{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T19:34:46Z","timestamp":1794080086970,"version":"4.8.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate prognostication is essential to guide clinical management in localised cutaneous melanoma (CM), the form of skin cancer with the highest mortality. While the tumour microenvironment (TME) plays a key role in disease progression, current staging systems rely on limited tumour features and exclude key clinicopathological prognostic features. Here we show that MelanoMAP, a multimodal AI model integrating TME-derived digital biomarkers and clinicopathological features from over 3,500 histology slides, improves prognostication of localised CM. MelanoMAP achieved a C-index of 0.82, a 24% improvement over traditional AJCC staging (0.66) and consistently outperformed clinicopathological-only models across six international patient cohorts. SHAP analysis identified TME-derived digital biomarkers, alongside traditional clinicopathological factors including age, mitotic count, and Breslow depth, were critical determinants of metastatic risk. MelanoMAP establishes a potential foundation for precision oncology in CM, demonstrating how AI-driven digital biomarkers can advance personalised prognostication and inform clinical-decision making.<\/jats:p>","DOI":"10.1038\/s41467-025-65051-0","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:55:01Z","timestamp":1763470501000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Multimodal AI and tumour microenvironment integration predicts metastasis in cutaneous melanoma"],"prefix":"10.1038","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2297-0003","authenticated-orcid":false,"given":"Tom W.","family":"Andrew","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marc","family":"Combalia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1849-5921","authenticated-orcid":false,"given":"Sydney","family":"Grant","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6612-9267","authenticated-orcid":false,"given":"Gyorgy","family":"Paragh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1337-9745","authenticated-orcid":false,"given":"Susanna","family":"Puig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8908-6071","authenticated-orcid":false,"given":"Grant","family":"Mc Arthur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grant","family":"Richardson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phil","family":"Sloan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2783-5265","authenticated-orcid":false,"given":"Sophia Z.","family":"Shalhout","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0107-1444","authenticated-orcid":false,"given":"Ruth","family":"Plummer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penny E.","family":"Lovat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"65051_CR1","unstructured":"American Cancer Society. Key statistics for melanoma skin cancer. https:\/\/www.cancer.org\/cancer\/types\/melanoma-skin-cancer\/about\/key-statistics.html (accessed June 2024)."},{"key":"65051_CR2","unstructured":"Cancer Research UK. Melanoma skin cancer statistics: incidence, survival, and mortality. https:\/\/www.cancerresearchuk.org\/health-professional\/cancer-statistics\/statistics-by-cancer-type\/melanoma-skin-cancer (accessed June 2024)."},{"key":"65051_CR3","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1016\/j.jaad.2016.10.018","volume":"76","author":"SM Landow","year":"2017","unstructured":"Landow, S. M., Gjelsvik, A. & Weinstock, M. A. Mortality burden and prognosis of thin melanomas overall and by subcategory of thickness, SEER registry data, 1992\u20132013. J. Am. Acad. Dermatol. 76, 258\u2013263 (2017).","journal-title":"J. Am. Acad. Dermatol."},{"key":"65051_CR4","first-page":"472","volume":"67","author":"JE Gershenwald","year":"2017","unstructured":"Gershenwald, J. E. et al. Melanoma staging: evidence-based changes in the American Joint Committee on Cancer eighth edition cancer staging manual. CA Cancer J. Clin. 67, 472\u2013492 (2017).","journal-title":"CA Cancer J. Clin."