{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T06:48:15Z","timestamp":1785739695194,"version":"3.56.0"},"reference-count":37,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Breast cancer biomarker detection through immunohistochemistry (IHC) is essential for treatment planning but faces challenges including turnaround time, variability, and laboratory resource constraints. Large open-source vision-language foundation models offer a potential avenue for inferring biomarker status directly from hematoxylin-and-eosin (H&amp;E)-stained whole-slide images (WSIs). Methods: We evaluated two open-source pathology foundation models\u2014TITAN (Transformer-based Pathology Image and Text Alignment Network, approximately 48.5 M parameters) and CHIEF (Clinical Histopathology Imaging Evaluation Foundation Model, approximately 1.2 M parameters)\u2014for predicting estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status from H&amp;E-stained breast cancer WSIs. WSI data were obtained from The Cancer Genome Atlas Breast Invasive Carcinoma collection (TCGA-BRCA) via the NCI Imaging Data Commons, with biomarker labels from the NCI Genomic Data Commons. In total, 937 cases (995 WSIs; 78.3% ER-positive) were evaluated for ER, 934 cases (992 WSIs; 68.4% PR-positive) for PR, and 646 cases (691 WSIs; 21.1% HER2-positive) for HER2. All evaluation was performed under a strict patient-level 50\/25\/25 split with 10 independent random partitions; metrics are reported as the mean across partitions with percentile-based 95% confidence intervals. Performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, specificity, and positive predictive value (PPV). Results: TITAN and CHIEF achieved comparable performance for ER (TITAN AUROC: 0.885 [95% CI: 0.848, 0.921], AUPRC: 0.954 [0.940, 0.964]; CHIEF AUROC: 0.877 [0.831, 0.914], AUPRC: 0.955 [0.938, 0.969]) and PR (TITAN AUROC: 0.799, AUPRC: 0.868; CHIEF AUROC: 0.791, AUPRC: 0.864). At the default 0.5 operating point, ER PPV was 0.90 and PR PPV was 0.79\u20130.81. For HER2, both models achieved AUROC values of 0.71\u20130.74 and AUPRC values of 0.41\u20130.45\u2014well above the prevalence-based random baseline (approximately 0.211)\u2014but default-threshold sensitivity was very low (approximately 0.07\u20130.08), reflecting class imbalance and the use of an uncalibrated default threshold rather than a categorical absence of morphologic signal. Conclusions: Under retrospective evaluation, both models demonstrate strong discriminative performance for ER and moderate performance for PR; HER2 prediction at the default operating point is limited and motivates threshold-calibration and multimodal extensions before any clinical use. AUPRC summarizes precision\u2212recall behavior across thresholds and is distinct from threshold-specific precision (PPV); the two should be reported together for clinical-utility assessment in pathology AI. The findings are hypothesis-generating and motivate prospective external validation across independent institutional cohorts before any clinical deployment is considered.<\/jats:p>","DOI":"10.3390\/cancers18152475","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T06:17:40Z","timestamp":1785737860000},"page":"2475","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Open-Source Pathology Foundation Models for Breast Cancer Biomarker Prediction from H&amp;E Whole-Slide Images"],"prefix":"10.3390","volume":"18","author":[{"given":"Samir","family":"Atiya","sequence":"first","affiliation":[{"name":"Department of Pathology, University of Chicago Medical Center, Chicago, IL 60637, USA"},{"name":"Biological Science Division, University of Chicago, Chicago, IL 60637, USA"},{"name":"Trillium Health Partners, Mississauga, ON L5B 1B8, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayou","family":"Liang","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kwaku","family":"Ofori-Atta","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Peng","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huili","family":"Wang","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3706-2320","authenticated-orcid":false,"given":"Ankush","family":"Patel","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"},{"name":"Department of Pathology, Ohio State University, Colombus, OH 43210, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mary","family":"Edgertion","sequence":"additional","affiliation":[{"name":"Department of Pathology, University of Nebraska Medical Center, Omaha, NE 68106, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0316-8365","authenticated-orcid":false,"given":"Junhan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, University of Chicago Medical Center, Chicago, IL 60637, USA"},{"name":"Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA"},{"name":"Department of Surgery, Massachusetts General Hospitals, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Utku","family":"Pamuksuz","sequence":"additional","affiliation":[{"name":"Data Science Institute, University of Chicago, Chicago, IL 60615, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.1200\/JCO.2009.25.6529","article-title":"American Society of Clinical Oncology\/College of American Pathologists Guideline Recommendations for Immunohistochemical Testing of Estrogen and Progesterone Receptors in Breast Cancer","volume":"28","author":"Hammond","year":"2010","journal-title":"J. Clin. