Preliminary qualification of a machine learning-based assessment of the tumor immune infiltrate as a predictor of outcome in patients with hepatocellular carcinoma treated with atezolizumab plus bevacizumab

Spontaneously immunogenic hepatocellular carcinoma (HCC), identified by a dense immune cell infiltrate (ICI), responds better to immunotherapy, although no validated biomarker exists to identify these cases. We used machine learning (ML) to quantify ICI from standard H&E-stained tissue and evaluated its correlation with characteristics of the tumor microenvironment (TME) and clinical outcome from atezolizumab plus bevacizumab (A+B).We therefore employed a supervised ML algorithm on 102 pretreatment H&E slides collected from patients treated with A+B. We quantified tumor, stroma and immune cell counts/mm<sup>2</sup> and dichotomized patients into ICI high and ICI low for clinicopathologic analysis. We correlated ICI signature with characteristics of the T-cell infiltrate (CD4+, FOXP3+, CD8+, PD1+) using multiplex immunohistochemistry in 62 resected specimens and evaluated gene expression profiles by bulk RNA sequencing in 44 samples.All patients treated with A+B were Child-Pugh A and received first-line A+B treatment for Barcelona Clinic Liver Cancer Stage C HCC (n=77, 75.5%) on a background of viral (n=53, 52%) and non-viral (n=49, 48%) liver disease. Median ICI density was 429.9 (IQR: 194.6-666.7) cells/mm<sup>2</sup> Two-thirds of patients (n=67, 65.7%) had ICI counts≥236/mm<sup>2</sup>, derived as the optimal prognostic cut-off (ICI-high). Baseline characteristics, including disease etiology, liver function, performance status, stage, prior therapy and alpha-fetoprotein (AFP) levels, were comparable between ICI-high versus ICI-low patients. Patients with ICI-high demonstrated a significantly longer overall survival (OS) compared with ICI-low: 20.9 (95% CI: 13.8 to 27.9) versus 15.3 (95% CI: 6.0 to 24.6 months, p=0.026). Multivariable analyses demonstrated ICI-low status to remain as an independent prognostic parameter (adjusted HR (aHR): 2.02, 95% CI: 1.03 to 3.96) alongside AFP concentration (per 100 ng/mL: aHR 1.00, 95% CI: 1.00 to 1.00). ICI-high tumors were characterized by STC1 underexpression and enrichment in proinflammatory gene expression sets previously associated with response to immunotherapy. The proinflammatory environment identified by ICI status was not exclusively mediated by T-cell phenotype polarization as shown by a lack of correlation between ICI-high status and CD4+, CD4+FOXP3+, CD8+ and CD8+PD1+ T-cell density.In conclusion, we propose a ML-based algorithm to identify proinflamed HCC TMEs bearing a positive correlation with the patient's OS. Digital characterization of the TME should be validated as a tool to improve precision delivery of anticancer immunotherapy.

Authors

Institutions

Publication Details

Journal
Journal for ImmunoTherapy of Cancer
Published
2025-10-01
DOI
https://doi.org/10.1136/jitc-2024-010975
Primary Topic
Cancer Immunotherapy and Biomarkers
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Preliminary qualification of a machine learning-based assessment of the tumor immune infiltrate as a predictor of outcome in patients with hepatocellular carcinoma treated with atezolizumab plus bevacizumab

David James Pinato, Teresa Marafioti, Jaekyung Cheon, Gwangil Kim et al.
Journal for ImmunoTherapy of Cancer
Cancer Immunotherapy and Biomarkers
article

Preliminary qualification of a machine learning-based assessment of the tumor immune infiltrate as a predictor of outcome in patients with hepatocellular carcinoma treated with atezolizumab plus bevacizumab

David James Pinato, Teresa Marafioti, Jaekyung Cheon, Gwangil Kim, Adel Samson, Mathias Heikenwälder, Antonio D’Alessio, Fabian Finkelmeier, Ciro Celsa, Katharina Pomej, Florian Hucke, Giuseppe Cabibbo, Rudolf E Stauber, Behrang Mozayani, Fabio Piscaglia, Bertram Bengsch, Pasquale Lombardi, Bernhard Scheiner, Claudia Angela Maria Fulgenzi, Vera Himmelsbach, Robert Goldin, Maryam Barsch, Matthias Pinter, Carolin Lackner, Francesco Vasuri, Lorenza Rimassa, Hong Jae Chon, Mehrdad Rakaee, Markus Peck‐Radosavljevic, Oleksandr Petrenko, Bernardo Stefanini, Masoud Tafavvoghi, Michael A Trauner, Lill‐Tove Busund, Anja Krall, Lorenz Balcar, Mohammad Rahbari, Aria Torkpour, Francesco Mauri, M Bernasconi
article en

