AI and Cancer Research ── Liver ── 2026-11-13
Liver cancer: treatment, trials and AI
- Abstract
WHAT IS ALREADY KNOWN ABOUT THIS TOPIC The tumour–stroma ratio (TSR) is a promising prognostic factor in solid tumours, yet its application is limited by quantification challenges and conflicting prognostic reports. Current assessments typically rely on manual estimation or supervised segmentation artificial intelligence (AI), which treats TSR as a static scalar and assumes a linear relationship with prognosis. WHAT THIS STUDY ADDS Non-linear discovery: This study identified a distinct inverted U-shaped relationship between TSR and hepatocellular carcinoma (HCC) prognosis, defining a specific risk window that challenges the traditional linear assumption and explaining previous contradictory reports. Methodological innovation: We developed a foundation model (Conch v1.5)-driven framework that enables precise, annotation-free TSR quantification, showing strong correlation with expert pathologists’ delineation. Architectural innovation: We developed a novel ‘Token-Guided Multimodal Framework’ that transforms TSR from a simple scalar into a high-dimensional ‘semantic anchor’ alongside whole-slide image...
Journal IF-equivalent: 3.5 (OpenAlex 2-year mean citedness, value as of 2026-11-11, retrieved 2026-11-12; not the official Clarivate IF)Reference: [No authors listed]. Token-guided multimodal prognosis in hepatocellular carcinoma: a framework steered by tumour-stroma ratio. Gut. [Epub ahead of print]. doi:.Checked: Abstract only - Abstract
The aim of this study was to develop and validate a machine learning model based on contrast-enhanced CT (CECT) for predicting the overall survival (OS) in unresectable HCC patients treated with TACE combined with immune checkpoint inhibitors (ICIs) plus molecular targeted therapies (MTTs). This study retrospectively reviewed 180 unresectable HCC patients who received TACE-ICIs-MTTs therapy from 4 medical centers. The study comprised of training cohort ( n = 93), internal validation cohort ( n = 39) and external validation cohort ( n = 48). A series of analyses and kinds of models were conducted to build a Radscore. Then, models were constructed using Radscore and clinical variables selected through multivariate Cox regression analysis, evaluated by the Harrell’s concordance index (C-index) and the area under the curve (AUC). The radiomics-clinical model was further assessed by decision curve and calibration curve analysis. The Radscore was derived from 6 features selected by the optimal model (Lasso Cox + RSF with the highest C-index of 0.777). HBV infection and vascular invasion are clinical independent predictors of OS. The radiomics-clinical model demonstrated favorable performance. It achieved C-index values of 0.893(0.859–0.927), 0.758 (0.657–0.86) and 0.74 (0.624–0.856) in the training, internal validation, and external validation cohorts, respectively. In the external validation cohort, the AUCs achieved 0.731 (0.569–0.893), 0.7 (0.515–0.885), and 0.756 (0.569–0.943) for predicting 1-, 2-, and 3-year outcomes, respectively. The machine learning model based on CECT exhibited favorable performance in predicting overall survival in unresectable HCC patients treated with TACE-ICIs-MTTs, showing potential to identify likely responders and guide treatment decision-making.
Journal IF-equivalent: 5.9 (OpenAlex 2-year mean citedness, value as of 2026-11-04, retrieved 2026-11-05; not the official Clarivate IF)Reference: Ning S, Chen Y, Feng B, Sun Z, Qu Q, Lv Y, et al. Machine learning model using contrast-enhanced CT for predicting overall survival in unresectable hepatocellular carcinoma treated with TACE plus targeted and immunotherapy: a multicenter study. Sci Rep. 2026 Nov 10;16(1):37437. doi:10.1038/s41598-026-64608-3.Checked: Abstract only