{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T14:08:04Z","timestamp":1770818884750,"version":"3.50.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":26,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University Cancer Research Fund of North Carolina"},{"DOI":"10.13039\/100009634","name":"Susan G. Komen","doi-asserted-by":"publisher","award":["OGUNC1202"],"award-info":[{"award-number":["OGUNC1202"]}],"id":[{"id":"10.13039\/100009634","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA253450"],"award-info":[{"award-number":["R01CA253450"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["R01CA253450"],"award-info":[{"award-number":["R01CA253450"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["5UH3CA225021"],"award-info":[{"award-number":["5UH3CA225021"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100001006","name":"Breast Cancer Research Foundation","doi-asserted-by":"publisher","award":["HEI-23-003"],"award-info":[{"award-number":["HEI-23-003"]}],"id":[{"id":"10.13039\/100001006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["HT94252310235"],"award-info":[{"award-number":["HT94252310235"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation","award":["IIS-2212046"],"award-info":[{"award-number":["IIS-2212046"]}]},{"name":"Stony Brook University Provost\u2019s ProFund"},{"name":"Donor support from Bob Beals and Betsy Barton"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Transcriptomic assays such as the PAM50-based ROR-P score guide recurrence risk stratification in non-metastatic, ER-positive, HER2-negative breast cancer but are not universally accessible. Histopathology is routinely available and may offer a scalable alternative. We introduce MAKO, a benchmarking framework evaluating 12 pathology foundation models and two non-pathology baselines for predicting ROR-P scores from H&amp;E-stained whole-slide images using attention-based multiple instance learning. Foundation models, large neural networks pre-trained on millions of pathology images and adaptable to diverse downstream tasks, were trained and validated on the Carolina Breast Cancer Study and externally tested on TCGA BRCA. Several foundation models outperformed baseline models across classification, regression, and survival tasks. CONCH achieved the highest ROC AUC, while H-optimus-0 and Virchow2 showed the top correlation with continuous ROR-P scores. All pathology models stratified CBCS participants by recurrence similarly to transcriptomic ROR-P. Using the HIPPO interpretability method, we found that tumor regions were necessary and sufficient for high-risk predictions, and we identified candidate tissue biomarkers of recurrence. These results highlight the promise of interpretable, histology-based risk models in precision oncology.<\/jats:p>","DOI":"10.1038\/s41746-025-02334-2","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T11:16:26Z","timestamp":1768562186000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards interpretable prediction of recurrence risk in breast cancer using pathology foundation models"],"prefix":"10.1038","volume":"9","author":[{"given":"Jakub R.","family":"Kaczmarzyk","sequence":"first","affiliation":[]},{"given":"Sarah C.","family":"Van Alsten","sequence":"additional","affiliation":[]},{"given":"Alyssa J.","family":"Cozzo","sequence":"additional","affiliation":[]},{"given":"Rajarsi","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Peter K.","family":"Koo","sequence":"additional","affiliation":[]},{"given":"Melissa A.","family":"Troester","sequence":"additional","affiliation":[]},{"given":"Katherine A.","family":"Hoadley","sequence":"additional","affiliation":[]},{"given":"Joel H.","family":"Saltz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"2334_CR1","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1158\/1055-9965.EPI-16-0520","volume":"26","author":"A-M Noone","year":"2017","unstructured":"Noone, A.-M. et al. Cancer incidence and survival trends by subtype using data from the surveillance epidemiology and end results program, 1992\u20132013. Cancer Epidemiol. Biomarkers Prev. 26, 632\u2013641 (2017).","journal-title":"Cancer Epidemiol. Biomarkers Prev."