Abstract

Spontaneously immunogenic hepatocellular carcinoma (HCC), identified by a dense immune cell infiltrate (ICI), responds better to immunotherapy, although no validated biomarker exists to identify these cases. We used machine learning (ML) to quantify ICI from standard H&E-stained tissue and evaluated its correlation with characteristics of the tumor microenvironment (TME) and clinical outcome from atezolizumab plus bevacizumab (A+B).We therefore employed a supervised ML algorithm on 102 pretreatment H&E slides collected from patients treated with A+B. We quantified tumor, stroma and immune cell counts/mm<sup>2</sup> and dichotomized patients into ICI high and ICI low for clinicopathologic analysis. We correlated ICI signature with characteristics of the T-cell infiltrate (CD4+, FOXP3+, CD8+, PD1+) using multiplex immunohistochemistry in 62 resected specimens and evaluated gene expression profiles by bulk RNA sequencing in 44 samples.All patients treated with A+B were Child-Pugh A and received first-line A+B treatment for Barcelona Clinic Liver Cancer Stage C HCC (n=77, 75.5%) on a background of viral (n=53, 52%) and non-viral (n=49, 48%) liver disease. Median ICI density was 429.9 (IQR: 194.6-666.7) cells/mm<sup>2</sup> Two-thirds of patients (n=67, 65.7%) had ICI counts≥236/mm<sup>2</sup>, derived as the optimal prognostic cut-off (ICI-high). Baseline characteristics, including disease etiology, liver function, performance status, stage, prior therapy and alpha-fetoprotein (AFP) levels, were comparable between ICI-high versus ICI-low patients. Patients with ICI-high demonstrated a significantly longer overall survival (OS) compared with ICI-low: 20.9 (95% CI: 13.8 to 27.9) versus 15.3 (95% CI: 6.0 to 24.6 months, p=0.026). Multivariable analyses demonstrated ICI-low status to remain as an independent prognostic parameter (adjusted HR (aHR): 2.02, 95% CI: 1.03 to 3.96) alongside AFP concentration (per 100 ng/mL: aHR 1.00, 95% CI: 1.00 to 1.00). ICI-high tumors were characterized by STC1 underexpression and enrichment in proinflammatory gene expression sets previously associated with response to immunotherapy. The proinflammatory environment identified by ICI status was not exclusively mediated by T-cell phenotype polarization as shown by a lack of correlation between ICI-high status and CD4+, CD4+FOXP3+, CD8+ and CD8+PD1+ T-cell density.In conclusion, we propose a ML-based algorithm to identify proinflamed HCC TMEs bearing a positive correlation with the patient's OS. Digital characterization of the TME should be validated as a tool to improve precision delivery of anticancer immunotherapy.

Journal for ImmunoTherapy of CancerVol. 13(10)
Università Cattolica del Sacro Cuore (IT), Goethe University Frankfurt (DE), Oslo University Hospital (NO), University College Hospital (GB), University Hospital of North Norway (NO), Humanitas University (IT), University of Freiburg (DE), German Cancer Research Center (DE), Medical University of Graz (AT), Heidelberg University (DE), University Medical Center Freiburg (DE), St James's University Hospital (GB), Agostino Gemelli University Polyclinic (IT), Klinikum Klagenfurt (AT), Azienda USL di Bologna (IT), University Hospital Frankfurt (DE), CHA University Bundang Medical Center (KR), CHA University (KR), Research Institute of Ukrainian Studies (UA), IRCCS Humanitas Research Hospital (IT), University College London (GB), Imperial College London (GB), Medical University of Vienna (AT), University of Palermo (IT), University of Bologna (IT)
UK Research and Innovation, Cancer Research UK, Imperial College London, Imperial College Healthcare NHS Trust
Openalex Percentile: Top 62%
Cancer Immunotherapy and Biomarkers
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.