Background: Clinical benefits of atezolizumab plus bevacizumab (atezolizumab-bevacizumab) are observed only in a subset of patients with hepatocellular carcinoma and the development of biomarkers is needed to improve therapeutic strategies. The atezolizumab-bevacizumab response signature (ABRS), assessed by molecular biology profiling techniques, has been shown to be associated with progression-free survival after treatment initiation. The primary objective of our study was to develop an artificial intelligence (AI) model able to estimate ABRS expression directly from histological slides, and to evaluate if model predictions were associated with progression-free survival., Methods: In this multicentre retrospective study, we developed a model (ABRS-prediction; ABRS-P), which was derived from the previously published clustering-constrained attention multiple instance learning (or CLAM) pipeline. We trained the model fit for regression analysis using a multicentre dataset from The Cancer Genome Atlas (patients treated by surgical resection, n=336). The ABRS-P model was externally validated on two independent series of samples from patients with hepatocellular carcinoma (a surgical resection series, n=225; and a biopsy series, n=157). The predictive value of the model was further tested in a series of biopsy samples from a multicentre cohort of patients with hepatocellular carcinoma treated with atezolizumab-bevacizumab (n=122). All samples in the study were from adults (aged ≥18 years). The validation sets were sampled between Jan 1, 2008, to Jan 1, 2023. For the multicentre validation set, the primary objective was to assess the association of high versus low ABRS-P values, defined relative to cross-validation median split thresholds in the first biopsy series, with progression-free survival after treatment initiation. Finally, we performed spatial transcriptomics and matched prediction heatmaps with in situ expression profiles., Findings: Of the 840 patients sampled, 641 (76%) were male and 199 (24%) were female. Across the development and validation datasets, hepatocellular carcinoma risk factors included alcohol intake, hepatitis B and C virus infections, and non-alcoholic steatohepatitis. Using cross-validation in the development series, the mean Pearson's correlation between ABRS-P values and ABRS score (mean expression of ABRS genes) was r=0·62 (SD 0·09; mean p<0·0001, SD<0·0001). The ABRS-P generalised well on the external validation series (surgical resection series, r=0·60 [95% CI 0·51-0·68], p<0·0001; biopsy series, r=0·53 [0·40-0·63], p<0·0001). In the 122 patients treated with atezolizumab-bevacizumab, those with ABRS-P-high tumours (n=74) showed significantly longer median progression-free survival than those with ABRS-P-low tumours (n=48) after treatment initiation (12 months [95% CI 7-not reached] vs 7 months [4-9]; p=0·014). Spatial transcriptomics showed significantly higher ABRS score, along with upregulation of various other immune effectors, in tumour areas with high ABRS-P values versus areas with low ABRS-P values., Interpretation: Our study indicates that AI applied on hepatocellular carcinoma digital slides is able to serve as a biomarker for progression-free survival in patients treated with atezolizumab-bevacizumab. This approach could be used in the development of inexpensive and fast biomarkers for targeted therapies. The combination of AI heatmaps with spatial transcriptomics provides insight on the molecular features associated with predictions. This methodology could be applied to other cancers or diseases and improve understanding of the biological mechanisms that drive responses to treatments., Funding: Institut National du Cancer, Fondation ARC, China Scholarship Council, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb Pour la Recherche en Immuno-Oncologie., Competing Interests: Declaration of interests LR reports grants from Agios, AstraZeneca, BeiGene, Eisai, Exelixis, Fibrogen, Incyte, Ipsen, Lilly, MSD, Nerviano Medical Sciences, Roche, and Zymeworks; consulting fees from AstraZeneca, Basilea, Bayer, Bristol Myers Squibb, Eisai, Exelixis, Genenta, Hengrui, Incyte, Ipsen, IQVIA, Jazz Pharmaceuticals, MSD, Nerviano Medical Sciences, Roche, Servier, Taiho Oncology, and Zymeworks; honoraria from AstraZeneca, Bayer, Bristol Myers Squibb, Eisai, Incyte, Ipsen, Merck Serono, Roche, and Servier; support