{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T22:39:31Z","timestamp":1790203171545,"version":"4.1.0"},"reference-count":35,"publisher":"American Medical Association (AMA)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Oncol"],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"\n Importance<\/jats:title>\n Easy and accessible biomarkers associated with response to immune checkpoint inhibition (ICI)\u2013treated melanoma are limited.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n To evaluate artificial intelligence (AI)\u2013detected tumor-infiltrating lymphocytes (TILs) on pretreatment melanoma metastases as a biomarker for response and survival in patients treated with ICIs.<\/jats:p>\n <\/jats:sec>\n \n Design, Setting, and Participants<\/jats:title>\n This multicenter cohort study included patients with advanced melanoma treated with first-line anti\u2013programmed cell death 1 protein (PD-1) with or without anti\u2013cytotoxic T-lymphocyte\u2013associated protein 4 (CTLA-4) between January 2016 and January 2023 at 11 melanoma treatment centers in the Netherlands. Data were analyzed from January to July 2025.<\/jats:p>\n <\/jats:sec>\n \n Exposure<\/jats:title>\n All patients received first-line anti\u2013PD-1 with or without anti\u2013CTLA-4.<\/jats:p>\n <\/jats:sec>\n \n Main Outcomes and Measures<\/jats:title>\n \n The percentage of TILs inside manually annotated tumor area in hematoxylin-eosin\u2013stained pretreatment metastases was determined using the Hover-NeXt model trained and evaluated on an independent melanoma dataset containing 161\u202f835 pathologist-verified manually annotated cells. The primary outcome was objective response rate (ORR); secondary outcomes were progression-free survival (PFS) and overall survival (OS). Correlation with manual TILs, scored according to the guidelines stated by the Immuno-Oncology Biomarkers Working Group, was evaluated with Spearman correlation coefficients. Logistic regression and Cox proportional regression were conducted, adjusted for age, sex, disease stage, ICI type,\n BRAF<\/jats:italic>\n status, brain metastases, lactate dehydrogenase level, and performance status.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Of 1202 included patients with advanced cutaneous melanoma, 445 (37.0%) were female and 757 (63.0%) were male, and the median (IQR) age was 67.0 (57.0-74.0) years. The median follow-up was 36.3 months (95% CI, 34.0-39.1). Metastatic melanoma specimens were available for 1202 patients, of whom 423 received combination therapy. The median (range) TIL percentage was 9.9% (0.3%-69.4%). A 10% increase in TILs was associated with increased ORR (adjusted odds ratio, 1.40; 95% CI, 1.23-1.59), PFS (adjusted hazard ratio, 0.85; 95% CI, 0.79-0.92), and OS (adjusted hazard ratio, 0.83; 95% CI, 0.76-0.91). Results were consistent for both patients treated with anti\u2013PD-1 monotherapy and patients treated with combination treatment with anti\u2013PD-1 plus anti\u2013CTLA-4. When comparing manual TIL scoring with AI-detected TILs, associations with response and survival were consistently stronger for AI-detected TILs.<\/jats:p>\n <\/jats:sec>\n \n Conclusions and Relevance<\/jats:title>\n In this cohort study, among patients with advanced melanoma, higher levels of AI-detected TILs on pretreatment hematoxylin-eosin slides were independently associated with improved ICI response and survival. Given the accessibility of TIL scoring on routine histology, TILs may serve as a biomarker for ICI outcomes. To facilitate broader validation, the Hover-NeXt architecture and model weights are publicly available.<\/jats:p>\n <\/jats:sec>","DOI":"10.1001\/jamaoncol.2025.4072","type":"journal-article","created":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T15:00:48Z","timestamp":1760626848000},"page":"1470","source":"Crossref","is-referenced-by-count":10,"title":["Artificial Intelligence\u2013Detected Tumor-Infiltrating Lymphocytes and Outcomes in Anti\u2013PD-1\u2013Based Treated Melanoma"],"prefix":"10.1001","volume":"11","author":[{"given":"Mark","family":"Schuiveling","sequence":"first","affiliation":[{"name":"Department of Medical Oncology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabella A. J.","family":"van Duin","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurens S.","family":"ter Maat","sequence":"additional","affiliation":[{"name":"Image Sciences Institute, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janneke C.","family":"van der Weerd","sequence":"additional","affiliation":[{"name":"Department of Pathology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rik J.","family":"Verheijden","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franchette","family":"van den Berkmortel","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Zuyderland