{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T07:39:06Z","timestamp":1773041946617,"version":"3.50.1"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000289","name":"Cancer Research UK","doi-asserted-by":"publisher","award":["A24042"],"award-info":[{"award-number":["A24042"]}],"id":[{"id":"10.13039\/501100000289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioinform."],"abstract":"<jats:p>Multiplex imaging provides valuable insights into the functional and spatial organization of cells and tissues. However, traditional brightfield histopathology imaging remains important and may be required alongside multiplex imaging. We introduce a generalized framework to generate virtual brightfield images from multiplexed data, thereby reducing the need for additional tissue preparation and alignment with the multiplex images. Our approach uses a physically based stain model that simulates the light absorption of stains through the tissue. A channel selection strategy, using a lookup table or Large Language Model (LLM), allows for the mapping of molecular markers to their corresponding stain colors. To further enhance image quality, we integrate a deep learning-based upsampling and denoising model, trained on real brightfield images. We evaluated the methods on several modalities including mass-spectrometry based imaging mass cytometry and fluorescence based multiplex imaging. The results demonstrate that our method produces virtual brightfield images that are of similar quality as real brightfield images, are quantifiable and of diagnostic quality. We also show that LLMs are able to consistently determine appropriate channels in the multiplex image.<\/jats:p>","DOI":"10.3389\/fbinf.2026.1765143","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:48:26Z","timestamp":1773038906000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A toolkit for generating virtual brightfield images of histological and immunohistochemical stains from multiplexed data with AI-based channel selection and image enhancement"],"prefix":"10.3389","volume":"6","author":[{"given":"Tristan","family":"Whitmarsh","sequence":"first","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Mohammad","family":"Al Sa\u2019d","sequence":"additional","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Eduardo","family":"Gonz\u00e1lez Solares","sequence":"additional","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Alireza","family":"Molaeinezhad","sequence":"additional","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Melis O.","family":"Irfan","sequence":"additional","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Claire","family":"Mulvey","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Marta","family":"Paez-Ribes","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Atefeh","family":"Fatem","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Wei","family":"Cope","sequence":"additional","affiliation":[{"name":"Cambridge University Hospitals NHS Foundation Trust","place":["Cambridge, United Kingdom"]}]},{"given":"Kui","family":"Hua","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Gregory","family":"Hannon","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Dario","family":"Bressan","sequence":"additional","affiliation":[{"name":"CRUK Cambridge Institute, Li Ka Shing Centre, University of Cambridge","place":["Cambridge, United Kingdom"]}]},{"given":"Nicholas","family":"Walton","sequence":"additional","affiliation":[{"name":"Institute of Astronomy, University of Cambridge","place":["Cambridge, United Kingdom"]}]}],"member":"1965","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1038\/s41597-023-02108-z","article-title":"Cross-platform dataset of multiplex fluorescent cellular object image annotations","volume":"10","author":"Aleynick","year":"2023","journal-title":"Sci. Data"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.7937\/TCIA.SVQT-Q016","article-title":"Canine glioma characterization project for icdc (icdc-glioma) 01","author":"Amin","year":"2020"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4643381","article-title":"Mitosis domain generalization challenge (miccai-midog 2021) training data","author":"Aubreville","year":"2021"},{"key":"B4","doi-asserted-by":"publisher","first-page":"103155","DOI":"10.1016\/j.media.2024.103155","article-title":"Domain generalization across tumor types, laboratories, and species \u2014 insights from the 2022 edition of the mitosis domain generalization challenge","volume":"94","author":"Aubreville","year":"2024","journal-title":"Med. Image Anal."