{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,9]],"date-time":"2026-11-09T21:04:41Z","timestamp":1794258281847,"version":"4.9.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T00:00:00Z","timestamp":1777939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Commun Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence has significantly advanced computational pathology by enabling high-resolution, clinical-grade tumor segmentation models with state-of-the-art diagnostic accuracy. Creating such models is resource-intensive, requiring substantial time and domain expertise. Additionally, deep learning models are typically restricted to single tumor types, making it challenging to develop separate models for each tumor type. Cross-cancer generalization of segmentation models could address this bottleneck and pave the way for pan-cancer segmentation models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We evaluated the cross-tumor generalization capability of five tissue segmentation models (breast, colon, lung, kidney, prostate) using 21 cancer types from The Cancer Genome Atlas, totaling over 7,700 whole slide images. Representative large tumor and benign regions were manually selected, and segmentation accuracy was evaluated using a semiquantitative scale (0-10).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Here we show that the lung model demonstrates excellent cross-cancer performance (overall mean score 7.9\u2009\u00b1\u20092.1), effectively segmenting tumor regions in many non-lung cancers with segmentation accuracy similar to its native domain in 11 of 19 other epithelial tumors and melanoma, achieving particularly strong results in ovarian cancer (9.2\u2009\u00b1\u20090.9). The breast and colon models also show strong cross-domain performance, while the kidney and prostate models exhibit more limited generalization. Overall, high-precision segmentation is achievable in most cancer types using existing models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Existing segmentation models generalize across multiple cancer types, reducing the need to develop new, entity-specific models from scratch. This cross-domain generalization enables fast-track model development and supports future creation of robust pan-cancer segmentation models. Leveraging these capabilities could accelerate clinical integration of pathology artificial intelligence tools and enable reproducible biomarker discovery.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s43856-026-01601-x","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T10:15:50Z","timestamp":1777976150000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Comprehensive evaluation of cross cancer generalization in histopathology segmentation models across 21 tumor types"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7510-2261","authenticated-orcid":false,"given":"Tillmann","family":"Bedau","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Harder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulkader","family":"Al-Shughri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexey","family":"Pryalukhin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Lisa","family":"Eich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Su Ir","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8806-4786","authenticated-orcid":false,"given":"Reinhard","family":"B\u00fcttner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Quaas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuri","family":"Tolkach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,5]]},"reference":[{"key":"1601_CR1","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1038\/s41416-020-01122-x","volume":"124","author":"A Echle","year":"2021","unstructured":"Echle, A. et al. Deep learning in cancer pathology: a new generation of clinical biomarkers. Br. J. Cancer 124, 686\u2013696 (2021).","journal-title":"Br. J. Cancer"},{"key":"1601_CR2","doi-asserted-by":"crossref","unstructured":"Perez-Lopez, R., Ghaffari, Laleh N., Mahmood, F. & Kather, J. N. A guide to artificial intelligence for cancer researchers. Nat. Rev. Cancer 24, 427\u2013441 (2024).","DOI":"10.1038\/s41568-024-00694-7"},{"key":"1601_CR3","doi-asserted-by":"publisher","unstructured":"Song, A.H. et al. (2023) Artificial intelligence for digital and computational pathology. Nat. Rev. Bioeng. 1, 930\u2013949 (2023). https:\/\/doi.org\/10.1038\/s44222-023-00096-8.","DOI":"10.1038\/s44222-023-00096-8"},{"key":"1601_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101813","volume":"67","author":"CL Srinidhi","year":"2021","unstructured":"Srinidhi, C. L., Ciga, O. & Martel, A. L. Deep neural network models for computational histopathology: a survey. Med. Image Anal. 67, 101813 (2021).","journal-title":"Med. Image Anal."},{"key":"1601_CR5","unstructured":"The Cancer Genome Atlas Program (TCGA) - NCI. https:\/\/www.cancer.gov\/ccg\/research\/genome-sequencing\/tcga. Zugegriffen: 16. September 2024 (2022)."