Medical Center Sittard, Sittard-Geleen, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian U.","family":"Blank","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerben E.","family":"Breimer","sequence":"additional","affiliation":[{"name":"Department of Pathology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Femke H.","family":"Burgers","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marye","family":"Boers-Sonderen","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Radboud University Medical Center, Nijmegen, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfons J. M.","family":"van den Eertwegh","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Amsterdam UMC, VU University Medical Center, Cancer Center Amsterdam, Amsterdam, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan Willem B.","family":"de Groot","sequence":"additional","affiliation":[{"name":"Isala Oncology Center, Isala Hospital, Zwolle, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John B. A. G.","family":"Haanen","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, the Netherlands"},{"name":"Department of Medical Oncology, Leiden University Medical Center, Leiden, the Netherlands"},{"name":"Division of Molecular Oncology and Immunology, Oncode Institute, Amsterdam, the Netherlands"},{"name":"Melanoma Clinic, Centre Hospitalier Universitaire Vaudois, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geke A. P.","family":"Hospers","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellen","family":"Kapiteijn","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Leiden University Medical Center, Leiden, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Djura","family":"Piersma","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Medisch Spectrum Twente, Enschede, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerard","family":"Vreugdenhil","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Maxima Medical Center, Eindhoven, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans","family":"Westgeest","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Amphia Hospital, Breda, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne M. R.","family":"Schrader","sequence":"additional","affiliation":[{"name":"Department of Pathology, Leiden University Medical Center, Leiden, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josien P. W.","family":"Pluim","sequence":"additional","affiliation":[{"name":"Medical Image Analysis, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul J.","family":"van Diest","sequence":"additional","affiliation":[{"name":"Department of Pathology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitko","family":"Veta","sequence":"additional","affiliation":[{"name":"Medical Image Analysis, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karijn P. M.","family":"Suijkerbuijk","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Willeke A. M.","family":"Blokx","sequence":"additional","affiliation":[{"name":"Department of Pathology, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","reference":[{"issue":"1","key":"coi250063r1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1056\/NEJMoa2407417","article-title":"Final, 10-year outcomes with nivolumab plus ipilimumab in advanced melanoma.","volume":"392","author":"Wolchok","year":"2025","journal-title":"N Engl J Med"},{"key":"coi250063r2","doi-asserted-by":"publisher","DOI":"10.1200\/PO.22.00018","article-title":"BRAF and NRAS mutation status and response to checkpoint inhibition in advanced melanoma.","volume":"6","author":"van Not","year":"2022","journal-title":"JCO Precis Oncol"},{"issue":"4","key":"coi250063r3","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1038\/s43018-024-00730-3","article-title":"Clinical and translational attributes of immune-related adverse events.","volume":"5","author":"Suijkerbuijk","year":"2024","journal-title":"Nat Cancer"},{"issue":"6","key":"coi250063r4","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2021.100320","article-title":"Trends in survival and costs in metastatic melanoma in the era of novel targeted and immunotherapeutic drugs.","volume":"6","author":"Franken","year":"2021","journal-title":"ESMO Open"},{"key":"coi250063r5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2024.115071","article-title":"Cost-effectiveness of treatment sequences for BRAF-mutant advanced melanoma in the Netherlands using a health economic model.","volume":"218","author":"Blommestein","year":"2025","journal-title":"Eur J Cancer"},{"issue":"6","key":"coi250063r6","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1097\/PAP.0000000000000161","article-title":"Assessing tumor-infiltrating lymphocytes in solid tumors: a practical review for pathologists and proposal