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...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
December 2025
|
| In: |
JHEP reports
Year: 2025, Jahrgang: 7, Heft: 12, Pages: 1-13 |
| ISSN: | 2589-5559 |
| DOI: | 10.1016/j.jhepr.2025.101592 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1016/j.jhepr.2025.101592 Verlag, kostenfrei, Volltext: https://www.sciencedirect.com/science/article/pii/S2589555925002745 
|
| Verfasserangaben: | 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 |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1950572226 | ||
| 003 | DE-627 | ||
| 005 | 20260129102213.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 260129s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jhepr.2025.101592 |2 doi | |
| 035 | |a (DE-627)1950572226 | ||
| 035 | |a (DE-599)KXP1950572226 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Seraphin, Tobias Paul |d 1991- |e VerfasserIn |0 (DE-588)1274116899 |0 (DE-627)1823852971 |4 aut | |
| 245 | 1 | 0 | |a Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma |c 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 |
| 264 | 1 | |c December 2025 | |
| 300 | |b Illustrationen | ||
| 300 | |a 13 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Online verfügbar: 11. September 2025, Artikelversion: 11. November 2025 | ||
| 500 | |a Gesehen am 29.01.2026 | ||
| 520 | |a 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. | ||
| 650 | 4 | |a AI | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Digital pathology | |
| 650 | 4 | |a HCC | |
| 650 | 4 | |a Molecular classes | |
| 650 | 4 | |a mVI | |
| 650 | 4 | |a Prognosis | |
| 650 | 4 | |a Tumor biology | |
| 700 | 1 | |a Mesropian, Agavni |e VerfasserIn |4 aut | |
| 700 | 1 | |a Žigutytė, Laura |e VerfasserIn |4 aut | |
| 700 | 1 | |a Brooks, James |e VerfasserIn |4 aut | |
| 700 | 1 | |a Mauro, Ezequiel |e VerfasserIn |4 aut | |
| 700 | 1 | |a Gris-Oliver, Albert |e VerfasserIn |4 aut | |
| 700 | 1 | |a Pinyol, Roser |e VerfasserIn |4 aut | |
| 700 | 1 | |a Montironi, Carla |e VerfasserIn |4 aut | |
| 700 | 1 | |a Balaseviciute, Ugne |e VerfasserIn |4 aut | |
| 700 | 1 | |a Piqué-Gili, Marta |e VerfasserIn |4 aut | |
| 700 | 1 | |a Huguet-Pradell, Júlia |e VerfasserIn |4 aut | |
| 700 | 1 | |a van Treeck, Marko |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kallenbach, Michael |e VerfasserIn |4 aut | |
| 700 | 1 | |a Schneider, Anne Theres |e VerfasserIn |4 aut | |
| 700 | 1 | |a Roderburg, Christoph |e VerfasserIn |4 aut | |
| 700 | 1 | |a Kather, Jakob Nikolas |d 1989- |e VerfasserIn |0 (DE-588)1064064914 |0 (DE-627)812897587 |0 (DE-576)423589091 |4 aut | |
| 700 | 1 | |a Luedde, Tom |e VerfasserIn |4 aut | |
| 700 | 1 | |a Llovet, Josep M. |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t JHEP reports |d Amsterdam : Elsevier, 2019 |g 7(2025), 12 vom: Dez., Artikel-ID 101592, Seite 1-13 |h Online-Ressource |w (DE-627)166592800X |w (DE-600)2972660-8 |x 2589-5559 |7 nnas |a Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma |
| 773 | 1 | 8 | |g volume:7 |g year:2025 |g number:12 |g month:12 |g elocationid:101592 |g pages:1-13 |g extent:13 |a Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.jhepr.2025.101592 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |7 0 |
| 856 | 4 | 0 | |u https://www.sciencedirect.com/science/article/pii/S2589555925002745 |x Verlag |z kostenfrei |3 Volltext |7 0 |
| 951 | |a AR | ||
| 992 | |a 20260129 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1064064914 |a Kather, Jakob Nikolas |m 1064064914:Kather, Jakob Nikolas |d 910000 |d 910100 |e 910000PK1064064914 |e 910100PK1064064914 |k 0/910000/ |k 1/910000/910100/ |p 16 | ||
| 999 | |a KXP-PPN1950572226 |e 4864232695 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"name":{"displayForm":["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"]},"id":{"eki":["1950572226"],"doi":["10.1016/j.jhepr.2025.101592"]},"recId":"1950572226","physDesc":[{"noteIll":"Illustrationen","extent":"13 S."}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"December 2025"}],"person":[{"display":"Seraphin, Tobias Paul","family":"Seraphin","role":"aut","given":"Tobias Paul"},{"family":"Mesropian","role":"aut","given":"Agavni","display":"Mesropian, Agavni"},{"family":"Žigutytė","role":"aut","given":"Laura","display":"Žigutytė, Laura"},{"display":"Brooks, James","role":"aut","given":"James","family":"Brooks"},{"role":"aut","given":"Ezequiel","family":"Mauro","display":"Mauro, Ezequiel"},{"family":"Gris-Oliver","role":"aut","given":"Albert","display":"Gris-Oliver, Albert"},{"display":"Pinyol, Roser","given":"Roser","role":"aut","family":"Pinyol"},{"role":"aut","given":"Carla","family":"Montironi","display":"Montironi, Carla"},{"family":"Balaseviciute","given":"Ugne","role":"aut","display":"Balaseviciute, Ugne"},{"family":"Piqué-Gili","given":"Marta","role":"aut","display":"Piqué-Gili, Marta"},{"display":"Huguet-Pradell, Júlia","family":"Huguet-Pradell","role":"aut","given":"Júlia"},{"display":"van Treeck, Marko","family":"van Treeck","given":"Marko","role":"aut"},{"display":"Kallenbach, Michael","role":"aut","given":"Michael","family":"Kallenbach"},{"display":"Schneider, Anne Theres","role":"aut","given":"Anne Theres","family":"Schneider"},{"role":"aut","given":"Christoph","family":"Roderburg","display":"Roderburg, Christoph"},{"display":"Kather, Jakob Nikolas","family":"Kather","role":"aut","given":"Jakob Nikolas"},{"display":"Luedde, Tom","given":"Tom","role":"aut","family":"Luedde"},{"display":"Llovet, Josep M.","given":"Josep M.","role":"aut","family":"Llovet"}],"relHost":[{"pubHistory":["Volume 1, issue (JMay 2019)-"],"name":{"displayForm":["EASL, European Association for the Study of the Liver"]},"origin":[{"publisher":"Elsevier","publisherPlace":"Amsterdam","dateIssuedDisp":"[2019]-"}],"language":["eng"],"type":{"media":"Online-Ressource","bibl":"periodical"},"part":{"pages":"1-13","extent":"13","text":"7(2025), 12 vom: Dez., Artikel-ID 101592, Seite 1-13","issue":"12","year":"2025","volume":"7"},"title":[{"title_sort":"JHEP reports","title":"JHEP reports"}],"id":{"eki":["166592800X"],"issn":["2589-5559"],"zdb":["2972660-8"]},"physDesc":[{"extent":"Online-Ressource"}],"recId":"166592800X","disp":"Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinomaJHEP reports"}],"title":[{"title":"Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma","title_sort":"Artificial intelligence predicts outcome-related molecular profiles and vascular invasion in hepatocellular carcinoma"}],"language":["eng"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Online verfügbar: 11. September 2025, Artikelversion: 11. November 2025","Gesehen am 29.01.2026"]} | ||
| SRT | |a SERAPHINTOARTIFICIAL2025 | ||