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.1200\/JCO.2018.77.8738","article-title":"Human Epidermal Growth Factor Receptor 2 Testing in Breast Cancer: American Society of Clinical Oncology\/College of American Pathologists Clinical Practice Guideline Focused Update","volume":"36","author":"Wolff","year":"2018","journal-title":"J. Clin. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"349","DOI":"10.5858\/2008-132-349-AOITBL","article-title":"Application of Immunohistochemistry to Breast Lesions","volume":"132","author":"Yeh","year":"2008","journal-title":"Arch. Pathol. Lab. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3867","DOI":"10.1200\/JCO.22.02864","article-title":"Human Epidermal Growth Factor Receptor 2 Testing in Breast Cancer: ASCO\u2013College of American Pathologists Guideline Update","volume":"41","author":"Wolff","year":"2023","journal-title":"J. Clin. Oncol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1710","DOI":"10.5858\/arpa.2013-0093-CP","article-title":"Validating Whole Slide Imaging for Diagnostic Purposes in Pathology: Guideline from the College of American Pathologists Pathology and Laboratory Quality Center","volume":"137","author":"Pantanowitz","year":"2013","journal-title":"Arch. Pathol. Lab. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1723","DOI":"10.5858\/arpa.2013-0200-OA","article-title":"Pathologist Workforce in the United States: I. Development of a Predictive Model to Examine Factors Influencing Supply","volume":"137","author":"Robboy","year":"2013","journal-title":"Arch. Pathol. Lab. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1016\/j.ajpath.2020.10.018","article-title":"Challenges in the Development, Deployment, and Regulation of Artificial Intelligence in Anatomic Pathology","volume":"191","author":"Cheng","year":"2021","journal-title":"Am. J. Pathol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1016\/j.ccell.2022.07.004","article-title":"Pan-cancer integrative histology-genomic analysis via multimodal deep learning","volume":"40","author":"Chen","year":"2022","journal-title":"Cancer Cell"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","article-title":"A visual-language foundation model for computational pathology","volume":"30","author":"Lu","year":"2024","journal-title":"Nat. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1038\/s41571-019-0252-y","article-title":"Artificial intelligence in digital pathology\u2014New tools for diagnosis and precision oncology","volume":"16","author":"Bera","year":"2019","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1038\/s41586-021-04301-9","article-title":"Magnetic control of tokamak plasmas through deep reinforcement learning","volume":"602","author":"Degrave","year":"2022","journal-title":"Nature"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4423","DOI":"10.1038\/s41467-021-24698-1","article-title":"The impact of site-specific digital histology signatures on deep learning model accuracy and bias","volume":"12","author":"Howard","year":"2021","journal-title":"Nat. Commun."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1109\/JBHI.2020.3032060","article-title":"Measuring Domain Shift for Deep Learning in Histopathology","volume":"25","author":"Stacke","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_15","unstructured":"Holzinger, A., Biemann, C., Pattichis, C.S., and Kell, D.B. (2017). What do we need to build explainable AI systems for the medical domain?. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1038\/s41746-020-00367-3","article-title":"Second opinion needed: Communicating uncertainty in medical machine learning","volume":"4","author":"Kompa","year":"2021","journal-title":"npj Digit. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Bareja, R., Carrillo-Perez, F., Zheng, Y., Pizurica, M., Nandi, T.N., Shen, J., Madduri, R., and Gevaert, O. (2025). Evaluating Vision and Pathology Foundation Models for Computational Pathology: A Comprehensive Benchmark Study. medRxiv.","DOI":"10.1101\/2025.05.08.25327250"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1056\/NEJMoa2203690","article-title":"Trastuzumab Deruxtecan in Previously Treated HER2-Low Advanced Breast Cancer","volume":"387","author":"Modi","year":"2022","journal-title":"N. Engl. J. Med."