for attending meetings from AstraZeneca; is Treasurer for the International Liver Cancer Association and member of the Executive Council of the International Liver Cancer Association; and is Co-chair of the European Organisation for Research and Treatment of Cancer task force on hepatobiliary and neuroendocrine tumours. SL reports grants from Institut National du Cancer, Fondation ARC, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb. MP reports consulting fees from Bayer, Bristol Myers Squibb, Eisai, Roche, AstraZeneca, Ipsen, Lilly, and MSD; honoraria from Bayer, Bristol Myers Squibb, Eisai, Roche, and MSD; and support for attending meetings from Bayer, Bristol Myers Squibb, Ipsen, and Roche. VP reports honoraria from Servier and participation in an advisory board for Bristol Myers Squibb. FP reports grants from Institut National du Cancer, Fondation ARC, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb. JB reports grants from Diafir, Echosens, Intercept, Inventiva, and Siemens; consulting fees from AstraZeneca, Echosens, Intercept, and Siemens; speaker fees from AbbVie, Gilead, Intercept, and Siemens; and participation in advisory boards for Bristol Myers Squibb, Intercept, Pfizer, MSD, and NovoNordisk. MM reports grants from Institut National du Cancer, Fondation ARC, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb. AV reports consulting fees from Astra Zeneca, Amgen, Beigene, Böhringer Mannheim, Bristol Myers Squibb, BTG, Daichi-Sankyo, Eisai, Incyte, Ipsen, MSD, Pierre Fabre, Roche, Servier, Sirtex, Tah, and Terumo; honoraria from AstraZeneca, Amgen, BeiGene, Böhringer Mannheim, BMS, BTG, Daichi-Sankyo, Eisai, GSK, Imaging Equipment (acquired by AAA), Incyte, Ipsen, Jiangsu Hengrui Medicines, MSD, Pierre Fabre, Roche, Servier, Sirtex, Tahio, and Terumo; and participation in advisory boards for AstraZeneca, Amgen, BeiGene, Böhringer Mannheim, BMS, BTG, Daichi-Sankyo, Eisai, Incyte, Ipsen, MSD, PierreFabre, Roche, Servier, Sirtex, Tahio, and Terumo. DJP reports grants from Associazone Per la Ricerca sul Cancro; consulting fees from AstraZeneca, MiNa Therapeutics, Avamune, Roche, Mursla, LiFt Biosciences, and Boeringher Ingelheim; honoraria from Roche, AstraZeneca, and Ipsen; and participation in advisory boards for AstraZeneca, Exact Sciences, and Roche. BM reports competitive grants from Instituto de Salud Carlos III (grant numbers PI18/00961 and PI21/00714), cofounded by the EU; grants from Laboratorios Viñas; honoraria from Bayer, Roche, Eisai, and AstraZeneca; support for attending meetings from Roche and Eisai; and participation in advisory boards for Bayer, Eisai, and Roche. JC reports grants from Institut National du Cancer, Fondation ARC, Ligue Contre le Cancer du Val de Marne, Fondation de l'Avenir, Ipsen, and Fondation Bristol Myers Squibb; honoraria from Servier, AstraZeneca, and Ipsen; participation in an advisory board for Bristol Myers Squibb; and owning stock in Clarapath. BrS reports grants from Instituto de Salud Carlos III and Bristol Myers Squibb; consulting fees from Adaptimmune, AstraZeneca, Bayer, Bristol Myers Squibb, Boston Scientific, Eisai, Incyte, Ipsen, MSD, Roche, Sanofi, Sirtex Medical, and Terumo; honoraria from AstraZeneca, Bayer, Bristol Myers Squibb, Eisai, Incyte, Ipsen, Roche, Sirtex Medical, and Terumo; advisory board participation for the GOING and ACTION trials; and support for attending meetings from AstraZeneca. BeS reports grants from Eisai and travel grants from AbbVie, Ipsen, Gilead, and AstraZeneca. MN reports honoraria from Astellas, Ipsen, and Roche. J-CN reports grants from Ipsen and Bayer. DSA reports grants from Ventana Medical Systems, Novo Nordisk, Hamni, Pfizer, Viking Therapeutics, and the US National Institutes of Health (grant numbers NIAA P50 and NIDDK U01); and is Secretary/Treasurer for the Hans Popper Hepatopathology Society. AD'A reports consulting fees, honoraria, and support to attend meetings from Roche. JA reports honoraria from Pfizer and Roche; and participation in a steering committee for Roche. MI reports grant funding from the Italian Ministry of Health; honoraria from Roche, AstraZeneca, Ipsen, Bayer, Gilead, Eisai, and MSD; support for attending meetings from AstraZeneca and Roche; and participation in advisory boards for AstraZeneca and Roche. All other authors declare no competing interests., (Copyright © 2023 Elsevier Ltd. All rights reserved.)