{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:39:05Z","timestamp":1783363145521,"version":"3.54.6"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013516","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000}}],"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Chemical staining methods, while reliable, are time consuming and can be resource-intensive, involving costly chemical reagents and raising environmental concerns. This underscores the compelling need for alternative solutions such as virtual staining, which not only accelerates the diagnostic process but also enhances the flexibility of stain applications without the associated physical and chemical costs. Generative artificial intelligence technologies prove to be immensely useful in addressing these challenges. However, in healthcare, particularly within computational pathology, the high-stakes nature of decisions complicates the adoption of these tools due to their often opaque processes. Our work introduces an innovative approach that harnesses generative models for virtual stain transformations, improving performance, trustworthiness, scalability, and adaptability within computational pathology. The core of the proposed methodology involves a singular Hematoxylin and Eosin (H&amp;E) encoder that supports multiple stain decoders. This design prioritizes critical regions in the latent space of H&amp;E tissues, leading to a richer representation that enables precise synthetic stain generation by the decoders. Tested to simultaneously generate eight different stains from a single H&amp;E slide, our method also offers significant scalability benefits for routine use by loading only necessary model components during production. We integrate label-free knowledge during training, using loss functions and regularization to minimize artifacts, thereby enhancing the accuracy of virtual staining in both paired and unpaired settings. To build trust in these synthetic stains, we employ a real-time self-inspection methodology using trained discriminators for each stain type, providing pathologists with confidence heatmaps to aid in their evaluations. In addition, we perform automatic quality checks on new H&amp;E slides to ensure that they conform to the trained H&amp;E distribution, guaranteeing the generation of high-quality synthetic stained slides. Recognizing the challenges pathologists face in adopting new technologies, we have encapsulated our method in an open-source, cloud-based proof-of-concept system. This system enables users to easily and virtually stain their H&amp;E slides through a browser, eliminating the need for specialized technical knowledge and addressing common hardware and software challenges. It also facilitates real-time user feedback integration. Lastly, we have curated a novel dataset comprising eight different paired H&amp;E\/stains related to pediatric Crohn\u2019s disease at diagnosis, providing 30 whole slide images (WSIs) for each stain set (total of 480 WSIs) to stimulate further research in computational pathology.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013516","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T17:44:43Z","timestamp":1761068683000},"page":"e1013516","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":8,"title":["Scalable, trustworthy generative model for virtual multi-staining from H&amp;E whole slide images"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0655-8112","authenticated-orcid":true,"given":"Mehdi","family":"Ounissi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4437-7897","authenticated-orcid":true,"given":"Ilias","family":"Sarbout","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Pierre","family":"Hugot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christine","family":"Martinez-Vinson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominique","family":"Berrebi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Racoceanu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"key":"pcbi.1013516.ref001","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.compmedimag.2017.12.001","article-title":"Efficient deep learning model for mitosis detection using breast histopathology images","volume":"64","author":"M Saha","year":"2018","journal-title":"Comput Med Imaging Graph"},{"issue":"4","key":"pcbi.1013516.ref002","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1038\/s41416-020-01122-x","article-title":"Deep learning in cancer pathology: a new generation of clinical biomarkers","volume":"124","author":"A Echle","year":"2021","journal-title":"Br J Cancer"},{"key":"pcbi.1013516.ref003","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1007\/978-1-4939-8935-5_25","article-title":"An introduction to the performance of immunohistochemistry","volume":"1897","author":"S Magaki","year":"2019","journal-title":"Methods Mol Biol"},{"issue":"1","key":"pcbi.1013516.ref004","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s13000-022-01197-5","article-title":"Immunohistochemical diagnosis of human infectious diseases: a review","volume":"17","author":"H Oumarou Hama","year":"2022","journal-title":"Diagn Pathol"},{"issue":"1","key":"pcbi.1013516.ref005","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41377-023-01104-7","article-title":"Deep learning-enabled virtual histological staining of biological samples","volume":"12","author":"B Bai","year":"2023","journal-title":"Light Sci Appl"},{"issue":"1","key":"pcbi.1013516.ref006","doi-asserted-by":"crossref","first-page":"4884","DOI":"10.1038\/s41467-021-25221-2","article-title":"Deep