for a standardized method from the International Immuno-Oncology Biomarkers Working Group: part 2: TILs in melanoma, gastrointestinal tract carcinomas, non-small cell lung carcinoma and mesothelioma, endometrial and ovarian carcinomas, squamous cell carcinoma of the head and neck, genitourinary carcinomas, and primary brain tumors.","volume":"24","author":"Hendry","year":"2017","journal-title":"Adv Anat Pathol"},{"key":"coi250063r7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2024.114190","article-title":"Baseline tumor-infiltrating lymphocyte patterns and response to immune checkpoint inhibition in metastatic cutaneous melanoma.","volume":"208","author":"van Duin","year":"2024","journal-title":"Eur J Cancer"},{"issue":"7","key":"coi250063r8","doi-asserted-by":"publisher","first-page":"2242","DOI":"10.1245\/s10434-016-5173-8","article-title":"Interobserver agreement between pathologists assessing tumor-infiltrating lymphocytes (TILs) in breast cancer using methodology proposed by the International TILs Working Group.","volume":"23","author":"Swisher","year":"2016","journal-title":"Ann Surg Oncol"},{"issue":"3","key":"coi250063r9","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1038\/s41571-024-00984-x","article-title":"Biological and clinical significance of tumour-infiltrating lymphocytes in the era of immunotherapy: a multidimensional approach.","volume":"22","author":"Lopez de Rodas","year":"2025","journal-title":"Nat Rev Clin Oncol"},{"issue":"17","key":"coi250063r10","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.1200\/JCO.21.02010","article-title":"Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes as complementary biomarker for immune checkpoint inhibition in non-small-cell lung cancer.","volume":"40","author":"Park","year":"2022","journal-title":"J Clin Oncol"},{"issue":"7","key":"coi250063r12","doi-asserted-by":"publisher","DOI":"10.1200\/PO.22.00317","article-title":"Association between biomarkers and clinical outcomes of pembrolizumab monotherapy in patients with metastatic triple-negative breast cancer: KEYNOTE-086 exploratory analysis.","volume":"7","author":"Loi","year":"2023","journal-title":"JCO Precis Oncol"},{"key":"coi250063r13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2023.104644","article-title":"Deep learning-based scoring of tumour-infiltrating lymphocytes is prognostic in primary melanoma and predictive to PD-1 checkpoint inhibition in melanoma metastases.","volume":"93","author":"Chatziioannou","year":"2023","journal-title":"EBioMedicine"},{"issue":"2","key":"coi250063r14","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2023-008339","article-title":"Inflamed immune phenotype predicts favorable clinical outcomes of immune checkpoint inhibitor therapy across multiple cancer types.","volume":"12","author":"Shen","year":"2024","journal-title":"J Immunother Cancer"},{"issue":"1","key":"coi250063r15","doi-asserted-by":"publisher","first-page":"5440","DOI":"10.1038\/s41467-019-13043-2","article-title":"An open source automated tumor infiltrating lymphocyte algorithm for prognosis in melanoma.","volume":"10","author":"Acs","year":"2019","journal-title":"Nat Commun"},{"key":"coi250063r16","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giaf011","article-title":"A novel dataset for nuclei and tissue segmentation in melanoma with baseline nuclei segmentation and tissue segmentation benchmarks.","volume":"14","author":"Schuiveling","year":"2025","journal-title":"Gigascience"},{"key":"coi250063r19","first-page":"61","article-title":"HoVer-NeXt: a fast nuclei segmentation and classification pipeline for next generation histopathology.","volume":"250","author":"Baumann","year":"2024","journal-title":"Proc 7th Int Conference Med Imaging Deep Learning"},{"key":"coi250063r20","article-title":"Panoptic segmentation with highly imbalanced semantic labels.","author":"Rumberger","journal-title":"2022 IEEE Int Symp Biomed Imaging Challenges"},{"key":"coi250063r21","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.ejca.2016.11.021","article-title":"Dutch Melanoma Treatment Registry: quality assurance in the care of patients with metastatic melanoma in the Netherlands.","volume":"72","author":"Jochems","year":"2017","journal-title":"Eur J Cancer"},{"issue":"6","key":"coi250063r22","doi-asserted-by":"publisher","first-page":"472","DOI":"10.3322\/caac.21409","article-title":"Melanoma staging: evidence-based changes in the American Joint Committee on Cancer eighth edition cancer staging manual.","volume":"67","author":"Gershenwald","year":"2017","journal-title":"CA Cancer J Clin"},{"issue":"5","key":"coi250063r24","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1002\/path.6155","article-title":"Pitfalls in machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer: