TY - JOUR AU - Scheiner, Bernhard AU - Lombardi, Pasquale AU - D'Alessio, Antonio AU - Kim, Gwangil AU - Tafavvoghi, Masoud AU - Petrenko, Oleksandr AU - Goldin, Robert D AU - Fulgenzi, Claudia A M AU - Torkpour, Aria AU - Balcar, Lorenz AU - Mauri, Francesco A AU - Pomej, Katharina AU - Himmelsbach, Vera AU - Barsch, Maryam AU - Celsa, Ciro AU - Cabibbo, Giuseppe AU - Cheon, Jaekyung AU - Krall, Anja AU - Hucke, Florian AU - Di Tommaso, Luca AU - Bernasconi, Monica AU - Rimassa, Lorenza AU - Samson, Adel AU - Stefanini, Bernardo AU - Mozayani, Behrang AU - Trauner, Michael AU - Lackner, Carolin AU - Stauber, Rudolf AU - Vasuri, Francesco AU - Piscaglia, Fabio AU - Bengsch, Bertram AU - Finkelmeier, Fabian AU - Peck-Radosavljevic, Markus AU - Rasmussen Busund, Lill-Tove AU - Marafioti, Teresa AU - Rahbari, Mohammad AU - Heikenwalder, Mathias AU - Pinter, Matthias AU - Chon, Hong Jae AU - Rakaee, Mehrdad AU - Pinato, David J TI - 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. JO - Journal for ImmunoTherapy of Cancer VL - 13 IS - 10 SN - 2051-1426 CY - London PB - BioMed Central M1 - DKFZ-2025-02050 SP - e010975 PY - 2025 AB - 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"> AB - 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"> AB - 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 KW - Humans KW - Carcinoma, Hepatocellular: drug therapy KW - Carcinoma, Hepatocellular: immunology KW - Carcinoma, Hepatocellular: pathology KW - Carcinoma, Hepatocellular: mortality KW - Liver Neoplasms: drug therapy KW - Liver Neoplasms: immunology KW - Liver Neoplasms: pathology KW - Liver Neoplasms: mortality KW - Bevacizumab: therapeutic use KW - Bevacizumab: pharmacology KW - Male KW - Female KW - Antibodies, Monoclonal, Humanized: therapeutic use KW - Antibodies, Monoclonal, Humanized: pharmacology KW - Machine Learning KW - Middle Aged KW - Antineoplastic Combined Chemotherapy Protocols: therapeutic use KW - Antineoplastic Combined Chemotherapy Protocols: pharmacology KW - Aged KW - Tumor Microenvironment: immunology KW - Prognosis KW - Treatment Outcome KW - Biomarker (Other) KW - Hepatocellular Carcinoma (Other) KW - Immunotherapy (Other) KW - Tumor infiltrating lymphocyte - TIL (Other) KW - Bevacizumab (NLM Chemicals) KW - Antibodies, Monoclonal, Humanized (NLM Chemicals) KW - atezolizumab (NLM Chemicals) LB - PUB:(DE-HGF)16 C6 - pmid:41052886 DO - DOI:10.1136/jitc-2024-010975 UR - https://inrepo02.dkfz.de/record/305098 ER -