},{"key":"2334_CR2","doi-asserted-by":"publisher","first-page":"dju055","DOI":"10.1093\/jnci\/dju055","volume":"106","author":"N Howlader","year":"2014","unstructured":"Howlader, N. et al. US incidence of breast cancer subtypes defined by joint hormone receptor and HER2 status. J. Natl. Cancer Inst. 106, dju055 (2014).","journal-title":"J. Natl. Cancer Inst."},{"key":"2334_CR3","doi-asserted-by":"publisher","first-page":"1708","DOI":"10.1016\/j.cell.2023.01.040","volume":"186","author":"E Nolan","year":"2023","unstructured":"Nolan, E., Lindeman, G. J. & Visvader, J. E. Deciphering breast cancer: from biology to the clinic. Cell 186, 1708\u20131728 (2023).","journal-title":"Cell"},{"key":"2334_CR4","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1056\/NEJMoa1701830","volume":"377","author":"H Pan","year":"2017","unstructured":"Pan, H. et al. 20-Year Risks of breast-cancer recurrence after stopping endocrine therapy at 5 years. N. Engl. J. Med. 377, 1836\u20131846 (2017).","journal-title":"N. Engl. J. Med."},{"key":"2334_CR5","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1093\/jnci\/djab202","volume":"114","author":"RN Pedersen","year":"2022","unstructured":"Pedersen, R. N. et al. The incidence of breast cancer recurrence 10\u201332 years after primary diagnosis. J. Natl. Cancer Inst. 114, 391\u2013399 (2022).","journal-title":"J. Natl. Cancer Inst."},{"key":"2334_CR6","doi-asserted-by":"publisher","unstructured":"Kuerer, H. M. et al. Selective elimination of breast surgery for invasive breast cancer: a nonrandomized clinical trial. JAMA Oncol. https:\/\/doi.org\/10.1001\/jamaoncol.2025.0207 (2025).","DOI":"10.1001\/jamaoncol.2025.0207"},{"key":"2334_CR7","doi-asserted-by":"publisher","unstructured":"Alvarado, M., Ozanne, E. & Esserman, L. Overdiagnosis and overtreatment of breast cancer. Am. Soc. Clin. Oncol. Educ. Book e40\u2013e45 https:\/\/doi.org\/10.14694\/EdBook_AM.2012.32.301 (2012).","DOI":"10.14694\/EdBook_AM.2012.32.301"},{"key":"2334_CR8","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1001\/jama.2018.0018","volume":"319","author":"SJ Katz","year":"2018","unstructured":"Katz, S. J., Jagsi, R. & Morrow, M. Reducing overtreatment of cancer with precision medicine: just what the doctor ordered. JAMA 319, 1091\u20131092 (2018).","journal-title":"JAMA"},{"key":"2334_CR9","doi-asserted-by":"publisher","first-page":"3584","DOI":"10.1002\/cncr.28260","volume":"119","author":"SJ Katz","year":"2013","unstructured":"Katz, S. J. & Morrow, M. Addressing overtreatment in breast cancer: the doctors\u2019 dilemma. Cancer 119, 3584\u20133588 (2013).","journal-title":"Cancer"},{"key":"2334_CR10","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1080\/14737140.2022.2064277","volume":"22","author":"LM Pak","year":"2022","unstructured":"Pak, L. M. & Morrow, M. Addressing the problem of overtreatment in breast cancer. Expert Rev. Anticancer Ther. 22, 535\u2013548 (2022).","journal-title":"Expert Rev. Anticancer Ther."},{"key":"2334_CR11","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s10549-022-06550-2","volume":"193","author":"MAA Ragusi","year":"2022","unstructured":"Ragusi, M. A. A. et al. Population-based estimates of overtreatment with adjuvant systemic therapy in early breast cancer patients with data from the Netherlands and the USA. Breast Cancer Res. Treat. 193, 161\u2013173 (2022).","journal-title":"Breast Cancer Res. Treat."},{"key":"2334_CR12","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1200\/JCO.2008.18.1370","volume":"27","author":"JS Parker","year":"2009","unstructured":"Parker, J. S. et al. Supervised risk predictor of breast cancer based on intrinsic subtypes. J. Clin. Oncol. 27, 1160\u20131167 (2009).","journal-title":"J. Clin. Oncol."},{"key":"2334_CR13","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1200\/JCO.2014.55.6894","volume":"33","author":"I Sestak","year":"2015","unstructured":"Sestak, I. et al. Prediction of late distant recurrence after 5 years of endocrine treatment: a combined analysis of patients from the austrian breast and colorectal cancer study group 8 and arimidex, tamoxifen alone or in combination randomized trials using the PAM50 risk of recurrence score. J. Clin. Oncol. 33, 916\u2013922 (2015).","journal-title":"J. Clin. Oncol."