a report of the International Immuno-Oncology Biomarker Working Group on Breast Cancer.","volume":"260","author":"Thagaard","year":"2023","journal-title":"J Pathol"},{"issue":"1","key":"coi250063r25","doi-asserted-by":"publisher","first-page":"16878","DOI":"10.1038\/s41598-017-17204-5","article-title":"QuPath: open source software for digital pathology image analysis.","volume":"7","author":"Bankhead","year":"2017","journal-title":"Sci Rep"},{"issue":"1","key":"coi250063r26","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1155\/2007\/971816","article-title":"Pathology databanking and biobanking in the Netherlands, a central role for PALGA, the nationwide histopathology and cytopathology data network and archive.","volume":"29","author":"Casparie","year":"2007","journal-title":"Cell Oncol"},{"issue":"2","key":"coi250063r27","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.ejca.2008.10.026","article-title":"New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1).","volume":"45","author":"Eisenhauer","year":"2009","journal-title":"Eur J Cancer"},{"issue":"1","key":"coi250063r28","doi-asserted-by":"publisher","DOI":"10.1080\/2162402X.2019.1659093","article-title":"Close proximity of immune and tumor cells underlies response to anti-PD-1 based therapies in metastatic melanoma patients.","volume":"9","author":"Gide","year":"2019","journal-title":"Oncoimmunology"},{"issue":"7528","key":"coi250063r29","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1038\/nature13954","article-title":"PD-1 blockade induces responses by inhibiting adaptive immune resistance.","volume":"515","author":"Tumeh","year":"2014","journal-title":"Nature"},{"issue":"3","key":"coi250063r30","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1111\/pcmr.12340","article-title":"PD-L1 expression in melanoma shows marked heterogeneity within and between patients: implications for anti-PD-1\/PD-L1 clinical trials.","volume":"28","author":"Madore","year":"2015","journal-title":"Pigment Cell Melanoma Res"},{"issue":"7","key":"coi250063r31","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1038\/s41591-020-0900-x","article-title":"Geospatial immune variability illuminates differential evolution of lung adenocarcinoma.","volume":"26","author":"AbdulJabbar","year":"2020","journal-title":"Nat Med"},{"issue":"3","key":"coi250063r33","doi-asserted-by":"publisher","first-page":"850","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"},{"issue":"9","key":"coi250063r34","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1056\/NEJMoa2211437","article-title":"Neoadjuvant-adjuvant or adjuvant-only pembrolizumab in advanced melanoma.","volume":"388","author":"Patel","year":"2023","journal-title":"N Engl J Med"},{"issue":"18","key":"coi250063r35","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1056\/NEJMoa2402604","article-title":"Neoadjuvant nivolumab and ipilimumab in resectable stage III melanoma.","volume":"391","author":"Blank","year":"2024","journal-title":"N Engl J Med"},{"key":"coi250063r11","doi-asserted-by":"crossref","unstructured":"Amgad? M, Salgado? R, Cooper? LAD. MuTILs: a multiresolution deep-learning model for interpretable scoring of tumor-infiltrating lymphocytes in breast carcinomas using clinical guidelines.? medRxiv. Preprint posted online May 15, 2023. doi:10.1101\/2022.01.08.22268814","DOI":"10.1101\/2022.01.08.22268814"},{"key":"coi250063r17","unstructured":"Schuiveling? M. Data from: Melanoma histopathology dataset with tissue and nuclei annotations. Deposited March 19, 2025. https:\/\/zenodo.org\/records\/15050523"},{"key":"coi250063r18","unstructured":"Schuiveling? M. Data from: Inference code for HoVer-NeXt for quantifiyng TILs in melanoma. Deposited May 27, 2025. https:\/\/github.com\/mschuiveling\/hover-next-inference-tils-melanoma"},{"key":"coi250063r23","unstructured":"Bankhead? P. Data from: QuPath v0.5.0. Deposited December 1, 2023. https:\/\/github.com\/qupath\/qupath\/releases\/tag\/v0.5.0"},{"key":"coi250063r32","unstructured":"Zimmermann? E, Vorontsov? E, Viret? J, . Virchow2: scaling self-supervised mixed magnification models in pathology.? arXiv. Preprint posted online November 6, 2024. doi:10.48550\/arXiv.2408.00738"}],"container-title":["JAMA Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamaoncology\/articlepdf\/2840003\/jamaoncology_schuiveling_2025_oi_250063_1774976340.71194.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:00:12Z","timestamp":1775142012000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamaoncology\/fullarticle\/2840003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":35,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamaoncol.2025.4072","relation":{},"ISSN":["2374-2437"],"issn-type":[{"value":"2374-2437","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}