},{"key":"1601_CR6","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen, R. J. et al. Towards a general-purpose foundation model for computational pathology. Nat. Med. 30, 850\u2013862 (2024).","journal-title":"Nat. Med."},{"key":"1601_CR7","doi-asserted-by":"publisher","unstructured":"Dippel J, et al (2024) RudolfV: A Foundation Model by Pathologists for Pathologists. https:\/\/doi.org\/10.48550\/arXiv.2401.04079","DOI":"10.48550\/arXiv.2401.04079"},{"key":"1601_CR8","doi-asserted-by":"crossref","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863\u2013874 (2024).","DOI":"10.1038\/s41591-024-02856-4"},{"key":"1601_CR9","doi-asserted-by":"crossref","unstructured":"Vorontsov, E. et al. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat. Med. 30, 2924\u20132935 (2024).","DOI":"10.1038\/s41591-024-03141-0"},{"key":"1601_CR10","doi-asserted-by":"crossref","unstructured":"Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181\u2013188 (2024).","DOI":"10.1038\/s41586-024-07441-w"},{"key":"1601_CR11","doi-asserted-by":"crossref","unstructured":"Campanella, G. et al. A clinical benchmark of public self-supervised pathology foundation models. Nat Commun. 16, 3640 (2025)","DOI":"10.1038\/s41467-025-58796-1"},{"key":"1601_CR12","doi-asserted-by":"publisher","unstructured":"Neidlinger, P. et al. Benchmarking foundation models as feature extractors for weakly-supervised computational pathology. Nat. Biomed. Eng. (2025). https:\/\/doi.org\/10.1038\/s41551-025-01516-3 (2024).","DOI":"10.1038\/s41551-025-01516-3"},{"key":"1601_CR13","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1146\/annurev-pathmechdis-051222-113147","volume":"19","author":"F Klauschen","year":"2024","unstructured":"Klauschen, F. et al. Toward explainable artificial intelligence for precision pathology. Annu. Rev. Pathol. 19, 541\u2013570 (2024).","journal-title":"Annu. Rev. Pathol."},{"key":"1601_CR14","doi-asserted-by":"publisher","unstructured":"Kludt, C. et al. Next-generation lung cancer pathology: development and validation of diagnostic and prognostic algorithms. CR Med. https:\/\/doi.org\/10.1016\/j.xcrm.2024.101697 (2024).","DOI":"10.1016\/j.xcrm.2024.101697"},{"key":"1601_CR15","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":"1601_CR16","doi-asserted-by":"crossref","unstructured":"H\u00f6rst, F. et al. CellViT: vision transformers for precise cell segmentation and classification. Med. Image Anal. 94, 103143 (2024).","DOI":"10.1016\/j.media.2024.103143"},{"key":"1601_CR17","doi-asserted-by":"publisher","unstructured":"Kirillov, A. et al. Segment anything. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2304.02643 (2023).","DOI":"10.48550\/arXiv.2304.02643"},{"key":"1601_CR18","doi-asserted-by":"publisher","unstructured":"Ravi, N. et al. SAM 2: segment anything in images and videos. https:\/\/doi.org\/10.48550\/arXiv.2408.00714 (2024).","DOI":"10.48550\/arXiv.2408.00714"},{"key":"1601_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J. et al. Segment anything in medical images. Nat. Commun. 15, 654 (2024).","journal-title":"Nat. Commun."},{"key":"1601_CR20","doi-asserted-by":"publisher","unstructured":"Ma, J. et al. MedSAM2: segment anything in 3D medical images and videos. https:\/\/doi.org\/10.48550\/arXiv.2504.03600 (2025).","DOI":"10.48550\/arXiv.2504.03600"},{"key":"1601_CR21","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41592-024-02499-w","volume":"22","author":"T Zhao","year":"2025","unstructured":"Zhao, T. et al. A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities. Nat Methods 22, 166\u2013176 (2025).","journal-title":"Nat Methods"},{"key":"1601_CR22","doi-asserted-by":"publisher","first-page":"100327","DOI":"10.1016\/j.modpat.2023.100327","volume":"36","author":"J Griem","year":"2023","unstructured":"Griem, J. et al. Artificial intelligence-based tool for tumor detection and quantitative tissue analysis in colorectal specimens. Mod. Pathol. 36, 100327 (2023).","journal-title":"Mod. Pathol."},{"key":"1601_CR23","doi-asserted-by":"publisher","unstructured":"Harder, C. et al. Enhancing prostate cancer diagnosis: AI-driven virtual biopsy for optimal MRI-targeted biopsy approach and gleason grading strategy. https:\/\/doi.org\/10.1016\/j.modpat.2024.100564 (2024).","DOI":"10.1016\/j.modpat.2024.100564"},{"key":"1601_CR24","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/s42256-020-0200-7","volume":"2","author":"Y Tolkach","year":"2020","unstructured":"Tolkach, Y., Dohmg\u00f6rgen, T., Toma, M. & Kristiansen, G. High-accuracy prostate cancer pathology using deep learning. Nat. Mach. Intell. 2, 411\u2013418 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"1601_CR25","doi-asserted-by":"crossref","unstructured":"Giammanco, A. et al. Fast-track development and multi-institutional clinical validation of an artificial intelligence algorithm for detection of lymph node metastasis in colorectal cancer. Mod. Pathol. 