{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T22:39:31Z","timestamp":1791412771626,"version":"4.3.3"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>PD-L1 expression is widely used as a predictive biomarker for anti-PD-1 therapies in non-small cell lung cancer (NSCLC). However, its prognostic value remains controversial. Here, we investigated whether deep learning (DL) applied to PD-L1 immunohistochemistry (IHC) slides could identify histological patterns predictive of outcome in patients treated with anti-PD-1 therapy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed two independent NSCLC cohorts: MSK (n=182, training) and CGFL (n=108, validation). Tumor regions were manually annotated, tiled, stain-normalized, and processed through the UNI foundation model to extract deep features. Clustering of tiles from 10 extreme-outcome MSK cases identified histology-based subgroups. These were then applied to the remaining patients by projection and majority voting. Associations with progression-free survival (PFS) and overall survival (OS) were assessed. DL groups were integrated with clinical covariates in a multivariate model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Clustering revealed two distinct DL-defined groups (DL\n                      <jats:sup>High<\/jats:sup>\n                      vs. DL\n                      <jats:sup>Low<\/jats:sup>\n                      ). In the MSK cohort, DL\n                      <jats:sup>High<\/jats:sup>\n                      patients had significantly longer PFS than DL\n                      <jats:sup>Low<\/jats:sup>\n                      (median 5.7 vs. 2.5 months; HR = 0.63, 95% CI 0.44\u20130.89; p=0.01). This prognostic value was independently confirmed in the CGFL cohort (median PFS 15.2 vs. 6.2 months; HR = 0.59, 95% CI 0.36\u20130.96; p=0.03). OS was numerically higher in DL\n                      <jats:sup>High<\/jats:sup>\n                      patients but did not reach significance. DL classification correlated with higher PD-L1 tumor proportion score (TPS). Discordance between DL and TPS was observed, and the DL model further stratified outcomes among patients with TPS \u226550%. A combined model integrating DL groups with clinical variables improved prediction of PFS compared to clinical features alone (HR = 0.50, 95% CI 0.33\u20130.75; p&amp;lt;0.001 in MSK; HR = 0.54, 95% CI 0.31\u20130.91; p=0.02 in CGFL).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning applied to PD-L1 IHC slides identifies reproducible histomorphological patterns associated with outcomes in anti-PD-1\u2013treated NSCLC patients. This approach provides prognostic information beyond conventional PD-L1 scoring and enhances predictive accuracy when combined with clinical factors.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1750816","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:38:28Z","timestamp":1770964708000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning-based assessment of PD-L1 expression in NSCLC predicts outcome for patients treated with anti-PD-1 immunotherapy"],"prefix":"10.3389","volume":"17","author":[{"given":"Morgane","family":"Peroz","sequence":"first","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Roussot","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]},{"name":"Department of Medical Oncology, Centre Georges-Fran\u00e7ois Leclerc","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alis","family":"Ilie","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rageot","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valentin","family":"Derangere","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]},{"name":"Genetic and Immunology Medical Institute","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Truntzer","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]},{"name":"Genetic and Immunology Medical Institute","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Ghiringhelli","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Bourgogne Europe, Centre Georges-Fran\u00e7ois Leclerc, Unicancer, Cancer Biology Transfer Platform, UMR INSERM 1231, Therapies and Immune Response in Cancers (TIRECs) team","place":["Dijon, France"]},{"name":"Department of Medical Oncology, Centre Georges-Fran\u00e7ois Leclerc","place":["Dijon, France"]},{"name":"Genetic and Immunology Medical Institute","place":["Dijon, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1504627","article-title":"Nivolumab versus docetaxel in advanced squamous-cell non\u2013small-cell lung cancer","volume":"373","author":"Brahmer","year":"2015","journal-title":"New Engl J Med"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1507643","article-title":"Nivolumab versus docetaxel