{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T08:04:12Z","timestamp":1777363452238,"version":"3.51.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T00:00:00Z","timestamp":1679529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004587","name":"Ministry of Economy and Competitiveness | Instituto de Salud Carlos III","doi-asserted-by":"publisher","award":["PI17\/01723 and PI21\/00920"],"award-info":[{"award-number":["PI17\/01723 and PI21\/00920"]}],"id":[{"id":"10.13039\/501100004587","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Predicting recurrence in low-grade, early-stage endometrial cancer (EC) is both challenging and clinically relevant. We present a weakly-supervised deep learning framework, NaroNet, that can learn, without manual expert annotation, the complex tumor-immune interrelations at three levels: local phenotypes, cellular neighborhoods, and tissue areas. It uses multiplexed immunofluorescence for the simultaneous visualization and quantification of CD68\u2009+\u2009macrophages, CD8\u2009+\u2009T cells, FOXP3\u2009+\u2009regulatory T cells, PD-L1\/PD-1 protein expression, and tumor cells. We used 489 tumor cores from 250 patients to train a multilevel deep-learning model to predict tumor recurrence. Using a tenfold cross-validation strategy, our model achieved an area under the curve of 0.90 with a 95% confidence interval of 0.83\u20130.95. Our model predictions resulted in concordance for 96,8% of cases (\u03ba\u2009=\u20090.88). This method could accurately assess the risk of recurrence in EC, outperforming current prognostic factors, including molecular subtyping.<\/jats:p>","DOI":"10.1038\/s41746-023-00795-x","type":"journal-article","created":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T05:03:06Z","timestamp":1679547786000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images"],"prefix":"10.1038","volume":"6","author":[{"given":"Daniel","family":"Jim\u00e9nez-S\u00e1nchez","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5744-3115","authenticated-orcid":false,"given":"\u00c1lvaro","family":"L\u00f3pez-Janeiro","sequence":"additional","affiliation":[]},{"given":"Mar\u00eda","family":"Villalba-Esparza","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7328-1582","authenticated-orcid":false,"given":"Mikel","family":"Ariz","sequence":"additional","affiliation":[]},{"given":"Ece","family":"Kadioglu","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Masetto","sequence":"additional","affiliation":[]},{"given":"Virginie","family":"Goubert","sequence":"additional","affiliation":[]},{"given":"Maria D.","family":"Lozano","sequence":"additional","affiliation":[]},{"given":"Ignacio","family":"Melero","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2183-3699","authenticated-orcid":false,"given":"David","family":"Hardisson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8720-0205","authenticated-orcid":false,"given":"Carlos","family":"Ortiz-de-Sol\u00f3rzano","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7628-8050","authenticated-orcid":false,"given":"Carlos E.","family":"de Andrea","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,23]]},"reference":[{"key":"795_CR1","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1038\/modpathol.2017.156","volume":"31","author":"JM Taube","year":"2018","unstructured":"Taube, J. M. et al. Implications of the tumor immune microenvironment for staging and therapeutics. Mod. Pathol. 31, 214\u2013234 (2018).","journal-title":"Mod. Pathol."},{"key":"795_CR2","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1038\/nrc3245","volume":"12","author":"WH Fridman","year":"2012","unstructured":"Fridman, W. H., Pag\u00e8s, F., Saut\u00e8s-Fridman, C. & Galon, J. The immune contexture in human tumours: impact on clinical outcome. Nat. Rev. Cancer 12, 298\u2013306 (2012).","journal-title":"Nat. Rev. Cancer"},{"key":"795_CR3","doi-asserted-by":"publisher","first-page":"1960","DOI":"10.1126\/science.1129139","volume":"313","author":"J Galon","year":"2006","unstructured":"Galon, J. et al. Type, density, and location of immune cells within human colorectal tumors predict clinical outcome. Science 313, 1960\u20131964 (2006).","journal-title":"Science"},{"key":"795_CR4","doi-asserted-by":"publisher","first-page":"e002197","DOI":"10.1136\/jitc-2020-002197","volume":"9","author":"JM Taube","year":"2021","unstructured":"Taube, J. M. et al. Multi-institutional TSA-amplified multiplexed immunofluorescence reproducibility evaluation (MITRE) study. J. Immunother. Cancer 9, e002197 (2021).","journal-title":"J. Immunother. Cancer"},{"key":"795_CR5","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1038\/s41379-020-0600-6","volume":"33","author":"M Abengozar-Muela","year":"2020","unstructured":"Abengozar-Muela, M. et al. Diverse immune environments in human lung tuberculosis granulomas assessed by quantitative multiplexed immunofluorescence. Mod. Pathol. 