%0 Journal Article %A Scheiner, Bernhard %A Lombardi, Pasquale %A D'Alessio, Antonio %A Kim, Gwangil %A Tafavvoghi, Masoud %A Petrenko, Oleksandr %A Goldin, Robert D %A Fulgenzi, Claudia A M %A Torkpour, Aria %A Balcar, Lorenz %A Mauri, Francesco A %A Pomej, Katharina %A Himmelsbach, Vera %A Barsch, Maryam %A Celsa, Ciro %A Cabibbo, Giuseppe %A Cheon, Jaekyung %A Krall, Anja %A Hucke, Florian %A Di Tommaso, Luca %A Bernasconi, Monica %A Rimassa, Lorenza %A Samson, Adel %A Stefanini, Bernardo %A Mozayani, Behrang %A Trauner, Michael %A Lackner, Carolin %A Stauber, Rudolf %A Vasuri, Francesco %A Piscaglia, Fabio %A Bengsch, Bertram %A Finkelmeier, Fabian %A Peck-Radosavljevic, Markus %A Rasmussen Busund, Lill-Tove %A Marafioti, Teresa %A Rahbari, Mohammad %A Heikenwalder, Mathias %A Pinter, Matthias %A Chon, Hong Jae %A Rakaee, Mehrdad %A Pinato, David J %T 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. %J Journal for ImmunoTherapy of Cancer %V 13 %N 10 %@ 2051-1426 %C London %I BioMed Central %M DKFZ-2025-02050 %P e010975 %D 2025 %X 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</td><td width="150"> %X 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</td><td width="150"> %X E slides collected from patients treated with A+B. We quantified tumor, stroma and immune cell counts/mm2 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 %K Humans %K Carcinoma, Hepatocellular: drug therapy %K Carcinoma, Hepatocellular: immunology %K Carcinoma, Hepatocellular: pathology %K Carcinoma, Hepatocellular: mortality %K Liver Neoplasms: drug therapy %K Liver Neoplasms: immunology %K Liver Neoplasms: pathology %K Liver Neoplasms: mortality %K Bevacizumab: therapeutic use %K Bevacizumab: pharmacology %K Male %K Female %K Antibodies, Monoclonal, Humanized: therapeutic use %K Antibodies, Monoclonal, Humanized: pharmacology %K Machine Learning %K Middle Aged %K Antineoplastic Combined Chemotherapy Protocols: therapeutic use %K Antineoplastic Combined Chemotherapy Protocols: pharmacology %K Aged %K Tumor Microenvironment: immunology %K Prognosis %K Treatment Outcome %K Biomarker (Other) %K Hepatocellular Carcinoma (Other) %K Immunotherapy (Other) %K Tumor infiltrating lymphocyte - TIL (Other) %K Bevacizumab (NLM Chemicals) %K Antibodies, Monoclonal, Humanized (NLM Chemicals) %K atezolizumab (NLM Chemicals) %F PUB:(DE-HGF)16 %9 Journal Article %$ pmid:41052886 %R 10.1136/jitc-2024-010975 %U https://inrepo02.dkfz.de/record/305098