{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:54:14Z","timestamp":1785513254703,"version":"3.56.0"},"reference-count":41,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LGF21H030010"],"award-info":[{"award-number":["LGF21H030010"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["ZCLY24H1601"],"award-info":[{"award-number":["ZCLY24H1601"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFC2505100"],"award-info":[{"award-number":["2022YFC2505100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82403697"],"award-info":[{"award-number":["82403697"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017594","name":"Medical Science and Technology Project of Zhejiang Province","doi-asserted-by":"publisher","award":["2025KY411"],"award-info":[{"award-number":["2025KY411"]}],"id":[{"id":"10.13039\/501100017594","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pathsocjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["The Journal of Pathology"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The heterogeneity of breast cancer at molecular and histological levels poses significant challenges for precise diagnosis and treatment. Current molecular subtyping, crucial for guiding personalized therapy, relies on immunohistochemistry, which is often limited by intratumoral heterogeneity and potential sampling bias. While deep learning shows promise in digital pathology, existing models face computational and technical hurdles in capturing multiscale morphological features and long\u2010range dependencies from high\u2010resolution images, particularly in the context of tissue microarrays (TMAs). To address this, we developed and validated the pathomics breast cancer hierarchical image pyramid transformer (PBC\u2010HIPT), a novel deep learning framework designed for automated molecular subtyping from standard H&amp;E\u2010stained images. The PBC\u2010HIPT model utilizes a multilevel transformer\u2010based architecture to hierarchically aggregate histopathological features from the cellular to the tissue scale, enabling a comprehensive analysis. We trained and validated the model on a multi\u2010institutional cohort comprising 252 TMA cases and 46 independent whole\u2010slide images (WSIs), assessing its performance via five\u2010fold cross\u2010validation on three\u2010, four\u2010, and five\u2010class molecular subtyping tasks, as well as key biomarker [estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2), Ki\u201067] prediction, comparing it against several established multiple instance learning methods. PBC\u2010HIPT demonstrated superior performance, achieving a mean accuracy of 84.3% and a mean area under the curve (AUC) of 0.91 in the clinically critical three\u2010class subtyping task (luminal, HER2\u2010enriched, triple\u2010negative breast cancer), significantly outperforming baseline models. The framework excelled in biomarker prediction, attaining accuracies of 91.8% (AUC: 0.97) for ER status and 92.0% (AUC: 0.96) for PR status. It also achieved an accuracy of 73.8% (AUC: 0.81) for Ki\u201067 proliferation status and 84.6% (AUC: 0.85) for binary HER2 status classification. While the model showed robust intramodality generalization on TMAs (ER AUC\u2009&gt;\u20090.96), its performance dropped in WSI cross\u2010modality validation. In conclusion, the PBC\u2010HIPT model provides a robust, automated solution for accurate molecular subtyping and biomarker assessment from H&amp;E\u2010stained TMAs. \u00a9 2026 The Pathological Society of Great Britain and Ireland.<\/jats:p>","DOI":"10.1002\/path.70028","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:01:41Z","timestamp":1769493701000},"page":"460-476","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical image pyramid transformer framework for automated breast cancer molecular subtyping using tissue microarrays"],"prefix":"10.1002","volume":"268","author":[{"given":"Baizhou","family":"Li","sequence":"first","affiliation":[{"name":"Department of Pathology, Second Affiliated Hospital Zhejiang University School of Medicine  Zhejiang PR China"},{"name":"Department of Pathology, Fourth Affiliated Hospital Zhejiang University School of Medicine  Zhejiang PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Northwest University  Xi'an PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehang","family":"Xing","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Northwest University  Xi'an PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaojiao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Second Affiliated Hospital Zhejiang University School of Medicine  Zhejiang PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hansheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Northwest University  Xi'an PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Yang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Biomedical Images Analysis Lab, School of Engineering Westlake University  Zhejiang PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0210-6645","authenticated-orcid":false,"given":"Wuzhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Second Affiliated Hospital Zhejiang University School of Medicine  Zhejiang PR China"},{"name":"Key Laboratory of Tumor Microenvironment and Immune Therapy of Zhejiang Province, Second Affiliated Hospital Zhejiang University School of Medicine  Zhejiang PR China"},{"name":"Cancer Institute Zhejiang University  Zhejiang PR China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)31891-8"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1172\/JCI60534"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2018.19323"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/dju055"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14143469"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/onco.13841"},{"key":"e_1_2_8_8_1","article-title":"Training health workers in clinical breast examination for early detection of breast cancer in low\u2010 and middle\u2010income countries","volume":"4","author":"Sayed S","year":"2023","journal-title":"Cochrane Database Syst Rev"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2015.07.008"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.858453"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13010161"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993788"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105221"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2007.10.006"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.7b00807"},{"key":"e_1_2_8_16_1","first-page":"2127","volume-title":"Proceedings International Conference on Machine Learning","author":"Ilse M","year":"2018"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01076"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21896-9"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2025.3526848"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-60307-1"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110745"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3386197"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.21972"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2018.77.8738"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.19.02309"},{"key":"e_1_2_8_27_1","first-page":"23","article-title":"A threshold selection method from gray\u2010level histograms","volume":"11","author":"Otsu N","year":"1975","journal-title":"Automatica"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102275"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_2_8_30_1","first-page":"156","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li B","year":"2021"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3399740"},{"key":"e_1_2_8_32_1","unstructured":"WangD KhoslaA GargeyaR et al.Deep learning for identifying metastatic breast cancer.arXiv2016; 1606.05718. [Not peer reviewed]."},{"key":"e_1_2_8_33_1","unstructured":"LiuY GadepalliK NorouziM et al.Detecting cancer metastases on gigapixel pathology images arXiv2017; 1703.02442. [Not peer reviewed]."},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_35_1","first-page":"7082","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu J","year":"2022"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3241204"},{"key":"e_1_2_8_37_1","unstructured":"DosovitskiyA BeyerL KolesnikovA et al.An image is worth 16\u2009\u00d7\u200916 words: Transformers for image recognition at scale.arXiv2020; 2010.11929. [Not peer reviewed]."},{"key":"e_1_2_8_38_1","first-page":"16144","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen RJ","year":"2022"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-024-02108-4"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2019.00193"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106395"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110424"}],"container-title":["The Journal of Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/path.70028","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/path.70028","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/path.70028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T13:07:34Z","timestamp":1773407254000},"score":1,"resource":{"primary":{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/10.1002\/path.70028"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1002\/path.70028"],"URL":"https:\/\/doi.org\/10.1002\/path.70028","archive":["Portico"],"relation":{},"ISSN":["0022-3417","1096-9896"],"issn-type":[{"value":"0022-3417","type":"print"},{"value":"1096-9896","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"assertion":[{"value":"2024-12-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}