33, 2507\u20132519 (2020).","journal-title":"Mod. Pathol."},{"key":"795_CR6","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-017-1311-8","volume":"15","author":"L Ying","year":"2017","unstructured":"Ying, L. et al. Understanding immune phenotypes in human gastric disease tissues by multiplexed immunohistochemistry. J. Transl. Med. 15, 206 (2017).","journal-title":"J. Transl. Med."},{"key":"795_CR7","doi-asserted-by":"publisher","first-page":"e000155","DOI":"10.1136\/jitc-2019-000155","volume":"8","author":"JM Taube","year":"2020","unstructured":"Taube, J. M. et al. The Society for Immunotherapy of Cancer statement on best practices for multiplex immunohistochemistry (IHC) and immunofluorescence (IF) staining and validation. J. Immunother. Cancer 8, e000155 (2020).","journal-title":"J. Immunother. Cancer"},{"key":"795_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-13942-8","volume":"7","author":"ER Parra","year":"2017","unstructured":"Parra, E. R. et al. Validation of multiplex immunofluorescence panels using multispectral microscopy for immune-profiling of formalin-fixed and paraffin-embedded human tumor tissues. Sci. Rep. 7, 13380 (2017).","journal-title":"Sci. Rep."},{"key":"795_CR9","doi-asserted-by":"publisher","first-page":"3417","DOI":"10.1158\/1078-0432.CCR-19-3748","volume":"28","author":"AS Szalay","year":"2022","unstructured":"Szalay, A. S. & Taube, J. M. Data-rich spatial profiling of cancer tissue: astronomy informs pathology. Clin. Cancer Res. 28, 3417\u20133424 (2022).","journal-title":"Clin. Cancer Res."},{"key":"795_CR10","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","volume":"25","author":"G Campanella","year":"2019","unstructured":"Campanella, G. et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 25, 1301\u20131309 (2019).","journal-title":"Nat. Med."},{"key":"795_CR11","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1158\/0008-5472.CAN-19-2268","volume":"80","author":"H Failmezger","year":"2020","unstructured":"Failmezger, H. et al. Topological tumor graphs: a graph-based spatial model to infer stromal recruitment for immunosuppression in melanoma histology. Cancer Res. 80, 1199\u20131209 (2020).","journal-title":"Cancer Res."},{"key":"795_CR12","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41586-021-03512-4","volume":"594","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. AI-based pathology predicts origins for cancers of unknown primary. Nature 594, 106\u2013110 (2021).","journal-title":"Nature"},{"key":"795_CR13","doi-asserted-by":"publisher","first-page":"102474","DOI":"10.1016\/j.media.2022.102474","volume":"79","author":"N Ghaffari Laleh","year":"2022","unstructured":"Ghaffari Laleh, N. et al. Benchmarking weakly-supervised deep learning pipelines for whole slide classification in computational pathology. Med. Image Anal. 79, 102474 (2022).","journal-title":"Med. Image Anal."},{"key":"795_CR14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"795_CR15","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"B Ehteshami Bejnordi","year":"2017","unstructured":"Ehteshami Bejnordi, B. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 2199\u20132210 (2017).","journal-title":"JAMA"},{"key":"795_CR16","doi-asserted-by":"publisher","first-page":"102384","DOI":"10.1016\/j.media.2022.102384","volume":"78","author":"D Jim\u00e9nez-S\u00e1nchez","year":"2022","unstructured":"Jim\u00e9nez-S\u00e1nchez, D. et al. NaroNet: discovery of tumor microenvironment elements from highly multiplexed images. Med. Image Anal. 78, 102384 (2022).","journal-title":"Med. Image Anal."},{"key":"795_CR17","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1038\/s41572-021-00324-8","volume":"7","author":"V Makker","year":"2021","unstructured":"Makker, V. et al. Endometrial cancer. Nat. Rev. Dis. Prim. 7, 88 (2021).","journal-title":"Nat. Rev. Dis. Prim."},{"key":"795_CR18","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.ejca.2016.09.033","volume":"69","author":"MM Jeppesen","year":"2016","unstructured":"Jeppesen, M. M., Jensen, P. T., Gils\u00e5 Hansen, D., Iachina, M. & Mogensen, O. The nature of early-stage endometrial cancer recurrence-A national cohort study. Eur. J. Cancer 69, 51\u201360 (2016).","journal-title":"Eur. J. Cancer"},{"key":"795_CR19","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1038\/bjc.2015.268","volume":"113","author":"MA Versluis","year":"2015","unstructured":"Versluis, M. A. et al. Prediction model for regional or distant recurrence in endometrial cancer based on classical pathological and immunological parameters. Br. J. Cancer 113, 786\u2013793 (2015).","journal-title":"Br. J. Cancer"},{"key":"795_CR20","first-page":"463","volume":"25","author":"S Ohno","year":"2005","unstructured":"Ohno, S. et al. Role of tumor-associated macrophages (TAM) in advanced gastric carcinoma: the impact on FasL-mediated counterattack. Anticancer Res. 25, 463\u2013470 (2005).","journal-title":"Anticancer Res."