in advanced nonsquamous non\u2013small-cell lung cancer","volume":"373","author":"Borghaei","year":"2015","journal-title":"New Engl J Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(15)01281-7","article-title":"Pembrolizumab versus docetaxel for previously treated, PD-L1-positive, advanced non-small-cell lung cancer (KEYNOTE-010): a randomised controlled trial","volume":"387","author":"Herbst","year":"2016","journal-title":"Lancet"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)32409-7","article-title":"Pembrolizumab versus chemotherapy for previously untreated, PD-L1-expressing, locally advanced or metastatic non-small-cell lung cancer (KEYNOTE-042): a randomised, open-label, controlled, phase 3 trial","volume":"393","author":"Mok","year":"2019","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2022.12.013","article-title":"Non-oncogene-addicted metastatic non-small-cell lung cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up","volume":"34","author":"Hendriks","year":"2023","journal-title":"Ann Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801005","article-title":"Pembrolizumab plus chemotherapy in metastatic non\u2013small-cell lung cancer","volume":"378","author":"Gandhi","year":"2018","journal-title":"New Engl J Med"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-023-00794-7","article-title":"Immune-checkpoint inhibition for resectable non-small-cell lung cancer - opportunities and challenges","volume":"20","author":"Mountzios","year":"2023","journal-title":"Nat Rev Clin Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2016.11.2228","article-title":"PD-L1 immunohistochemistry assays for lung cancer: results from phase 1 of the blueprint PD-L1 IHC assay comparison project","volume":"12","author":"Hirsch","year":"2017","journal-title":"J Thorac Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1606774","article-title":"Pembrolizumab versus chemotherapy for PD-L1\u2013positive non\u2013small-cell lung cancer","volume":"375","author":"Reck","year":"2016","journal-title":"N Engl J Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2017.74.7642","article-title":"Programmed death-ligand 1 immunohistochemistry testing: A review of analytical assays and clinical implementation in non-small-cell lung cancer","volume":"35","author":"B\u00fcttner","year":"2017","journal-title":"J Clin Oncol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1001\/jamaoncol.2015.3638","article-title":"Quantitative assessment of the heterogeneity of PD-L1 expression in non\u2013small-cell lung cancer","volume":"2","author":"McLaughlin","year":"2016","journal-title":"JAMA Oncol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1038\/s41379-021-00919-2","article-title":"Digital pathology and artificial intelligence in translational medicine and clinical practice","volume":"35","author":"Baxi","year":"2022","journal-title":"Mod Pathol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0177-5","article-title":"Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning","volume":"24","author":"Coudray","year":"2018","journal-title":"Nat Med"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1111\/his.14571","article-title":"Development and validation of a supervised deep learning algorithm for automated whole-slide programmed death-ligand 1 tumour proportion score assessment in non-small cell lung cancer","volume":"80","author":"Hondelink","year":"2022","journal-title":"Histopathology"},{"key":"B15","doi-asserted-by":"publisher","first-page":"106829","DOI":"10.1016\/j.cmpb.2022.106829","article-title":"A new AI-assisted scoring system for PD-L1 expression in NSCLC","volume":"221","author":"Huang","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-022-00436-4","article-title":"Artificial intelligence in histopathology: enhancing cancer research and clinical oncology","volume":"3","author":"Shmatko","year":"2022","journal-title":"Nat Cancer"},{"key":"B17","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.celrep.2018.03.086","article-title":"Spatial organization and molecular correlation of tumor-infiltrating lymphocytes using deep learning on pathology images","volume":"23","author":"Saltz","year":"2018","journal-title":"Cell Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e011346","DOI":"10.1136\/jitc-2024-011346","article-title":"Artificial intelligence-based digital pathology using H&E-stained whole slide images in immuno-oncology: from immune biomarker detection to immunotherapy response prediction","volume":"13","author":"Zhang","year":"2025","journal-title":"J Immunother Cancer"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-022-00416-8","article-title":"Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer","volume":"3","author":"Vanguri","year":"2022","journal-title":"Nat