},{"key":"2334_CR14","doi-asserted-by":"publisher","first-page":"iii29","DOI":"10.1093\/annonc\/mdt084.1","volume":"24","author":"M Gnant","year":"2013","unstructured":"Gnant, M. et al. Predicting risk for late metastasis: the PAM50 Risk of Recurrence (ROR) score after 5 years of endocrine therapy in postmenopausal women with Hr+ early breast cancer: a study on 1,478 patients from the Abcsg-8 trial. Ann. Oncol. 24, iii29 (2013).","journal-title":"Ann. Oncol."},{"key":"2334_CR15","doi-asserted-by":"publisher","first-page":"P2","DOI":"10.1158\/0008-5472.SABCS12-P2-10-02","volume":"72","author":"M Gnant","year":"2012","unstructured":"Gnant, M. et al. Abstract P2-10-02: clinical validation of the PAM50 risk of recurrence (ROR) score for predicting residual risk of distant-recurrence (DR) after endocrine therapy in postmenopausal women with ER+ early breast cancer (EBC): an ABCSG study. Cancer Res. 72, P2\u201310\u201302 (2012).","journal-title":"Cancer Res."},{"key":"2334_CR16","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1200\/JCO.2012.46.1558","volume":"31","author":"M Dowsett","year":"2013","unstructured":"Dowsett, M. et al. Comparison of PAM50 Risk of Recurrence score with oncotype DX and IHC4 for predicting risk of distant recurrence after endocrine therapy. J. Clin. Oncol. 31, 2783\u20132790 (2013).","journal-title":"J. Clin. Oncol."},{"key":"2334_CR17","doi-asserted-by":"publisher","first-page":"545","DOI":"10.1001\/jamaoncol.2017.5524","volume":"4","author":"I Sestak","year":"2018","unstructured":"Sestak, I. et al. Comparison of the performance of 6 prognostic signatures for estrogen receptor\u2013positive breast cancer: a secondary analysis of a randomized clinical trial. JAMA Oncol. 4, 545\u2013553 (2018).","journal-title":"JAMA Oncol."},{"key":"2334_CR18","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1093\/jnci\/djt244","volume":"105","author":"I Sestak","year":"2013","unstructured":"Sestak, I. et al. Factors predicting late recurrence for estrogen receptor\u2013positive breast cancer. J. Natl. Cancer Inst. 105, 1504\u20131511 (2013).","journal-title":"J. Natl. Cancer Inst."},{"key":"2334_CR19","doi-asserted-by":"publisher","first-page":"5222","DOI":"10.1158\/1078-0432.CCR-10-1282","volume":"16","author":"TO Nielsen","year":"2010","unstructured":"Nielsen, T. O. et al. A comparison of PAM50 intrinsic subtyping with immunohistochemistry and clinical prognostic factors in tamoxifen-treated estrogen receptor-positive breast cancer. Clin. Cancer Res. 16, 5222\u20135232 (2010).","journal-title":"Clin. Cancer Res."},{"key":"2334_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13058-017-0911-9","volume":"19","author":"HO Ohnstad","year":"2017","unstructured":"Ohnstad, H. O. et al. Prognostic value of PAM50 and risk of recurrence score in patients with early-stage breast cancer with long-term follow-up. Breast Cancer Res. 19, 1\u201312 (2017).","journal-title":"Breast Cancer Res."},{"key":"2334_CR21","first-page":"654","volume":"33","author":"SC Van Alsten","year":"2024","unstructured":"Van Alsten, S. C. et al. Disparities in OncotypeDx testing and subsequent chemotherapy receipt by geography and socioeconomic status. Cancer Epidemiol. Biomark. Prev. Publ. Am. Assoc. Cancer Res. Cosponsored Am. Soc. Prev. Oncol. 33, 654\u2013661 (2024).","journal-title":"Cancer Epidemiol. Biomark. Prev. Publ. Am. Assoc. Cancer Res. Cosponsored Am. Soc. Prev. Oncol."},{"key":"2334_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19334-3","volume":"11","author":"N Naik","year":"2020","unstructured":"Naik, N. et al. Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains. Nat. Commun. 11, 5727 (2020).","journal-title":"Nat. Commun."},{"key":"2334_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41523-018-0079-1","volume":"4","author":"HD Couture","year":"2018","unstructured":"Couture, H. D. et al. Image analysis with deep learning to predict breast cancer grade, ER status, histologic subtype, and intrinsic subtype. Npj Breast Cancer 4, 1\u20138 (2018).","journal-title":"Npj Breast Cancer"},{"key":"2334_CR24","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1097\/PAI.0000000000001258","volume":"33","author":"A Akbarnejad","year":"2025","unstructured":"Akbarnejad, A., Ray, N., Barnes, P. J. & Bigras, G. Toward accurate deep learning-based prediction of Ki67, ER, PR, and HER2 status from H&E-stained breast cancer images. Appl. Immunohistochem. Mol. Morphol. 