},{"key":"ref_20","unstructured":"Ding, T., Wagner, S.J., Song, A.H., Chen, R.J., Lu, M.Y., Zhang, A., Vaidya, A.J., Jaume, G., Shaban, M., and Kim, A. (2024). Multimodal whole slide foundation model for pathology. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1038\/s41746-022-00689-4","article-title":"Integrated multimodal artificial intelligence framework for healthcare applications","volume":"5","author":"Soenksen","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4188","DOI":"10.1158\/0008-5472.CAN-21-0950","article-title":"NCI Imaging Data Commons","volume":"81","author":"Fedorov","year":"2021","journal-title":"Cancer Res."},{"key":"ref_24","unstructured":"Lingle, W., Erickson, B.J., Zuley, M.L., Jarosz, R., Bonaccio, E., Filippini, J., Net, J.M., Levi, L., Morris, E.A., and Figler, G.G. (2016). The Cancer Genome Atlas Breast Invasive Carcinoma Collection (TCGA-BRCA) [Data set]. Cancer Imaging Arch."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"The Cancer Genome Atlas Network (2012). Comprehensive molecular portraits of human breast tumours. Nature, 490, 61\u201370.","DOI":"10.1038\/nature11412"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1182\/blood-2017-03-735654","article-title":"The NCI Genomic Data Commons as an engine for precision medicine","volume":"130","author":"Jensen","year":"2017","journal-title":"Blood"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1346","DOI":"10.1200\/JCO.19.02309","article-title":"Estrogen and Progesterone Receptor Testing in Breast Cancer: ASCO\/CAP Guideline Update","volume":"38","author":"Allison","year":"2020","journal-title":"J. Clin. Oncol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1038\/s41573-022-00579-0","article-title":"Targeting HER2-positive breast cancer: Advances and future directions","volume":"22","author":"Swain","year":"2022","journal-title":"Nat. Rev. Drug Discov."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1038\/s43856-021-00013-3","article-title":"Determining breast cancer biomarker status and associated morphological features using deep learning","volume":"1","author":"Gamble","year":"2021","journal-title":"Commun. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1186\/s13058-019-1165-5","article-title":"A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk","volume":"21","author":"Klimov","year":"2019","journal-title":"Breast Cancer Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.critrevonc.2016.12.006","article-title":"How could breast cancer molecular features contribute to locoregional treatment decision making?","volume":"110","author":"Tsoutsou","year":"2017","journal-title":"Crit. Rev. Oncol. Hematol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"5727","DOI":"10.1038\/s41467-020-19334-3","article-title":"Deep learning-enabled breast cancer hormonal receptor status determination from base-level H&E stains","volume":"11","author":"Naik","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1016\/S1470-2045(19)30154-8","article-title":"Digital pathology and artificial intelligence","volume":"20","author":"Niazi","year":"2019","journal-title":"Lancet Oncol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"2786","DOI":"10.1093\/annonc\/mdt350","article-title":"Ki67 levels as predictive and prognostic parameters in pretherapeutic breast cancer core biopsies: A translational investigation in the neoadjuvant GeparTrio trial","volume":"24","author":"Denkert","year":"2013","journal-title":"Ann. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1016\/j.ccell.2022.09.012","article-title":"Artificial intelligence for multimodal data integration in oncology","volume":"40","author":"Lipkova","year":"2022","journal-title":"Cancer Cell"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., Chen, B., Zhang, A., Williamson, D.F.K., Chen, R.J., Ding, T., Le, L.P., Chuang, Y.-S., and Mahmood, F. (2023, January 18\u201322). Visual language pretrained multiple instance zero-shot transfer for histopathology images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"107979","DOI":"10.1016\/j.neunet.2025.107979","article-title":"Enhancing feature discrimination with pseudo-labels for foundation model in segmentation of 3D medical images","volume":"193","author":"Jin","year":"2026","journal-title":"Neural Netw."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/15\/2475\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T06:33:00Z","timestamp":1785738780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/15\/2475"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":37,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["cancers18152475"],"URL":"https:\/\/doi.org\/10.3390\/cancers18152475","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,1]]}}}