Cancer"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI.2009.5193250","article-title":"A method for normalizing histology slides for quantitative analysis","author":"Macenko","year":"2009"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2014.55.2208","article-title":"Moving beyond the hazard ratio in quantifying the between-group difference in survival analysis","volume":"32","author":"Uno","year":"2014","journal-title":"J Clin Oncol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13000-025-01707-1","article-title":"Artificial Intelligence-driven image analysis for standardised programmed death-ligand 1 expression evaluation in non-small cell lung cancer","volume":"20","author":"Ge","year":"2025","journal-title":"Diagn Pathol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"6753","DOI":"10.1038\/s41467-022-34275-9","article-title":"Deep learning-based image analysis predicts PD-L1 status from H&E-stained histopathology images in breast cancer","volume":"13","author":"Shamai","year":"2022","journal-title":"Nat Commun"},{"key":"B25","doi-asserted-by":"publisher","first-page":"24","DOI":"10.4103\/jpi.jpi_24_19","article-title":"Multi-field-of-view deep learning model predicts nonsmall cell lung cancer programmed death-ligand 1 status from whole-slide hematoxylin and eosin images","volume":"10","author":"Sha","year":"2019","journal-title":"J Pathol Inform"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtho.2025.07.131","article-title":"Digital versus manual PD-L1 scoring in advanced NSCLC from the IMpower110 and IMpower150 trials","volume":"20","author":"Herbst","year":"2025","journal-title":"J Thorac Oncol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1097\/RCT.0000000000001644","article-title":"Comprehensive potential of artificial intelligence for predicting PD-L1 expression and EGFR mutations in lung cancer: A systematic review and meta-analysis","volume":"49","author":"Wu","year":"2025","journal-title":"J Comput Assist Tomogr"},{"key":"B28","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1111\/his.15432","article-title":"Comparative performance of PD-L1 scoring by pathologists and AI algorithms","volume":"87","author":"Plass","year":"2025","journal-title":"Histopathology"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e2300556","DOI":"10.1200\/PO.23.00556","article-title":"Clinical validation of artificial intelligence\u2013powered PD-L1 tumor proportion score interpretation for immune checkpoint inhibitor response prediction in non\u2013small cell lung cancer","author":"Kim","year":"2024","journal-title":"JCO Precis Oncol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1136\/jcp-2024-209766","article-title":"Assessment of PD-L1 expression and tumour infiltrating lymphocytes in early-stage non-small cell lung carcinoma with artificial intelligence algorithms","volume":"78","author":"Molero","year":"2025","journal-title":"J Clin Pathol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2024.5356","article-title":"Deep learning model for predicting immunotherapy response in advanced non\u2013small cell lung cancer","volume":"11","author":"Rakaee","year":"2025","journal-title":"JAMA Oncol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"037502","DOI":"10.1117\/1.JMI.11.3.037502","article-title":"WhARIO: whole-slide-image-based survival analysis for patients treated with immunotherapy","volume":"11","author":"Tourniaire","year":"2024","journal-title":"JMI"},{"key":"B33","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1038\/s41467-025-55847-5","article-title":"Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer","volume":"16","author":"Captier","year":"2025","journal-title":"Nat Commun"},{"key":"B34","doi-asserted-by":"publisher","first-page":"29585","DOI":"10.1038\/s41598-024-81383-1","article-title":"Deciphering cell to cell spatial relationship for pathology images using SpatialQPFs","volume":"14","author":"Li","year":"2024","journal-title":"Sci Rep"},{"key":"B35","doi-asserted-by":"publisher","first-page":"112765","DOI":"10.1016\/j.isci.2025.112765","article-title":"Entropy measures for quantifying complexity in digital pathology and spatial omics","volume":"28","author":"Li","year":"2025","journal-title":"iScience"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1750816\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:38:28Z","timestamp":1770964708000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1750816\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":35,"alternative-id":["10.3389\/fimmu.2026.1750816"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1750816","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"article-number":"1750816"}}