},{"key":"65051_CR5","doi-asserted-by":"publisher","first-page":"202","DOI":"10.3389\/fonc.2020.00851","volume":"10","author":"M Neagu","year":"2020","unstructured":"Neagu, M. Metabolic traits in cutaneous melanoma. Front. Oncol. 10, 202 (2020).","journal-title":"Front. Oncol."},{"key":"65051_CR6","first-page":"598655","volume":"9","author":"ST Zhou","year":"2021","unstructured":"Zhou, S. T. et al. The landscape of the tumor microenvironment in skin cutaneous melanoma reveals a prognostic and immunotherapeutically relevant gene signature. Front. Cell Dev. Biol. 9, 598655 (2021).","journal-title":"Front. Cell Dev. Biol."},{"key":"65051_CR7","doi-asserted-by":"publisher","first-page":"7259","DOI":"10.1007\/s00432-023-04680-8","volume":"149","author":"JP Li","year":"2023","unstructured":"Li, J. P. et al. The evaluation of tumor microenvironment infiltration and the identification of angiogenesis-related subgroups in skin cutaneous melanoma. J. Cancer Res. Clin. Oncol. 149, 7259\u20137273 (2023).","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"65051_CR8","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s10020-023-00665-y","volume":"29","author":"ZW Peng","year":"2023","unstructured":"Peng, Z. W., Tong, Z. W., Ren, Z. H., Ye, M. P. & Hu, K. W. Cancer-associated fibroblasts and their derived exosomes: a new perspective for reshaping the tumor microenvironment. Mol. Med. 29, 99 (2023).","journal-title":"Mol. Med."},{"key":"65051_CR9","doi-asserted-by":"publisher","DOI":"10.1186\/s12943-022-01682-x","volume":"21","author":"P Nallasamy","year":"2022","unstructured":"Nallasamy, P. et al. Tumor microenvironment enriches the stemness features: the architectural event of therapy resistance and metastasis. Mol. Cancer 21, 211 (2022).","journal-title":"Mol. Cancer"},{"key":"65051_CR10","first-page":"649609","volume":"9","author":"PJ Wu","year":"2021","unstructured":"Wu, P. J. et al. Adaptive mechanisms of tumor therapy resistance driven by tumor microenvironment. Front. Cell Dev. Biol. 9, 649609 (2021).","journal-title":"Front. Cell Dev. Biol."},{"key":"65051_CR11","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17678-4","volume":"11","author":"B Schmauch","year":"2020","unstructured":"Schmauch, B. et al. A deep learning model to predict RNA-seq expression of tumours from whole slide images. Nat. Commun. 11, 3877 (2020).","journal-title":"Nat. Commun."},{"key":"65051_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-55659-z","volume":"16","author":"A Fathi Kazerooni","year":"2025","unstructured":"Fathi Kazerooni, A. et al. Multiparametric MRI along with machine learning predicts prognosis and treatment response in pediatric low-grade glioma. Nat. Commun. 16, 340 (2025).","journal-title":"Nat. Commun."},{"key":"65051_CR13","doi-asserted-by":"publisher","first-page":"5290","DOI":"10.1109\/JBHI.2024.3418341","volume":"28","author":"RK Mondol","year":"2024","unstructured":"Mondol, R. K., Millar, E. K. A., Sowmya, A. & Meijering, E. BioFusionNet: deep learning-based survival risk stratification in ER+ breast cancer through multifeature and multimodal data fusion. IEEE J. Biomed. Health Inform. 28, 5290\u20135302 (2024).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"65051_CR14","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1111\/phpp.12770","volume":"38","author":"L Ding","year":"2022","unstructured":"Ding, L. et al. Prognostic biomarkers of cutaneous melanoma. Photodermatol. Photoimmunol. Photomed. 38, 418\u2013434 (2022).","journal-title":"Photodermatol. Photoimmunol. Photomed."