{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:46:45Z","timestamp":1790704005709,"version":"4.1.0"},"reference-count":20,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>HER2 is a critical prognostic biomarker in breast cancer and associated with aggressive tumor biology. Current IHC scoring is subjective and labor-intensive. Deep learning has demonstrated success in histopathological image analysis, yet HER2 IHC automation remains underexplored. External-center validation is essential to establish clinical credibility and demonstrate robustness across diverse institutional practices and imaging protocols.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This dual-center retrospective study analyzed 135 HER2 IHC whole-slide images from 118 breast cancer patients labeled as 1+, 2+, or 3+ by standard clinical criteria. Two board-certified pathologists manually annotated tumor-enriched ROIs, which were tiled into non-overlapping 512x512 patches; tiles with &amp;gt;60% white background were excluded. Patches were harmonized using a modified Macenko color normalization and augmented during training. Six pretrained deep learning models (AlexNet, VGG16, ResNet34, DenseNet121, Inception, Swin Transformer) were trained with patient-level splits and evaluated on an independent test set using macro-averaged AUC and complementary metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The cohort included 118 patients with comparable age and largely similar baseline imaging\/pathologic characteristics across groups, although clinical symptoms and lymph node status differed. On the independent test set, all models showed good discrimination for three-class HER2 grading, with AlexNet performing best (macro-AUC 0.971), followed by VGG16 (0.967). For AlexNet, per-class AUCs were 0.980 (1+), 0.955 (2+), and 0.979 (3+); most errors occurred between adjacent grades (1+\/2+, 2+\/3+). Grad-CAM highlighted strongly stained tumor regions driving predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A deep learning framework showed encouraging patch-level performance for three-class HER2 IHC score prediction in a pooled dual-center retrospective cohort. This approach may assist pathologists by improving scoring consistency and identifying borderline or low-confidence cases that require careful review and, when clinically indicated, confirmatory testing.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1868102","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:44:41Z","timestamp":1782384281000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning based automated HER2 score prediction using immunohistochemistry histopathological images: a dual-center study"],"prefix":"10.3389","volume":"17","author":[{"given":"Juan","family":"Ma","sequence":"first","affiliation":[{"name":"Medical Imaging Center, Xinjiang Medical University Affiliated Fourth Hospital","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Song","sequence":"additional","affiliation":[{"name":"Medical Imaging Center, Xinjiang Medical University Affiliated Fourth Hospital","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mireguli","family":"Damaola","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Medical Imaging Center, Xinjiang Medical University Affiliated Fourth Hospital","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"You","sequence":"additional","affiliation":[{"name":"Department of Deepwise AI lab, Hangzhou Deepwise & League of PHD Technology Co., Ltd","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiongling","family":"Tian","sequence":"additional","affiliation":[{"name":"Medical Imaging Center, Xinjiang Medical University Affiliated Fourth Hospital","place":["Urumqi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abudushalamu","family":"Abulaiti","sequence":"additional","affiliation":[{"name":"Department of Ultrasonography, Shule County People\u2019s Hospital","place":["Kashi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diliaremi","family":"Aihaiti","sequence":"additional","affiliation":[{"name":"Department of Radiology, The First People's Hospital of Kashi (Kashgar) Prefecture","place":["Kashi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayidili","family":"Nijiati","sequence":"additional","affiliation":[{"name":"Medical Imaging Center, Xinjiang Medical University Affiliated Fourth Hospital","place":["Urumqi, China"]},{"name":"Department of Ultrasonography, Xinjiang Key Laboratory of Artificial Intelligence assisted Imaging Diagnosis","place":["Kashi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1097\/pai.0000000000001258","article-title":"Toward accurate deep learning-based prediction of Ki67, ER, PR, and HER2 status from H&E-stained breast cancer images","volume":"33","author":"Akbarnejad","year":"2025","journal-title":"Appl. Immunohistochem. Mol. Morphol."