learning-based transformation of H&E stained tissues into special stains","volume":"12","author":"K de Haan","year":"2021","journal-title":"Nat Commun"},{"issue":"3","key":"pcbi.1013516.ref007","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1364\/BOE.10.001339","article-title":"Digital staining through the application of deep neural networks to multi-modal multi-photon microscopy","volume":"10","author":"N Borhani","year":"2019","journal-title":"Biomed Opt Express"},{"key":"pcbi.1013516.ref008","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/s41377-019-0129-y","article-title":"PhaseStain: the digital staining of label-free quantitative phase microscopy images using deep learning","volume":"8","author":"Y Rivenson","year":"2019","journal-title":"Light Sci Appl"},{"key":"pcbi.1013516.ref009","doi-asserted-by":"crossref","unstructured":"Abraham T, Costa PC, Filan CE, Robles F, Levenson RM. Mode-mapping qOBM microscopy to virtual hematoxylin and eosin (H&E) histology via deep learning. In: Unconventional Optical Imaging III. 2022. p. 58. https:\/\/doi.org\/10.1117\/12.2622160","DOI":"10.1117\/12.2622160"},{"key":"pcbi.1013516.ref010","article-title":"Artificial intelligence for pathology: challenges and opportunities","author":"F Ciompi","year":"2017","journal-title":"Journal of Clinical Pathology"},{"issue":"1","key":"pcbi.1013516.ref011","doi-asserted-by":"crossref","first-page":"17507","DOI":"10.1038\/s41598-020-74500-3","article-title":"SHIFT: speedy histological-to-immunofluorescent translation of a tumor signature enabled by deep learning","volume":"10","author":"EA Burlingame","year":"2020","journal-title":"Sci Rep"},{"issue":"1","key":"pcbi.1013516.ref012","doi-asserted-by":"crossref","first-page":"19255","DOI":"10.1038\/s41598-021-98857-1","article-title":"Deep learning-based virtual cytokeratin staining of gastric carcinomas to measure tumor-stroma ratio","volume":"11","author":"Y Hong","year":"2021","journal-title":"Sci Rep"},{"issue":"2","key":"pcbi.1013516.ref013","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1158\/0008-5472.CAN-21-2843","article-title":"Prostate cancer risk stratification via nondestructive 3D pathology with deep learning-assisted gland analysis","volume":"82","author":"W Xie","year":"2022","journal-title":"Cancer Res"},{"key":"pcbi.1013516.ref014","doi-asserted-by":"crossref","unstructured":"Liu S, Zhu C, Xu F, Jia X, Shi Z, Jin M. BCI: breast cancer immunohistochemical image generation through pyramid Pix2pix. 2022.","DOI":"10.1109\/CVPRW56347.2022.00198"},{"issue":"9","key":"pcbi.1013516.ref015","doi-asserted-by":"crossref","first-page":"3134","DOI":"10.1021\/acsphotonics.2c00932","article-title":"Virtual stain transfer in histology via cascaded deep neural networks","volume":"9","author":"X Yang","year":"2022","journal-title":"ACS Photonics"},{"key":"pcbi.1013516.ref016","article-title":"Generative adversarial nets","author":"I Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pcbi.1013516.ref017","doi-asserted-by":"crossref","unstructured":"Zhu J, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. CoRR. 2017. https:\/\/doi.org\/abs\/1703.10593","DOI":"10.1109\/ICCV.2017.244"},{"key":"pcbi.1013516.ref018","doi-asserted-by":"crossref","unstructured":"Levy J, Jackson C, Sriharan A, Christensen B, Vaickus L. Preliminary evaluation of the utility of deep generative histopathology image translation at a mid-sized NCI cancer center. In: Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies. 2020. p. 302\u201311. https:\/\/doi.org\/10.5220\/0009427603020311","DOI":"10.5220\/0009427603020311"},{"key":"pcbi.1013516.ref019","doi-asserted-by":"crossref","unstructured":"Mercan C, Reijnen-Mooij G, Martin DT, Lotz J, Weiss N, van Gerven M. Virtual staining for mitosis detection in breast histopathology. 2020.","DOI":"10.1109\/ISBI45749.2020.9098409"},{"issue":"2","key":"pcbi.1013516.ref020","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1109\/JBHI.2020.2975151","article-title":"Seamless virtual whole slide image synthesis and validation using perceptual embedding consistency","volume":"25","author":"A Lahiani","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"issue":"8","key":"pcbi.1013516.ref021","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1109\/TMI.2021.3069874","article-title":"Unpaired stain transfer using pathology-consistent constrained generative adversarial networks","volume":"40","author":"S Liu","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"pcbi.1013516.ref022","doi-asserted-by":"crossref","first-page":"102520","DOI":"10.1016\/j.media.2022.102520","article-title":"MVFStain: multiple virtual functional stain histopathology images generation based on specific domain mapping","volume":"80","author":"R Zhang","year":"2022","journal-title":"Medical Image Analysis"},{"key":"pcbi.1013516.ref023","doi-asserted-by":"crossref","unstructured":"Choi Y, Choi M, Kim M, Ha J, Kim S, Choo J. