{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:03:24Z","timestamp":1790154204773,"version":"4.0.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Immunohistochemistry (IHC) remains the gold standard for assessing key breast cancer biomarkers such as estrogen receptor (ER) and progesterone receptor (PR). However, the staining process is resource-intensive, time-consuming, and dependent on specialized laboratory infrastructure. While recent advances in computational pathology have demonstrated the feasibility of predicting biomarker status directly from hematoxylin and eosin (H&amp;amp;E) stained tissue, most models lack visual interpretability, limiting clinical trust and adoption.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a two-stage deep learning pipeline for virtual immunohistochemistry. In Stage 1, a regression-based convolutional neural network predicts continuous ER\/PR positivity from H&amp;amp;E image patches trained using a mean-squared-error objective; an Edge-Focused Loss was explored as an alternative but was not adopted. In Stage 2, the predicted biomarker percentage is incorporated as a spatial condition into a conditional generative adversarial network (cGAN), enabling the synthesis of virtual IHC images. The framework was evaluated on the IHC4BC dataset using 5-fold patient-level cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The predictive model achieved a mean absolute error (MAE) of 9.14% for ER and 6.10% for PR under 5-fold patient-level cross-validation; treated as a clinical positive\/negative classifier it reached an area under the ROC curve of 0.92 for ER and 0.74 for PR. The generative stage produced visually plausible virtual IHC images with biologically meaningful nuclear staining patterns. Although pixel-based metrics (SSIM and PSNR) favored the unconditioned baseline, domain-specific analysis of the deconvolved DAB channel showed substantially improved biomarker-specific staining fidelity for the conditional framework. For PR, the correlation between the generated DAB signal and ground-truth positivity increased from 0.32 (unconditioned baseline) to 0.61 in the deployed pipeline, reaching 0.82 under oracle conditioning, illustrating both the benefit of conditioning and the residual error propagated from Stage 1.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This proof-of-concept study presents a dual-output computational framework that integrates quantitative biomarker prediction with interpretable virtual staining. The proposed approach may support preliminary biomarker assessment and workflow prioritization, particularly in resource-limited settings. However, external validation and domain-specific evaluation metrics are required before clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1867968","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T04:33:57Z","timestamp":1789533237000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Virtual immunohistochemistry for ER and PR prediction in breast cancer histopathology: a two-stage conditional generative framework"],"prefix":"10.3389","volume":"16","author":[{"given":"Hiba","family":"Alzoubi","sequence":"first","affiliation":[{"name":"Department of Basic Pathological Sciences, Faculty of Medicine, Yarmouk University","place":["Irbid, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulla","family":"Shatarah","sequence":"additional","affiliation":[{"name":"Cirrusgo","place":["Amman, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulrhman","family":"Sanajleh","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Yarmouk University","place":["Irbid, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maher","family":"Sughayer","sequence":"additional","affiliation":[{"name":"Department of Pathology, King Hussein Cancer Center","place":["Amman, Jordan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"B1","article-title":"Global breast cancer initiative implementation framework","year":"2023","journal-title":"WHO"},{"key":"B2","doi-asserted-by":"publisher","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":"B3","doi-asserted-by":"publisher","first-page":"3469","DOI":"10.3390\/cancers14143469","article-title":"From immunohistochemistry to new digital ecosystems","volume":"14","author":"Hacking","year":"2022","journal-title":"Cancers"},{"key":"B4","doi-asserted-by":"publisher","first-page":"298","DOI":"10.5858\/arpa.2024-0215-ra","article-title":"Generative AI in anatomic pathology","volume":"149","author":"Brodsky","year":"2025","journal-title":"Arch Pathol Lab Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12122022","article-title":"Deep learning-based prediction of molecular tumor biomarkers from H&E: a practical review","volume":"12","author":"Couture","year":"2022","journal-title":"J Pers Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"5727","DOI":"10.1038\/s41467-020-19334-3","article-title":"Deep learning-enabled breast cancer hormonal receptor status determination from H&E stains","volume":"11","author":"Naik","year":"2020","journal-title":"Nat Commun"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1038\/s41467-024-45589-1","article-title":"Regression-based deep-learning predicts molecular biomarkers from pathology slides","volume":"15","author":"El Nahhas","year":"2024","journal-title":"Nat Commun"},{"key":"B8","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s43856-024-00471-5","article-title":"A systematic pan-cancer study on DL-based prediction of multi-omic biomarkers","volume":"4","author":"Arslan","year":"2024","journal-title":"Commun Med"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/s2589-7500(20)30159-x","article-title":"An AI algorithm for prostate cancer diagnosis in WSIs: a blinded clinical validation","volume":"2","author":"Pantanowitz","year":"2020","journal-title":"Lancet Digit