},{"key":"795_CR21","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.ygyno.2009.03.022","volume":"114","author":"RA de Jong","year":"2009","unstructured":"de Jong, R. A. et al. Presence of tumor-infiltrating lymphocytes is an independent prognostic factor in type I and II endometrial cancer. Gynecol. Oncol. 114, 105\u2013110 (2009).","journal-title":"Gynecol. Oncol."},{"key":"795_CR22","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1002\/path.6012","volume":"258","author":"\u00c1 L\u00f3pez-Janeiro","year":"2022","unstructured":"L\u00f3pez-Janeiro, \u00c1. et al. The association between the tumor immune microenvironments and clinical outcome in low-grade, early-stage endometrial cancer patients. J. Pathol. 258, 426\u2013436 (2022).","journal-title":"J. Pathol."},{"key":"795_CR23","unstructured":"Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. Preprint at https:\/\/arxiv.org\/abs\/1912.01703 (2019)."},{"key":"795_CR24","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. Preprint at https:\/\/arxiv.org\/abs\/2002.05709 (2020)."},{"key":"795_CR25","unstructured":"Schmidt, U., Weigert, M., Broaddus, C. & Myers, G. Lecture Notes in Computer Science Vol. 11071 (Springer, 2018)."},{"key":"795_CR26","doi-asserted-by":"publisher","first-page":"3532","DOI":"10.1093\/bioinformatics\/btw413","volume":"32","author":"D Legland","year":"2016","unstructured":"Legland, D., Arganda-Carreras, I. & Andrey, P. MorphoLibJ: integrated library and plugins for mathematical morphology with ImageJ. Bioinformatics 32, 3532\u20133534 (2016).","journal-title":"Bioinformatics"},{"key":"795_CR27","doi-asserted-by":"publisher","first-page":"794","DOI":"10.3390\/cancers13040794","volume":"13","author":"\u00c1 L\u00f3pez-Janeiro","year":"2021","unstructured":"L\u00f3pez-Janeiro, \u00c1. et al. Proteomic analysis of low-grade, early-stage endometrial carcinoma reveals new dysregulated pathways associated with cell death and cell signaling. Cancers 13, 794 (2021).","journal-title":"Cancers"},{"key":"795_CR28","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1016\/j.cell.2018.09.018","volume":"175","author":"M Angelova","year":"2018","unstructured":"Angelova, M. et al. Evolution of metastases in space and time under immune selection. Cell 175, 751\u2013765.e16 (2018).","journal-title":"Cell"},{"key":"795_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-019-0133-7","volume":"5","author":"ME Gatti-Mays","year":"2019","unstructured":"Gatti-Mays, M. E. et al. If we build it they will come: targeting the immune response to breast cancer. NPJ Breast Cancer 5, 37 (2019).","journal-title":"NPJ Breast Cancer"},{"key":"795_CR30","doi-asserted-by":"publisher","first-page":"2654","DOI":"10.1056\/NEJMoa051424","volume":"353","author":"F Pag\u00e8s","year":"2005","unstructured":"Pag\u00e8s, F. et al. Effector memory T cells, early metastasis, and survival in colorectal cancer. N. Engl. J. Med. 353, 2654\u20132666 (2005).","journal-title":"N. Engl. J. Med."},{"key":"795_CR31","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1016\/j.cell.2020.07.005","volume":"182","author":"CM Sch\u00fcrch","year":"2020","unstructured":"Sch\u00fcrch, C. M. et al. Coordinated cellular neighborhoods orchestrate antitumoral immunity at the colorectal cancer invasive front. Cell 182, 1341\u20131359.e19 (2020).","journal-title":"Cell"},{"key":"795_CR32","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/j.cell.2017.07.025","volume":"170","author":"A Jim\u00e9nez-S\u00e1nchez","year":"2017","unstructured":"Jim\u00e9nez-S\u00e1nchez, A. et al. Heterogeneous tumor-immune microenvironments among differentially growing metastases in an ovarian cancer patient. Cell 170, 927\u2013938.e20 (2017).","journal-title":"Cell"},{"key":"795_CR33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26974-6","volume":"12","author":"D Phillips","year":"2021","unstructured":"Phillips, D. et al. Immune cell topography predicts response to PD-1 blockade in cutaneous T cell lymphoma. Nat. Commun. 12, 6726 (2021).","journal-title":"Nat. Commun."},{"key":"795_CR34","doi-asserted-by":"publisher","first-page":"100400","DOI":"10.1016\/j.xcrm.2021.100400","volume":"2","author":"R Hong","year":"2021","unstructured":"Hong, R., Liu, W., DeLair, D., Razavian, N. & Feny\u00f6, D. Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models. Cell Rep. Med. 2, 100400 (2021).","journal-title":"Cell Rep. Med."},{"key":"795_CR35","doi-asserted-by":"publisher","first-page":"1559","DOI":"10.1038\/s41591-018-0177-5","volume":"24","author":"N Coudray","year":"2018","unstructured":"Coudray, N. et al. Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat. Med. 24, 1559\u20131567 (2018).","journal-title":"Nat. Med."},{"key":"795_CR36","doi-asserted-by":"publisher","first-page":"e71","DOI":"10.1016\/S2589-7500(22)00210-2","volume":"5","author":"S Fremond","year":"2023","unstructured":"Fremond, S. et al. Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts. Lancet Digit. Health 5, e71\u2013e82 (2023).","journal-title":"Lancet Digit. Health"},{"key":"795_CR37","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1016\/j.ccell.2018.11.003","volume":"34","author":"M van den Eynde","year":"2018","unstructured":"van den Eynde, M. et al. The link between the multiverse of immune microenvironments in metastases and the survival of colorectal cancer patients. Cancer Cell 34, 1012\u20131026.e3 (2018).","journal-title":"Cancer Cell"},{"key":"795_CR38","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1038\/s41591-018-0339-5","volume":"25","author":"KA Schalper","year":"2019","unstructured":"Schalper, K. A. et al. Neoadjuvant nivolumab modifies the tumor immune microenvironment in resectable glioblastoma. Nat. Med. 25, 470\u2013476 (2019).","journal-title":"Nat. Med."},{"key":"795_CR39","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1002\/path.5753","volume":"255","author":"CE de Andrea","year":"2021","unstructured":"de Andrea, C. E. et al. Heterogenous presence of neutrophil extracellular traps in human solid tumours is partially dependent on IL-8. J. Pathol. 255, 190\u2013201 (2021).","journal-title":"J. Pathol."},{"key":"795_CR40","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s41378-019-0104-z","volume":"5","author":"D Migliozzi","year":"2019","unstructured":"Migliozzi, D. et al. Microfluidics-assisted multiplexed biomarker detection for in situ mapping of immune cells in tumor sections. Microsyst. Nanoeng. 5, 59 (2019).","journal-title":"Microsyst. Nanoeng."},{"key":"795_CR41","doi-asserted-by":"crossref","unstructured":"Sternberg, S. Biomedical image processing. Computer 16, 22\u201334 (1983).","DOI":"10.1109\/MC.1983.1654163"},{"key":"795_CR42","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M. & Hinton, G. Big self-supervised models are strong semi-supervised learners. Preprint at https:\/\/arxiv.org\/abs\/2006.10029 (2020)."},{"key":"795_CR43","first-page":"1","volume":"27","author":"J Shi","year":"2022","unstructured":"Shi, J., Gong, T., Wang, C. & Li, C. Semi-supervised pixel contrastive learning framework for tissue segmentation in histopathological image. IEEE J. Biomed. Health Inform. 27, 1\u201312 (2022).","journal-title":"IEEE J. Biomed. Health Inform"},{"key":"795_CR44","unstructured":"Liaw, R. et al. Tune: a research platform for distributed model selection and training. Preprint at https:\/\/arxiv.org\/abs\/1807.05118 (2018)."},{"key":"795_CR45","unstructured":"Li, L. et al. A system for massively parallel hyperparameter tuning. Preprint at https:\/\/arxiv.org\/abs\/1810.05934 (2018)."},{"key":"795_CR46","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1002\/path.5372","volume":"250","author":"A Le\u00f3n-Castillo","year":"2020","unstructured":"Le\u00f3n-Castillo, A. et al. Interpretation of somatic POLE mutations in endometrial carcinoma. J. Pathol. 250, 323\u2013335 (2020).","journal-title":"J. Pathol."},{"key":"795_CR47","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1002\/path.5375","volume":"250","author":"N Singh","year":"2020","unstructured":"Singh, N. et al. p53 immunohistochemistry is an accurate surrogate for TP53 mutational analysis in endometrial carcinoma biopsies. J. Pathol. 250, 336\u2013345 (2020).","journal-title":"J. Pathol."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00795-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00795-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00795-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,23]],"date-time":"2023-03-23T05:04:51Z","timestamp":1679547891000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00795-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,23]]},"references-count":47,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["795"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00795-x","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,23]]},"assertion":[{"value":"5 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"C.E.A. has received research support from AstraZeneca. I.M. has received research support from AstraZeneca, Bristol Myers Squibb, Bioncotech Therapeutics, Alligator Bioscience, Pfizer, Leadartis, and Roche. I.M. is a consultant or advisory board member for AstraZeneca, Roche, Genmab, and Merck Serono. Iv.M. and V.G. are employed by Akoya Biosciences. E.K. is employed by Lunaphore Technologies. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}