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.2196\/45547","article-title":"Data-efficient computational pathology platform for faster and cheaper breast cancer subtype identifications: Development of a deep learning model","volume":"9","author":"Bae","year":"2023","journal-title":"JMIR Cancer"},{"key":"B3","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1111\/his.15274","article-title":"Development of a deep-learning model tailored for HER2 detection in breast cancer to aid pathologists in interpreting HER2-low cases","volume":"85","author":"Bannier","year":"2024","journal-title":"Histopathology"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104730","article-title":"Deep learning for colon cancer histopathological images analysis","volume":"136","author":"Ben Hamida","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15151895","article-title":"Deep learning-based recurrence prediction in HER2-low breast cancer: Comparison of MRI-alone, clinicopathologic-alone, and combined models","volume":"15","author":"Choi","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2243","DOI":"10.17305\/bb.2025.12475","article-title":"Deep learning predicts HER2 status in invasive breast cancer from multimodal ultrasound and MRI","volume":"25","author":"Fan","year":"2025","journal-title":"Biomol. Biomed."},{"key":"B7","doi-asserted-by":"publisher","first-page":"19075","DOI":"10.1038\/s41598-022-23166-0","article-title":"Deep learning-based framework for slide-based histopathological image analysis","volume":"12","author":"Kosaraju","year":"2022","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2025.110429","article-title":"MRI-based habitat analysis for intratumoral heterogeneity quantification combined with deep learning for HER2 status prediction in breast cancer","volume":"122","author":"Li","year":"2025","journal-title":"Magn. Reson. Imaging"},{"key":"B9","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.semcancer.2020.02.016","article-title":"Evolving concepts in HER2 evaluation in breast cancer: Heterogeneity, HER2-low carcinomas and beyond","volume":"72","author":"Marchi\u00f2","year":"2021","journal-title":"Semin. Cancer Biol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41571-019-0268-3","article-title":"HER2-targeted therapies - a role beyond breast cancer","volume":"17","author":"Oh","year":"2020","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"2189","DOI":"10.1109\/TIP.2018.2795742","article-title":"Her2Net: A deep framework for semantic segmentation and classification of cell membranes and nuclei in breast cancer evaluation","volume":"27","author":"Saha","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10238-021-00781-1","article-title":"A review of prognostic and predictive biomarkers in breast cancer","volume":"23","author":"Tarighati","year":"2023","journal-title":"Clin. Exp. Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1007\/s10278-021-00442-5","article-title":"HER2 molecular marker scoring using transfer learning and decision level fusion","volume":"34","author":"Tewary","year":"2021","journal-title":"J. Digit Imaging"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/srep45938","article-title":"Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer","volume":"7","author":"Vandenberghe","year":"2017","journal-title":"Sci. Rep."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106340","article-title":"Automatic diagnosis and grading of prostate cancer with weakly supervised learning on whole slide images","volume":"152","author":"Xiang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.829041","article-title":"Predicting HER2 status in breast cancer on ultrasound images using deep learning method","volume":"12","author":"Xu","year":"2022","journal-title":"Front. Oncol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.csbj.2021.12.028","article-title":"Prediction of HER2-positive breast cancer recurrence and metastasis risk from histopathological images and clinical information via multimodal deep learning","volume":"20","author":"Yang","year":"2022","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B19","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1038\/s41571-024-00924-9","article-title":"HER2-targeted therapies beyond breast cancer - an update","volume":"21","author":"Yoon","year":"2024","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.breast.2023.06.005","article-title":"Concordance of HER2-low scoring in breast carcinoma among expert pathologists in the United Kingdom and the republic of Ireland -on behalf of the UK national coordinating committee for breast pathology","volume":"70","author":"Zaakouk","year":"2023","journal-title":"Breast"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1868102\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T10:44:42Z","timestamp":1782384282000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1868102\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":20,"alternative-id":["10.3389\/fphys.2026.1868102"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1868102","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"article-number":"1868102"}}