33, 131\u2013141 (2025).","journal-title":"Appl. Immunohistochem. Mol. Morphol."},{"key":"2334_CR25","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41379-021-00911-w","volume":"35","author":"S Farahmand","year":"2022","unstructured":"Farahmand, S. et al. Deep learning trained on hematoxylin and eosin tumor region of Interest predicts HER2 status and trastuzumab treatment response in HER2+ breast cancer. Mod. Pathol. 35, 44\u201351 (2022).","journal-title":"Mod. Pathol."},{"key":"2334_CR26","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13058-020-1248-3","volume":"22","author":"MI Jaber","year":"2020","unstructured":"Jaber, M. I. et al. A deep learning image-based intrinsic molecular subtype classifier of breast tumors reveals tumor heterogeneity that may affect survival. Breast Cancer Res. 22, 12 (2020).","journal-title":"Breast Cancer Res."},{"key":"2334_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41523-023-00597-0","volume":"9","author":"Y Shi","year":"2023","unstructured":"Shi, Y. et al. Predicting early breast cancer recurrence from histopathological images in the Carolina Breast Cancer Study. Npj Breast Cancer 9, 1\u20137 (2023).","journal-title":"Npj Breast Cancer"},{"key":"2334_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13058-024-01915-5","volume":"26","author":"DN Lee","year":"2024","unstructured":"Lee, D. N. et al. Image analysis-based identification of high risk ER-positive, HER2-negative breast cancers. Breast Cancer Res. 26, 1\u201311 (2024).","journal-title":"Breast Cancer Res."},{"key":"2334_CR29","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"2334_CR30","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","volume":"634","author":"X Wang","year":"2024","unstructured":"Wang, X. et al. A pathology foundation model for cancer diagnosis and prognosis prediction. Nature 634, 970\u2013978 (2024).","journal-title":"Nature"},{"key":"2334_CR31","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":"2334_CR32","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 863\u2013874 (2024).","journal-title":"Nat. Med."},{"key":"2334_CR33","unstructured":"bioptimus\/releases. https:\/\/github.com\/bioptimus\/releases."},{"key":"2334_CR34","doi-asserted-by":"publisher","unstructured":"Nechaev, D., Pchelnikov, A. & Ivanova, E. Hibou: a family of foundational vision transformers for pathology. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2406.05074 (2024).","DOI":"10.48550\/arXiv.2406.05074"},{"key":"2334_CR35","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","volume":"630","author":"H Xu","year":"2024","unstructured":"Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181\u2013188 (2024).","journal-title":"Nature"},{"key":"2334_CR36","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","volume":"30","author":"E Vorontsov","year":"2024","unstructured":"Vorontsov, E. et al. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat. Med. 30, 2924\u20132935 (2024).","journal-title":"Nat. Med."},{"key":"2334_CR37","doi-asserted-by":"publisher","unstructured":"Mahmood, F. A benchmarking crisis in biomedical machine learning. Nat. Med. 1\u20131 https:\/\/doi.org\/10.1038\/s41591-025-03637-3 (2025).","DOI":"10.1038\/s41591-025-03637-3"},{"key":"2334_CR38","unstructured":"Ilse, M., Tomczak, J. & Welling, M. Attention-based Deep Multiple Instance Learning. In Proc. of the 35th International Conference on Machine Learning (eds Dy, J. & Krause, A.) 2127\u20132136 (PMLR, 2018)."},{"key":"2334_CR39","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":"2334_CR40","doi-asserted-by":"publisher","unstructured":"Kaczmarzyk, J. R., Saltz, J. H. & Koo, P. K. Explainable AI for computational pathology identifies model limitations and tissue biomarkers. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2409.03080 (2024).","DOI":"10.48550\/arXiv.2409.03080"},{"key":"2334_CR41","unstructured":"Javed, S. A. et al. Additive MIL: intrinsically interpretable multiple instance learning for pathology. In Advances in Neural Information Processing Systems (eds Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., & Oh, A.) 20689\u201320702 https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/hash\/82764461a05e933cc2fd9d312e107d12-Abstract-Conference.html (Curran Associates, Inc., 2022)."},{"key":"2334_CR42","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1016\/j.cell.2015.09.033","volume":"163","author":"G Ciriello","year":"2015","unstructured":"Ciriello, G. et al. Comprehensive molecular portraits of invasive lobular breast cancer. Cell 163, 506\u2013519 (2015).","journal-title":"Cell"},{"key":"2334_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45589-1","volume":"15","author":"OSM El Nahhas","year":"2024","unstructured":"El Nahhas, O. S. M. et al. Regression-based deep-Learning predicts molecular biomarkers from pathology slides. Nat. Commun. 15, 1253 (2024).","journal-title":"Nat. Commun."},{"key":"2334_CR44","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/sim.6370","volume":"34","author":"L Kang","year":"2015","unstructured":"Kang, L., Chen, W., Petrick, N. A. & Gallas, B. D. Comparing two correlated C indices with right-censored survival outcome: a one-shot nonparametric approach. Stat. Med. 34, 685\u2013703 (2015).","journal-title":"Stat. Med."},{"key":"2334_CR45","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.cell.2018.02.052","volume":"173","author":"J Liu","year":"2018","unstructured":"Liu, J. et al. An integrated TCGA Pan-Cancer Clinical Data Resource to drive high-quality survival outcome analytics. Cell 173, 400\u2013416.e11 (2018).","journal-title":"Cell"},{"key":"2334_CR46","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1038\/nrc.2017.32","volume":"17","author":"WG Kaelin","year":"2017","unstructured":"Kaelin, W. G. Common pitfalls in preclinical cancer target validation. Nat. Rev. Cancer 17, 441\u2013450 (2017).","journal-title":"Nat. Rev. Cancer"},{"key":"2334_CR47","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-57283-x","volume":"16","author":"KM Boehm","year":"2025","unstructured":"Boehm, K. M. et al. Multimodal histopathologic models stratify hormone receptor-positive early breast cancer. Nat. Commun. 16, 2106 (2025).","journal-title":"Nat. Commun."},{"key":"2334_CR48","doi-asserted-by":"publisher","DOI":"10.1200\/PO.24.00137","volume":"8","author":"SC Van Alsten","year":"2024","unstructured":"Van Alsten, S. C. et al. Differences in 21-gene and PAM50 recurrence scores in younger and black women with breast cancer. JCO Precis. Oncol. 8, e2400137 (2024).","journal-title":"JCO Precis. Oncol."},{"key":"2334_CR49","doi-asserted-by":"publisher","first-page":"2174","DOI":"10.1002\/cncr.28630","volume":"120","author":"BY Hair","year":"2014","unstructured":"Hair, B. Y., Hayes, S., Tse, C.-K., Bell, M. B. & Olshan, A. F. Racial differences in physical activity among breast cancer survivors: implications for breast cancer care. Cancer 120, 2174\u20132182 (2014).","journal-title":"Cancer"},{"key":"2334_CR50","first-page":"470","volume":"25","author":"EH Allott","year":"2016","unstructured":"Allott, E. H. et al. Performance of three-biomarker immunohistochemistry for intrinsic breast cancer subtyping in the AMBER Consortium. Cancer Epidemiol. Biomark. Prev. Publ. Am. Assoc. Cancer Res. Cosponsored Am. Soc. Prev. Oncol. 25, 470\u2013478 (2016).","journal-title":"Cancer Epidemiol. Biomark. Prev. Publ. Am. Assoc. Cancer Res. Cosponsored Am. Soc. Prev. Oncol."},{"key":"2334_CR51","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1038\/35021093","volume":"406","author":"CM Perou","year":"2000","unstructured":"Perou, C. M. et al. Molecular portraits of human breast tumours. Nature 406, 747\u2013752 (2000).","journal-title":"Nature"},{"key":"2334_CR52","doi-asserted-by":"publisher","first-page":"102559","DOI":"10.1016\/j.media.2022.102559","volume":"81","author":"X Wang","year":"2022","unstructured":"Wang, X. et al. Transformer-based unsupervised contrastive learning for histopathological image classification. Med. Image Anal. 81, 102559 (2022).","journal-title":"Med. Image Anal."