},{"key":"B5","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. and Appl."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.7937\/gwsp-wh72","article-title":"Cancer moonshot biobank \u2013 melanoma collection (Cmb-mel) (version 7)","author":"Biobank","year":"2022"},{"key":"B7","doi-asserted-by":"publisher","first-page":"3802","DOI":"10.1038\/s41596-021-00556-8","article-title":"Codex multiplexed tissue imaging with dna-conjugated antibodies","volume":"16","author":"Black","year":"2021","journal-title":"Nat. Protoc."},{"key":"B8","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/978-3-031-20071-7_2","article-title":"Simple baselines for image restoration","volume-title":"Computer vision \u2013 ECCV 2022","author":"Chen","year":"2022"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.7937\/6RDA-P940","article-title":"Proteogenomic analysis of chemo-refractory high grade serous ovarian cancer (ptrc-hgsoc) (version 1)","author":"Chowdhury","year":"2023"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1243663","DOI":"10.3389\/fbinf.2023.1243663","article-title":"Digital staining facilitates biomedical microscopy","volume":"3","author":"Fanous","year":"2023","journal-title":"Front. Bioinforma."},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.7937\/E65C-AM96","article-title":"Her2 and trastuzumab treatment response h&e slides with tumor roi annotations","author":"Farahmand","year":"2022"},{"key":"B12","first-page":"16549","article-title":"Multiple instance captioning: learning representations from histopathology textbooks and articles","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Gamper","year":"2021"},{"key":"B13","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-3-030-23937-4_2","article-title":"Pannuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification","volume-title":"European Congress on Digital pathology","author":"Gamper","year":"2019"},{"key":"B14","doi-asserted-by":"publisher","first-page":"034050","DOI":"10.1117\/1.3149853","article-title":"Feasibility of digitally stained multimodal confocal mosaics to simulate histopathology","volume":"14","author":"Gareau","year":"2009","journal-title":"J. Biomed. Opt."},{"key":"B15","doi-asserted-by":"publisher","first-page":"e0159337","DOI":"10.1371\/journal.pone.0159337","article-title":"Virtual hematoxylin and eosin transillumination microscopy using epi-fluorescence imaging","volume":"11","author":"Giacomelli","year":"2016","journal-title":"PLoS ONE"},{"key":"B16","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1038\/nmeth.2869","article-title":"Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometry","volume":"11","author":"Giesen","year":"2014","journal-title":"Nat. Methods"},{"key":"B17","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in neural information processing systems","author":"Ho","year":"2020"},{"key":"B18","article-title":"The single-cell pathology landscape of breast cancer","author":"Jackson","year":"2019"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1214456","article-title":"100,000 histological images of human colorectal cancer and healthy tissue","author":"Kather","year":"2018","journal-title":"Zenodo"},{"key":"B20","doi-asserted-by":"publisher","first-page":"100725","DOI":"10.1016\/j.patter.2023.100725","article-title":"The effect of neural network architecture on virtual h&e staining: systematic assessment of histological feasibility","volume":"4","author":"Khan","year":"2023","journal-title":"Patterns"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1038\/s41467-024-46077-2","article-title":"Virtual histological staining of unlabeled autopsy tissue","volume":"15","author":"Li","year":"2024","journal-title":"Nat. Commun."},{"key":"B22","doi-asserted-by":"publisher","first-page":"8390","DOI":"10.1038\/ncomms9390","article-title":"Highly multiplexed imaging of single cells using a high-throughput cyclic immunofluorescence method","volume":"6","author":"Lin","year":"2015","journal-title":"Nat. Commun."