Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma
Background & Aims - Advances in digital pathology and artificial intelligence (AI) are driving progress toward personalized clinical management. In hepatocellular carcinoma (HCC), AI-based models using digitized H&E slides can be a robust tool to predict outcome-related molecular profiles an...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
December 2025
|
| In: |
JHEP reports
Year: 2025, Volume: 7, Issue: 12, Pages: 1-13 |
| ISSN: | 2589-5559 |
| DOI: | 10.1016/j.jhepr.2025.101592 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.jhepr.2025.101592 Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S2589555925002745 
|
| Author Notes: | Tobias Paul Seraphin, Agavni Mesropian, Laura Žigutytė, James Brooks, Ezequiel Mauro, Albert Gris-Oliver, Roser Pinyol, Carla Montironi, Ugne Balaseviciute, Marta Piqué-Gili, Júlia Huguet-Pradell, Marko van Treeck, Michael Kallenbach, Anne Theres Schneider, Christoph Roderburg, Jakob Nikolas Kather, Tom Luedde, Josep M. Llovet |
| Summary: | Background & Aims - Advances in digital pathology and artificial intelligence (AI) are driving progress toward personalized clinical management. In hepatocellular carcinoma (HCC), AI-based models using digitized H&E slides can be a robust tool to predict outcome-related molecular profiles and presence of microvascular invasion (mVI), with potential clinical utility. - Methods - A transformer-based deep-learning (DL) model was deployed using digitized H&E slides from 431 resected HCC cases (training cohort). Five-fold cross-validation was applied, and the model was tested on two external cohorts: TCGA-LIHC (n = 363) and advanced-stage HCC cohort (n = 64). - Results - The DL model effectively predicted outcome-related molecular profiles, distinguishing poor-prognosis (S1/S2, proliferation) from good-prognosis (S3, non-proliferation) subclasses. In internal cross-validation, mean areas under the curves (AUCs) were 0.75 for proliferation and 0.79 for non-proliferation subclasses. This performance was reproduced in the TCGA test set, with AUCs ranging from 0.72-0.80, and in the advanced-stage HCC cohort, with AUCs ranging from 0.76-0.81. In these test sets, the AI-predicted non-proliferation subclass was associated with a longer median OS compared with the proliferation subclass (5.8 vs. 3.5 years in TCGA; p = 0.02). For mVI prediction, the DL model achieved a mean AUC of 0.70 in the internal cross-validation and 0.62 in the TCGA. AI-predicted mVI was associated with shorter OS (4.9 vs. 7.6 years for non-mVI; p = 0.003) and an immunosuppressive microenvironment (p = 0.002). - Conclusions - Our H&E-based AI model enables accurate prediction of outcome-related molecular subtypes of poor prognosis and presence of mVI, offering a scalable and accessible tool to extract clinically relevant features from routine histology. - Impact and implications - Outcome-related molecular profiles and the presence of microvascular invasion (mVI) are critical determinants of prognosis and treatment decisions in hepatocellular carcinoma (HCC). This study presents an artificial intelligence (AI)-based method that analyzes routine H&E-stained slides and accurately predicts: (a) biologically relevant HCC molecular subtypes associated with patient outcomes, and (b) the presence of mVI, a well-established predictor of poor outcomes and risk of recurrence, that currently requires meticulous pathological assessment of multiple H&E slides. These AI tools can offer a scalable method to support personalized treatment decisions, such as transplant eligibility, trial enrollment, or neo/adjuvant therapy planning, and may improve clinical management of HCC. Our findings lay the groundwork for incorporating AI-assisted pathology into future prospective studies aimed at improving HCC clinical management. |
|---|---|
| Item Description: | Online verfügbar: 11. September 2025, Artikelversion: 11. November 2025 Gesehen am 29.01.2026 |
| Physical Description: | Online Resource |
| ISSN: | 2589-5559 |
| DOI: | 10.1016/j.jhepr.2025.101592 |