Health"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on WSIs","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat Med"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2024.02.009","article-title":"Virtual staining for histology by deep learning","volume":"42","author":"Latonen","year":"2024","journal-title":"Trends Biotechnol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1038\/s41746-025-01741-9","article-title":"H&E to IHC virtual staining methods in breast cancer: overview and benchmarking","volume":"8","author":"Kl\u00f6ckner","year":"2025","journal-title":"NPJ Digit Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43987-2_61","article-title":"Adaptive supervised PatchNCE loss for learning H&E-to-IHC stain translation with inconsistent groundtruth image pairs","volume":"14225","author":"Li","year":"2023","journal-title":"MICCAI"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00889-5","article-title":"Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling","volume":"6","author":"Pati","year":"2024","journal-title":"Nat Mach Intell"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw56347.2022.00198","article-title":"BCI: Breast cancer immunohistochemical image generation through pyramid pix2pix","author":"Liu","year":"2022","journal-title":"Proc IEEE\/CVF CVPR Workshops"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2025.105708","article-title":"A review of breast cancer histopathology image analysis with deep learning: challenges, innovations, and clinical integration","volume":"162","author":"Haq","year":"2025","journal-title":"Image Vision Comput"},{"key":"B17","doi-asserted-by":"publisher","first-page":"7011984","DOI":"10.1155\/acis\/7011984","article-title":"Image-Based Breast Cancer Histopathology Classification and Diagnosis Using Deep Learning Approaches","volume":"2025","author":"Aldakhil","year":"2025","journal-title":"Appl Comput Intell Soft Comput"},{"key":"B18","doi-asserted-by":"publisher","first-page":"24633","DOI":"10.1038\/s41598-025-00930-6","article-title":"A hybrid deep learning model EfficientNet with GRU for breast cancer detection from histopathology images","volume":"15","author":"Pradeepa","year":"2025","journal-title":"Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3574210","article-title":"HistoDX: Revolutionizing Breast Cancer Diagnosis Through Advanced Imaging Techniques","volume":"13","author":"Arshad","year":"2025","journal-title":"IEEE Access"},{"key":"B20","doi-asserted-by":"publisher","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":"B21","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1038\/s43856-024-00695-5","article-title":"Clinical utility of receptor status prediction in breast cancer and misdiagnosis identification using deep learning on hematoxylin and eosin-stained slides","volume":"4","author":"Shamai","year":"2024","journal-title":"Commun Med"},{"key":"B22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/s41377-023-01104-7","article-title":"Deep learning-enabled virtual histological staining of biological samples","volume":"12","author":"Bai","year":"2023","journal-title":"Light Sci Appl"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.34133\/2022\/9818965","article-title":"Virtual staining of defocused autofluorescence images using deep neural networks","volume":"2022","author":"Zhang","year":"2022","journal-title":"Intell Comput"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_1","article-title":"Advancing H&E-to-IHC virtual staining with task-specific domain knowledge for HER2 scoring","volume":"15004","author":"Peng","year":"2024","journal-title":"MICCAI 2024"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-71038-2","article-title":"Generative AI for misalignment-resistant virtual staining","volume":"17","author":"Ma","year":"2026","journal-title":"Nat Commun"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016","journal-title":"Proc IEEE CVPR"},{"key":"B27","article-title":"EfficientNet: Rethinking model scaling for CNNs","volume":"97","author":"Tan","year":"2019","journal-title":"Proc ICML"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on WSIs","volume":"5","author":"Lu","year":"2021","journal-title":"Nat BioMed Eng"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"NeurIPS"},{"key":"B30","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1145\/3422622","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.632","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017","journal-title":"Proc IEEE CVPR"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017","journal-title":"Proc IEEE ICCV"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-019-0362-y","article-title":"Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning","volume":"3","author":"Rivenson","year":"2019","journal-title":"Nat BioMed Eng"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/EMBC46164.2021.9629970","article-title":"Automatic multi-stain registration of whole slide images in histopathology","volume-title":"IEEE EMBC","author":"Shafique","year":"2021"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-resolution image synthesis with latent diffusion models","volume-title":"Proc. IEEE\/CVF CVPR","author":"Rombach","year":"2022"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nat Med"},{"key":"B38","doi-asserted-by":"publisher","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"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1867968\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:15:27Z","timestamp":1790151327000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1867968\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,16]]},"references-count":38,"alternative-id":["10.3389\/fonc.2026.1867968"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1867968","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,16]]},"article-number":"1867968"}}