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1036","DOI":"10.1038\/s43018-023-00576-1","article-title":"High-plex immunofluorescence imaging and traditional histology of the same tissue section for discovering image-based biomarkers","volume":"4","author":"Lin","year":"2023","journal-title":"Nat. Cancer"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1002\/cyto.a.24789","article-title":"A novel process for h&e, immunofluorescence, and imaging mass cytometry on a single slide with a concise analytics pipeline","volume":"103","author":"Marlin","year":"2023","journal-title":"Cytom. Part A"},{"key":"B25","doi-asserted-by":"publisher","article-title":"The clinical proteomic tumor analysis consortium clear cell renal cell carcinoma collection (cptac-ccrcc)","year":"","DOI":"10.7937\/k9\/tcia.2018.oblamn27"},{"key":"B26","doi-asserted-by":"publisher","article-title":"The clinical proteomic tumor analysis consortium cutaneous melanoma collection (Cptac-cm)","year":"","DOI":"10.7937\/K9\/TCIA.2018.ODU24GZE"},{"key":"B27","doi-asserted-by":"publisher","article-title":"The clinical proteomic tumor analysis consortium head and neck squamous cell carcinoma collection (cptac-hnscc)","year":"","DOI":"10.7937\/k9\/tcia.2018.uw45nh81"},{"key":"B28","doi-asserted-by":"publisher","article-title":"The clinical proteomic tumor analysis consortium sarcomas collection (Cptac-sar)","year":"2019","DOI":"10.7937\/tcia.2019.9bt23r95"},{"key":"B29","doi-asserted-by":"publisher","article-title":"The clinical proteomic tumor analysis consortium breast invasive carcinoma collection (cptac-brca)","year":"2020","DOI":"10.7937\/TCIA.CAEM-YS80"},{"key":"B30","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1038\/nmeth.1854","article-title":"Serial two-photon tomography for automated ex vivo mouse brain imaging","volume":"9","author":"Ragan","year":"2012","journal-title":"Nat. Methods"},{"key":"B31","doi-asserted-by":"publisher","first-page":"466","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":"B32","doi-asserted-by":"publisher","DOI":"10.7937\/BH0R-Y074","article-title":"Highly multiplexed spatially resolved immune cell atlas of hepatocellular carcinoma","author":"Ruf","year":"2023","journal-title":"Data Set"},{"key":"B33","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13000-021-01126-y","article-title":"Normalization of he-stained histological images using cycle consistent generative adversarial networks","volume":"16","author":"Runz","year":"2021","journal-title":"Diagn. Pathol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"107528","DOI":"10.1016\/j.cmpb.2023.107528","article-title":"Comparison of deep learning models for digital h&e staining from unpaired label-free multispectral microscopy images","volume":"235","author":"Salido","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"key":"B35","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/978-3-030-00934-2_30","article-title":"Cell detection with star-convex polygons","author":"Schmidt","year":"2018","journal-title":"Med. Image Comput. Comput. Assisted Intervention - MICCAI 2018 - 21st Int. Conf. Granada, Spain, Sept. 16-20, 2018, Proc. Part"},{"key":"B36","doi-asserted-by":"publisher","first-page":"52","DOI":"10.4103\/jpi.jpi_114_20","article-title":"Creating virtual hematoxylin and eosin images using samples imaged on a commercial codex platform","volume":"12","author":"Simonson","year":"2021","journal-title":"J. Pathology Inf."},{"key":"B37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/WIECON-ECE60392.2023.10456447","article-title":"Image-to-image translation with conditional adversarial networks","volume-title":"2023 IEEE 9th international Women in Engineering (WIE) conference on electrical and computer engineering (WIECON-ECE)","author":"Tahmid","year":"2023"},{"key":"B38","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1038\/s44303-024-00021-7","article-title":"Deep learning-based virtual h&e staining from label-free autofluorescence lifetime images","volume":"2","author":"Wang","year":"2024","journal-title":"Imaging"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.7937\/TCIA.JHQD-FR46","article-title":"Nascent prostate cancer heterogeneity drives evolution and resistance to intense hormonal therapy","author":"Wilkinson","year":"2020"},{"key":"B40","doi-asserted-by":"publisher","first-page":"7978","DOI":"10.1038\/s41467-024-52263-z","article-title":"Virtual birefringence imaging and histological staining of amyloid deposits in label-free tissue using autofluorescence microscopy and deep learning","volume":"15","author":"Yang","year":"2024","journal-title":"Nat. Commun."}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1765143\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:48:30Z","timestamp":1773038910000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2026.1765143\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":40,"alternative-id":["10.3389\/fbinf.2026.1765143"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2026.1765143","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"article-number":"1765143"}}