},{"key":"2334_CR53","doi-asserted-by":"publisher","first-page":"103070","DOI":"10.1016\/j.media.2023.103070","volume":"93","author":"S Kapse","year":"2024","unstructured":"Kapse, S. et al. Attention de-sparsification matters: inducing diversity in digital pathology representation learning. Med. Image Anal. 93, 103070 (2024).","journal-title":"Med. Image Anal."},{"key":"2334_CR54","doi-asserted-by":"publisher","unstructured":"Ai, K. et al. Towards large-scale training of Pathology Foundation models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2404.15217 (2024).","DOI":"10.48550\/arXiv.2404.15217"},{"key":"2334_CR55","doi-asserted-by":"publisher","unstructured":"Filiot, A. et al. Scaling self-supervised learning for histopathology with masked image modeling. Preprint at https:\/\/doi.org\/10.1101\/2023.07.21.23292757 (2023).","DOI":"10.1101\/2023.07.21.23292757"},{"key":"2334_CR56","doi-asserted-by":"publisher","unstructured":"Filiot, A., Jacob, P., Kain, A. M. & Saillard, C. Phikon-v2, a large and public feature extractor for biomarker prediction. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2409.09173 (2024).","DOI":"10.48550\/arXiv.2409.09173"},{"key":"2334_CR57","doi-asserted-by":"publisher","unstructured":"Zimmermann, E. et al. Virchow2: scaling self-supervised mixed magnification models in pathology. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2408.00738 (2024).","DOI":"10.48550\/arXiv.2408.00738"},{"key":"2334_CR58","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (eds Agapito, L., Berg, T., Kosecka, J. & Zelnik-Manor, L.) 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2334_CR59","unstructured":"Oquab, M. et al. DINOv2: learning robust visual features without supervision. Transactions on Machine Learning Research. (2024)."},{"key":"2334_CR60","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44, 837\u2013845 (1988).","journal-title":"Biometrics"},{"key":"2334_CR61","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1037\/0033-2909.111.1.172","volume":"111","author":"X Meng","year":"1992","unstructured":"Meng, X., Rosenthal, R. & Rubin, D. B. Comparing correlated correlation coefficients. Psychol. Bull. 111, 172\u2013175 (1992).","journal-title":"Psychol. Bull."},{"key":"2334_CR62","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","volume":"57","author":"Y Benjamini","year":"1995","unstructured":"Benjamini, Y. & Hochberg, Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. Ser. B Methodol. 57, 289\u2013300 (1995).","journal-title":"J. R. Stat. Soc. Ser. B Methodol."},{"key":"2334_CR63","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32\u201335 (1950).","journal-title":"Cancer"},{"key":"2334_CR64","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":"2334_CR65","doi-asserted-by":"publisher","first-page":"9","DOI":"10.4103\/jpi.jpi_85_20","volume":"12","author":"PJ Sch\u00fcffler","year":"2021","unstructured":"Sch\u00fcffler, P. J., Yarlagadda, D. V. K., Vanderbilt, C. & Fuchs, T. J. Overcoming an annotation hurdle: digitizing pen annotations from whole slide images. J. Pathol. Inform. 12, 9 (2021).","journal-title":"J. Pathol. Inform."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02334-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02334-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02334-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:03:47Z","timestamp":1770815027000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02334-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2334"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02334-2","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]},"assertion":[{"value":"15 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The University of North Carolina, Chapel Hill has a license of intellectual property interest in GeneCentric Diagnostics and BioClassifier, LLC, which may be used in this study. The University of North Carolina, Chapel Hill may benefit from this interest that is\/are related to this research. The terms of this arrangement have been reviewed and approved by the University of North Carolina, Chapel Hill Conflict of Interest Program in accordance with its conflict of interest policies. J.H.S. and R.G. are co-founders of Chilean Wool, LLC. All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"149"}}