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. CoRR. 2017. https:\/\/doi.org\/abs\/1711.09020","DOI":"10.1109\/CVPR.2018.00916"},{"key":"pcbi.1013516.ref024","doi-asserted-by":"crossref","unstructured":"Choi Y, Uh Y, Yoo J, Ha J. StarGAN v2: diverse image synthesis for multiple domains. CoRR. 2019. https:\/\/doi.org\/abs\/1912.01865","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"pcbi.1013516.ref025","doi-asserted-by":"crossref","unstructured":"Anoosheh A, Agustsson E, Timofte R, Gool LV. ComboGAN: unrestrained scalability for image domain translation. CoRR. 2017. https:\/\/doi.org\/abs\/1712.06909","DOI":"10.1109\/CVPRW.2018.00122"},{"key":"pcbi.1013516.ref026","unstructured":"Liu Q, Mackey L, Rojas-Carulla M, Deisenroth M. Regularization techniques for fine-tuning in neural networks. arXiv preprint 2018. https:\/\/arxiv.org\/abs\/1810.00553"},{"issue":"9","key":"pcbi.1013516.ref027","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.1109\/TMI.2018.2820199","article-title":"Whole-slide mitosis detection in H&E breast histology using PHH3 as a reference to train distilled stain-invariant convolutional networks","volume":"37","author":"D Tellez","year":"2018","journal-title":"IEEE Trans Med Imaging"},{"issue":"5","key":"pcbi.1013516.ref028","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TMI.2016.2525803","article-title":"Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images","volume":"35","author":"K Sirinukunwattana","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"pcbi.1013516.ref029","unstructured":"Courtney P, Tavakoli T, Koohbanani NA, Magee D, Heidari M, Rajpoot N. Fully convolutional networks for multiclass segmentation of histopathology handbag imagery. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). 2018."},{"key":"pcbi.1013516.ref030","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.ymeth.2020.05.012","article-title":"Deep-Hipo: multi-scale receptive field deep learning for histopathological image analysis","volume":"179","author":"SC Kosaraju","year":"2020","journal-title":"Methods"},{"issue":"1","key":"pcbi.1013516.ref031","doi-asserted-by":"crossref","first-page":"16878","DOI":"10.1038\/s41598-017-17204-5","article-title":"QuPath: open source software for digital pathology image analysis","volume":"7","author":"P Bankhead","year":"2017","journal-title":"Sci Rep"},{"issue":"2","key":"pcbi.1013516.ref032","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1007313","article-title":"Orbit image analysis: an open-source whole slide image analysis tool","volume":"16","author":"M Stritt","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"pcbi.1013516.ref033","first-page":"3","article-title":"Bringing open data to whole slide imaging","volume":"2019","author":"S Besson","year":"2019","journal-title":"Digit Pathol 2019"},{"issue":"5","key":"pcbi.1013516.ref034","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1083\/jcb.201004104","article-title":"Metadata matters: access to image data in the real world","volume":"189","author":"M Linkert","year":"2010","journal-title":"J Cell Biol"},{"issue":"9","key":"pcbi.1013516.ref035","doi-asserted-by":"crossref","first-page":"1395","DOI":"10.1093\/bioinformatics\/btw013","article-title":"Collaborative analysis of multi-gigapixel imaging data using Cytomine","volume":"32","author":"R Mar\u00e9e","year":"2016","journal-title":"Bioinformatics"},{"key":"pcbi.1013516.ref036","doi-asserted-by":"crossref","unstructured":"Li C, Wand M. Precomputed real-time texture synthesis with Markovian generative adversarial networks. In: Leibe B, Matas J, Sebe N, Welling M, editors. Computer Vision \u2013 ECCV 2016. Cham: Springer; 2016. p. 702\u201316.","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"pcbi.1013516.ref037","unstructured":"Isola P, Zhu J, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. CoRR. 2016; arXiv:abs\/1611.07004."},{"issue":"11","key":"pcbi.1013516.ref038","first-page":"120","article-title":"The opencv library","volume":"25","author":"G Bradski","year":"2000","journal-title":"Dr Dobb\u2019s Journal: Software Tools for the Professional Programmer"},{"key":"pcbi.1013516.ref039","unstructured":"Hamming RW. Digital filters. Dover Publications; 1998."},{"key":"pcbi.1013516.ref040","unstructured":"Oppenheim AV, Schafer RW. Discrete-time signal processing. 2nd ed. Prentice Hall; 1999."},{"issue":"7825","key":"pcbi.1013516.ref041","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"CR Harris","year":"2020","journal-title":"Nature"},{"key":"pcbi.1013516.ref042","unstructured":"PyVips Library. 2024. https:\/\/www.libvips.org\/"},{"key":"pcbi.1013516.ref043","unstructured":"Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems. 2019. p. 8024\u201335. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"issue":"2","key":"pcbi.1013516.ref044","doi-asserted-by":"crossref","first-page":"1630","DOI":"10.1609\/aaai.v36i2.20054","article-title":"Unpaired multi-domain stain transfer for kidney histopathological images","volume":"36","author":"Y Lin","year":"2022","journal-title":"AAAI"},{"issue":"10","key":"pcbi.1013516.ref045","doi-asserted-by":"crossref","first-page":"3042","DOI":"10.1109\/TMI.2020.2986331","article-title":"ANHIR: automatic non-rigid histological image registration challenge","volume":"39","author":"J Borovec","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pcbi.1013516.ref046","doi-asserted-by":"crossref","first-page":"4502","DOI":"10.1038\/s41467-023-40218-9","article-title":"Virtual alignment of pathology image series for multi-gigapixel whole slide images","volume":"14","author":"CD Gatenbee","year":"2023","journal-title":"Nat Commun"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013516","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T18:08:17Z","timestamp":1761934097000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013516"}},"subtitle":[],"editor":[{"given":"Piero","family":"Fariselli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"references-count":46,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,21]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013516","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}