37, 100496 (2024).","DOI":"10.1016\/j.modpat.2024.100496"},{"key":"1601_CR26","unstructured":"GDC Data Transfer Tool | NCI Genomic Data Commons. https:\/\/gdc.cancer.gov\/access-data\/gdc-data-transfer-tool. Zugegriffen: 08. August 2024"},{"key":"1601_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-17204-5","volume":"7","author":"P Bankhead","year":"2017","unstructured":"Bankhead, P. et al. QuPath: open source software for digital pathology image analysis. Sci Rep 7, 1\u20137 (2017).","journal-title":"Sci Rep"},{"key":"1601_CR28","doi-asserted-by":"publisher","unstructured":"Bedau, T. et al. Evaluation data for: Comprehensive evaluation of cross-cancer generalization in histopathology segmentation models across 21 tumor types. https:\/\/doi.org\/10.5281\/zenodo.18518811 (2026).","DOI":"10.5281\/zenodo.18518811"},{"key":"1601_CR29","doi-asserted-by":"publisher","unstructured":"Bedau, T. et al. Tumor ROIs for: comprehensive evaluation of cross-cancer generalization in histopathology segmentation models across 21 tumor types. https:\/\/doi.org\/10.5281\/zenodo.18668580 (2026).","DOI":"10.5281\/zenodo.18668580"},{"key":"1601_CR30","doi-asserted-by":"publisher","unstructured":"Bedau, T. et al. Segmentation masks for: comprehensive evaluation of cross-cancer generalization in histopathology segmentation models across 21 tumor types. https:\/\/doi.org\/10.5281\/zenodo.18669667 (2026).","DOI":"10.5281\/zenodo.18669667"},{"key":"1601_CR31","doi-asserted-by":"crossref","unstructured":"Martinez, K. & Cupitt, J. VIPS - a highly tuned image processing software architecture. In Proc. IEEE International Conference on Image Processing 2005 S II\u2013574 (IEEE, 2005).","DOI":"10.1109\/ICIP.2005.1530120"},{"key":"1601_CR32","unstructured":"Ram\u00edrez, S. FastAPI (2024)."},{"key":"1601_CR33","unstructured":"Gilman, I. et al. OpenSeadragon (2024)."},{"key":"1601_CR34","doi-asserted-by":"publisher","first-page":"102685","DOI":"10.1016\/j.media.2022.102685","volume":"83","author":"S Graham","year":"2023","unstructured":"Graham, S. et al. One model is all you need: multi-task learning enables simultaneous histology image segmentation and classification. Med. Image Anal. 83, 102685 (2023).","journal-title":"Med. Image Anal."},{"key":"1601_CR35","doi-asserted-by":"publisher","unstructured":"Nahhas, OSME. et al. Joint multi-task learning improves weakly-supervised biomarker prediction in computational pathology. In Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science.. (Linguraru, M.G., et al.) Vol 15004, https:\/\/doi.org\/10.48550\/arXiv.2403.03891 (Springer, Cham, 2024).","DOI":"10.48550\/arXiv.2403.03891"},{"key":"1601_CR36","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20030-5","volume":"11","author":"J Noorbakhsh","year":"2020","unstructured":"Noorbakhsh, J. et al. Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images. Nat. Commun. 11, 6367 (2020).","journal-title":"Nat. Commun."},{"key":"1601_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s43856-024-00471-5","volume":"4","author":"S Arslan","year":"2024","unstructured":"Arslan, S. et al. A systematic pan-cancer study on deep learning-based prediction of multi-omic biomarkers from routine pathology images. Commun. Med. 4, 1\u201315 (2024).","journal-title":"Commun. Med."},{"key":"1601_CR38","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1016\/j.ccell.2022.07.004","volume":"40","author":"RJ Chen","year":"2022","unstructured":"Chen, R. J. et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell 40, 865\u2013878.e6 (2022).","journal-title":"Cancer Cell"},{"key":"1601_CR39","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1038\/s43018-020-0085-8","volume":"1","author":"Y Fu","year":"2020","unstructured":"Fu, Y. et al. Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis. Nat. Cancer 1, 800\u2013810 (2020).","journal-title":"Nat. Cancer"},{"key":"1601_CR40","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1038\/s43018-020-0087-6","volume":"1","author":"JN Kather","year":"2020","unstructured":"Kather, J. N. et al. Pan-cancer image-based detection of clinically actionable genetic alterations. Nat. Cancer 1, 789\u2013799 (2020).","journal-title":"Nat. Cancer"},{"key":"1601_CR41","doi-asserted-by":"publisher","unstructured":"Bedau, T. et al. Code for: comprehensive evaluation of cross cancer generalization in histopathology segmentation models across 21 tumor types. https:\/\/doi.org\/10.5281\/zenodo.18520078 (2026).","DOI":"10.5281\/zenodo.18520078"}],"container-title":["Communications Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01601-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01601-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01601-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:16:20Z","timestamp":1779416180000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s43856-026-01601-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,5]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1601"],"URL":"https:\/\/doi.org\/10.1038\/s43856-026-01601-x","relation":{},"ISSN":["2730-664X"],"issn-type":[{"value":"2730-664X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,5]]},"assertion":[{"value":"14 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2026","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":"302"}}