},{"key":"65051_CR15","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.3390\/cancers14246231","volume":"14","author":"SR Grant","year":"2022","unstructured":"Grant, S. R., Andrew, T. W., Alvarez, E. V., Huss, W. J. & Paragh, G. Diagnostic and prognostic deep learning applications for histological assessment of cutaneous melanoma. Cancers 14, 2687 (2022).","journal-title":"Cancers"},{"key":"65051_CR16","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.ccell.2023.02.016","volume":"41","author":"KE de Visser","year":"2023","unstructured":"de Visser, K. E. & Joyce, J. A. The evolving tumor microenvironment from cancer initiation to metastatic outgrowth. Cancer Cell 41, 374\u2013403 (2023).","journal-title":"Cancer Cell"},{"key":"65051_CR17","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.1158\/1078-0432.CCR-19-1495","volume":"26","author":"PM Kulkarni","year":"2020","unstructured":"Kulkarni, P. M. et al. Deep learning based on standard H&E images of primary melanoma tumors identifies patients at risk for visceral recurrence and death. Clin. Cancer Res. 26, 1126\u20131134 (2020).","journal-title":"Clin. Cancer Res."},{"key":"65051_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-24315-1","volume":"12","author":"MC Comes","year":"2022","unstructured":"Comes, M. C. et al. A deep learning model based on whole slide images to predict disease-free survival in cutaneous melanoma patients. Sci. Rep. 12, 20366 (2022).","journal-title":"Sci. Rep."},{"key":"65051_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-31526-7","volume":"13","author":"EL Clarke","year":"2023","unstructured":"Clarke, E. L., Wade, R. G., Magee, D., Newton-Bishop, J. & Treanor, D. Image analysis of cutaneous melanoma histology: a systematic review and meta-analysis. Sci. Rep. 13, 4774 (2023).","journal-title":"Sci. Rep."},{"key":"65051_CR20","doi-asserted-by":"publisher","first-page":"e330","DOI":"10.1016\/S2589-7500(22)00021-8","volume":"4","author":"M Combalia","year":"2022","unstructured":"Combalia, M. et al. Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge. Lancet Digit. Health 4, e330\u2013e339 (2022).","journal-title":"Lancet Digit. Health"},{"key":"65051_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-024-03387-w","volume":"11","author":"C Hern\u00e1ndez-P\u00e9rez","year":"2024","unstructured":"Hern\u00e1ndez-P\u00e9rez, C. et al. BCN20000: dermoscopic lesions in the wild. Sci. Data 11, 123 (2024).","journal-title":"Sci. Data"},{"key":"65051_CR22","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.ejca.2021.05.026","volume":"154","author":"TJ Brinker","year":"2021","unstructured":"Brinker, T. J. et al. Deep learning approach to predict sentinel lymph node status directly from routine histology of primary melanoma tumours. Eur. J. Cancer 154, 227\u2013234 (2021).","journal-title":"Eur. J. Cancer"},{"key":"65051_CR23","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41746-021-00427-2","volume":"4","author":"E Wulczyn","year":"2021","unstructured":"Wulczyn, E. et al. Interpretable survival prediction for colorectal cancer using deep learning. NPJ Digit. Med. 4, 71 (2021).","journal-title":"NPJ Digit. Med."},{"key":"65051_CR24","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1111\/bjd.20889","volume":"186","author":"I Cosgarea","year":"2022","unstructured":"Cosgarea, I. et al. Melanoma secretion of transforming growth factor-\u03b22 leads to loss of epidermal AMBRA1 threatening epidermal integrity and facilitating tumour ulceration. Br. J. Dermatol. 186, 694\u2013704 (2022).","journal-title":"Br. J. Dermatol."},{"key":"65051_CR25","doi-asserted-by":"publisher","first-page":"3961","DOI":"10.1245\/s10434-013-3100-9","volume":"20","author":"CM Balch","year":"2013","unstructured":"Balch, C. M. et al. Age as a prognostic factor in patients with localized melanoma and regional metastases. Ann. Surg. Oncol. 20, 3961\u20133968 (2013).","journal-title":"Ann. Surg. Oncol."},{"key":"65051_CR26","doi-asserted-by":"publisher","first-page":"3622","DOI":"10.1200\/JCO.2001.19.16.3622","volume":"19","author":"CM Balch","year":"2001","unstructured":"Balch, C. M. et al. Prognostic factors analysis of 17,600 melanoma patients: validation of the American Joint Committee on Cancer melanoma staging system. J. Clin. Oncol. 19, 3622\u20133634 (2001).","journal-title":"J. Clin. Oncol."