abstract only - Abstract
PURPOSE: To develop and externally validate a peri-ablational contrast-enhanced CT radiomics model for predicting early hepatocellular carcinoma (HCC) progression after microwave ablation (MWA) and to assess its incremental value over clinical predictors. METHODS: This retrospective multicenter study included 376 patients in training (n = 235), internal validation (n = 60), and external validation (n = 81) cohorts. Early progression was defined as local tumor progression or new intrahepatic HCC within 1 year after MWA. Radiomics features were extracted from 5-mm peri-ablational regions on multiphasic CT obtained 1-2 months after MWA. Six machine-learning algorithms and phase combinations were evaluated. The selected radiomics model was combined with independent clinical predictors. Discrimination, calibration, clinical utility, and model interpretability were assessed. RESULTS: The arterial-plus-portal venous phase (AP + PP) multilayer perceptron model achieved AUCs of 0.857, 0.815, and 0.903 in the training, internal validation, and external validation cohorts, respectively, with performance comparable to the three-phase model. Log 10 AFP and tumor size > 2 cm were independent clinical predictors. The combined clinical-radiomics model achieved AUCs of 0.926, 0.884, and 0.963, respectively. In external validation, sensitivity, specificity, and accuracy were 84.2%, 96.8%, and 93.8%, respectively. SHAP analysis identified the radiomics score as the most influential predictor. CONCLUSION: Peri-ablational AP + PP CT radiomics combined with AFP and tumor size demonstrated good discrimination for early HCC progression after MWA and may facilitate individualized risk assessment, pending further validation.
Journal IF-equivalent: 3.1 (OpenAlex 2-year mean citedness, value as of 2026-11-12, retrieved 2026-11-13; not the official Clarivate IF)Reference: Fu Y, Jiao L, Yu P, Meng Z, Qiu S, Wang Y, et al. Peri-ablational contrast-enhanced CT radiomics for predicting early progression of hepatocellular carcinoma after microwave ablation: development and external validation of a clinical–radiomics model. Abdom Radiol (NY). 2026 Nov 12 [Epub ahead of print]. doi:10.1007/s00261-026-05863-w. PMID: 43018705.Checked: Abstract only