{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T03:40:18Z","timestamp":1782358818563,"version":"3.54.5"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100007753","name":"It\u00e4-Suomen Yliopisto","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007753","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006383","name":"Sy\u00f6p\u00e4j\u00e4rjest\u00f6t","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006383","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Data"],"DOI":"10.1038\/s41597-026-07106-5","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T01:56:12Z","timestamp":1775094972000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Malignant vs. Non-malignant Annotations on TCGA Breast Cancer Whole Slide Images for AI Analysis"],"prefix":"10.1038","volume":"13","author":[{"given":"Zahra Alidousti","family":"Shahraki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Otto","family":"Jokelainen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mari","family":"Valkonen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P\u00e4ivi","family":"Auvinen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arto","family":"Mannermaa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Behravan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"7106_CR1","doi-asserted-by":"publisher","DOI":"10.1186\/s13058-024-01863-0","volume":"26","author":"R Valieris","year":"2024","unstructured":"Valieris, R. et al. Weakly-supervised deep learning models enable HER2-low prediction from H &E stained slides. Breast Cancer Res. 26, 124 (2024).","journal-title":"Breast Cancer Res."},{"key":"7106_CR2","doi-asserted-by":"publisher","first-page":"100410","DOI":"10.1016\/j.jpi.2024.100410","volume":"16","author":"M Tafavvoghi","year":"2025","unstructured":"Tafavvoghi, M. et al. Deep learning-based classification of breast cancer molecular subtypes from H&E whole-slide images. J. Pathol. Inform. 16, 100410 (2025).","journal-title":"J. Pathol. Inform."},{"key":"7106_CR3","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":"7106_CR4","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TMI.2018.2867350","volume":"38","author":"P Bandi","year":"2019","unstructured":"Bandi, P. et al. From detection of individual metastases to classification of lymph node status at the patient level: the CAMELYON17 challenge. IEEE Trans. Med. Imaging 38, 550\u2013560 (2019).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"7106_CR5","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","volume":"28","author":"W Bulten","year":"2022","unstructured":"Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154\u2013163 (2022).","journal-title":"Nat. Med."},{"key":"7106_CR6","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1038\/s41746-024-01411-2","volume":"7","author":"W Zhao","year":"2024","unstructured":"Zhao, W. et al. Aligning knowledge concepts to whole slide images for precise histopathology image analysis. NPJ Digit. Med. 7, 383 (2024).","journal-title":"NPJ Digit. Med."},{"key":"7106_CR7","doi-asserted-by":"publisher","first-page":"102485","DOI":"10.1016\/j.media.2022.102485","volume":"80","author":"Q Da","year":"2022","unstructured":"Da, Q. et al. DigestPath: A benchmark dataset with challenge review for the pathological detection and segmentation of digestive-system. Med. Image Anal. 80, 102485 (2022).","journal-title":"Med. Image Anal."},{"issue":"1","key":"7106_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41523-024-00663-1","volume":"10","author":"S Liu","year":"2024","unstructured":"Liu, S. et al. A panoptic segmentation dataset and deep-learning approach for explainable scoring of tumor-infiltrating lymphocytes. NPJ breast cancer 10(1), 52, https:\/\/doi.org\/10.1038\/s41523-024-00663-1 (2024).","journal-title":"NPJ breast cancer"},{"key":"7106_CR9","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5320076","author":"C Loeffler","year":"2021","unstructured":"Loeffler, C. & Kather, J. N. Manual tumor annotations in TCGA. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.5320076 (2021)."},{"key":"7106_CR10","doi-asserted-by":"publisher","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, 16878 (2017).","journal-title":"Sci. Rep."},{"key":"7106_CR11","doi-asserted-by":"publisher","first-page":"107997","DOI":"10.1016\/j.compbiomed.2024.107997","volume":"170","author":"H Liu","year":"2024","unstructured":"Liu, H., Zhang, Y. & Luo, J. Contrastive learning-based histopathological features infer molecular subtypes and clinical outcomes of breast cancer from unannotated whole slide images. Comput. Biol. Med. 170, 107997 (2024).","journal-title":"Comput. Biol. Med."},{"key":"7106_CR12","doi-asserted-by":"publisher","unstructured":"BRCA-QuPath-Annot dataset, https:\/\/doi.org\/10.6084\/m9.figshare.30256354.","DOI":"10.6084\/m9.figshare.30256354"},{"key":"7106_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. A simple framework for contrastive learning of visual representations. In Proc. 37th Int. Conf. Mach. Learn. 1597\u20131607 (PMLR, 2020)."},{"key":"7106_CR14","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep learning. Cambridge: MIT Press (2016)."},{"key":"7106_CR15","doi-asserted-by":"crossref","unstructured":"Wang, P., Han, K., Wei, X.-S., Zhang, L. & Wang, L. Contrastive learning based hybrid networks for long-tailed image classification. In Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 943\u2013952 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.00100"},{"key":"7106_CR16","doi-asserted-by":"publisher","unstructured":"Macenko, M. et al. A method for normalizing histology slides for quantitative analysis. In Proc. IEEE Int. Symp. Biomed. Imaging 1107\u20131110, https:\/\/doi.org\/10.1109\/ISBI.2009.5193250 (IEEE, 2009).","DOI":"10.1109\/ISBI.2009.5193250"},{"key":"7106_CR17","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1038\/s43856-022-00186-5","volume":"2","author":"J Pocock","year":"2022","unstructured":"Pocock, J. et al. TIAToolbox as an end-to-end library for advanced tissue image analytics. Commun. Med. 2, 120 (2022).","journal-title":"Commun. Med."},{"issue":"7418","key":"7106_CR18","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/nature11412","volume":"490","author":"Cancer Genome Atlas Network","year":"2012","unstructured":"Cancer Genome Atlas Network. Comprehensive molecular portraits of human breast tumours. Nature. 490(7418), 61\u201370 (2012).","journal-title":"Nature."},{"key":"7106_CR19","doi-asserted-by":"publisher","first-page":"619110","DOI":"10.3389\/fmolb.2021.619110","volume":"8","author":"N Sun","year":"2021","unstructured":"Sun, N. et al. Screening and identification of key common and specific genes and their prognostic roles in different molecular subtypes of breast cancer. Front. Mol. Biosci. 8, 619110 (2021).","journal-title":"Front. Mol. Biosci."},{"key":"7106_CR20","first-page":"2929","volume":"5","author":"X Dai","year":"2015","unstructured":"Dai, X. et al. Breast cancer intrinsic subtype classification, clinical use and future trends. Am. J. Cancer Res. 5, 2929\u20132949 (2015).","journal-title":"Am. J. Cancer Res."},{"key":"7106_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-27707-4","volume":"8","author":"S Wang","year":"2018","unstructured":"Wang, S. et al. Comprehensive analysis of lung cancer pathology images to discover tumor shape and boundary features that predict survival outcome. Sci. Rep. 8, 10393 (2018).","journal-title":"Sci. Rep."}],"container-title":["Scientific Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07106-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07106-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07106-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T23:14:35Z","timestamp":1779837275000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41597-026-07106-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["7106"],"URL":"https:\/\/doi.org\/10.1038\/s41597-026-07106-5","relation":{"references":[{"id-type":"doi","id":"10.5281\/zenodo.5320076","asserted-by":"subject"}]},"ISSN":["2052-4463"],"issn-type":[{"value":"2052-4463","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]},"assertion":[{"value":"9 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 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":"783"}}