},{"key":"65051_CR27","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1200\/JCO.2010.31.5812","volume":"29","author":"JF Thompson","year":"2011","unstructured":"Thompson, J. F. et al. Prognostic significance of mitotic rate in localized primary cutaneous melanoma: an analysis of patients in the multi-institutional American Joint Committee on Cancer melanoma staging database. J. Clin. Oncol. 29, 2199\u20132205 (2011).","journal-title":"J. Clin. Oncol."},{"key":"65051_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0302309","volume":"19","author":"A Buja","year":"2024","unstructured":"Buja, A. et al. Could the mitotic count improve personalized prognosis in melanoma patients?. PLoS One 19, e0310667 (2024).","journal-title":"PLoS One"},{"key":"65051_CR29","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1158\/2159-8290.CD-21-1059","volume":"12","author":"D Hanahan","year":"2022","unstructured":"Hanahan, D. Hallmarks of cancer: new dimensions. Cancer Discov. 12, 31\u201346 (2022).","journal-title":"Cancer Discov."},{"key":"65051_CR30","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21896-9","volume":"12","author":"JA Diao","year":"2021","unstructured":"Diao, J. A. et al. Human-interpretable image features derived from densely mapped cancer pathology slides predict diverse molecular phenotypes. Nat. Commun. 12, 1613 (2021).","journal-title":"Nat. Commun."},{"key":"65051_CR31","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2, 56\u201367 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"65051_CR32","doi-asserted-by":"crossref","unstructured":"Carse J., Olmo A. A. & McKenna S. Calibration of deep medical image classifiers: an empirical comparison using dermatology and histopathology datasets. In Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, Vol. 13563, 89\u201399 (Springer, 2022).","DOI":"10.1007\/978-3-031-16749-2_9"},{"key":"65051_CR33","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1245\/s10434-012-2475-3","volume":"19","author":"SL Wong","year":"2012","unstructured":"Wong, S. L. et al. Sentinel lymph node biopsy for melanoma: American Society of Clinical Oncology and Society of Surgical Oncology joint clinical practice guideline. Ann. Surg. Oncol. 19, 3313\u20133324 (2012).","journal-title":"Ann. Surg. Oncol."},{"key":"65051_CR34","unstructured":"National Institute for Health and Care Excellence (NICE). Melanoma: assessment and management. https:\/\/www.nice.org.uk\/guidance\/ng14 (accessed June 2024)."},{"key":"65051_CR35","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1093\/bjd\/ljad459","volume":"190","author":"T Ewen","year":"2024","unstructured":"Ewen, T. et al. Validation of epidermal AMBRA1 and loricrin (AMBLor) as a prognostic biomarker for non-ulcerated American Joint Committee on Cancer stage I\/II cutaneous melanoma. Br. J. Dermatol. 190, 549\u2013558 (2024).","journal-title":"Br. J. Dermatol."},{"key":"65051_CR36","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1038\/ncb3171","volume":"17","author":"V Cianfanelli","year":"2015","unstructured":"Cianfanelli, V. et al. AMBRA1 links autophagy to cell proliferation and tumorigenesis by promoting c-Myc dephosphorylation and degradation. Nat. Cell Biol. 17, 706\u2013716 (2015).","journal-title":"Nat. Cell Biol."},{"key":"65051_CR37","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1038\/nature05925","volume":"447","author":"GM Fimia","year":"2007","unstructured":"Fimia, G. M. et al. Ambra1 regulates autophagy and development of the nervous system. Nature 447, 1121\u20131125 (2007).","journal-title":"Nature"}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-65051-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-65051-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-65051-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T01:03:47Z","timestamp":1763514227000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-025-65051-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["65051"],"URL":"https:\/\/doi.org\/10.1038\/s41467-025-65051-0","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"19 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10095"}}