E-Staining DermaRepo: H&E whole slide image staining dataset. Asaf, M. Z., Salam, A. A., Khan, S., Musolff, N., Akram, M. U., & Rao, B. Data in Brief, 57:110997, December, 2024. doi abstract bibtex In the era of artificial intelligence and machine learning, computer-aided diagnostic frameworks are data-hungry and require large amounts of annotated data to automate the disease diagnosis procedure. Moreover, to enhance the performance and accuracy of disease diagnosis, procedures need to be automated to ensure timely and accurate diagnosis. We are providing a whole slide image repository comprising unstained skin biopsy images acquired using a brightfield microscope, along with Hematoxylin and Eosin chemically and virtually stained image samples, to virtualize the staining procedure and enhance the efficiency of the disease diagnosis pipeline. The dataset was utilized to train a Dual Contrastive GAN to generate virtually stained image samples. The trained model achieved an FID score of 80.47 between virtually stained and chemically stained image samples, indicating a high correlation of content between synthesized and original images. In contrast, FID scores of 342.01 and 320.40 were observed between unstained images and virtually stained slides, and between unstained images and chemically stained images, respectively, indicating less similarity in content.
@article{asaf_e-staining_2024,
title = {E-{Staining} {DermaRepo}: {H}\&{E} whole slide image staining dataset},
volume = {57},
issn = {2352-3409},
shorttitle = {E-{Staining} {DermaRepo}},
doi = {10.1016/j.dib.2024.110997},
abstract = {In the era of artificial intelligence and machine learning, computer-aided diagnostic frameworks are data-hungry and require large amounts of annotated data to automate the disease diagnosis procedure. Moreover, to enhance the performance and accuracy of disease diagnosis, procedures need to be automated to ensure timely and accurate diagnosis. We are providing a whole slide image repository comprising unstained skin biopsy images acquired using a brightfield microscope, along with Hematoxylin and Eosin chemically and virtually stained image samples, to virtualize the staining procedure and enhance the efficiency of the disease diagnosis pipeline. The dataset was utilized to train a Dual Contrastive GAN to generate virtually stained image samples. The trained model achieved an FID score of 80.47 between virtually stained and chemically stained image samples, indicating a high correlation of content between synthesized and original images. In contrast, FID scores of 342.01 and 320.40 were observed between unstained images and virtually stained slides, and between unstained images and chemically stained images, respectively, indicating less similarity in content.},
language = {eng},
journal = {Data in Brief},
author = {Asaf, Muhammad Zeeshan and Salam, Anum Abdul and Khan, Samavia and Musolff, Noah and Akram, Muhammad Usman and Rao, Babar},
month = dec,
year = {2024},
pmid = {39498153},
pmcid = {PMC11532812},
keywords = {Bright field microscope, Histological staining, Virtual staining, Whole slide image segmentation},
pages = {110997},
}
Downloads: 0
{"_id":"2eotmYdtbqEB49QL5","bibbaseid":"asaf-salam-khan-musolff-akram-rao-estainingdermarepohewholeslideimagestainingdataset-2024","author_short":["Asaf, M. Z.","Salam, A. A.","Khan, S.","Musolff, N.","Akram, M. U.","Rao, B."],"bibdata":{"bibtype":"article","type":"article","title":"E-Staining DermaRepo: H&E whole slide image staining dataset","volume":"57","issn":"2352-3409","shorttitle":"E-Staining DermaRepo","doi":"10.1016/j.dib.2024.110997","abstract":"In the era of artificial intelligence and machine learning, computer-aided diagnostic frameworks are data-hungry and require large amounts of annotated data to automate the disease diagnosis procedure. Moreover, to enhance the performance and accuracy of disease diagnosis, procedures need to be automated to ensure timely and accurate diagnosis. We are providing a whole slide image repository comprising unstained skin biopsy images acquired using a brightfield microscope, along with Hematoxylin and Eosin chemically and virtually stained image samples, to virtualize the staining procedure and enhance the efficiency of the disease diagnosis pipeline. The dataset was utilized to train a Dual Contrastive GAN to generate virtually stained image samples. The trained model achieved an FID score of 80.47 between virtually stained and chemically stained image samples, indicating a high correlation of content between synthesized and original images. In contrast, FID scores of 342.01 and 320.40 were observed between unstained images and virtually stained slides, and between unstained images and chemically stained images, respectively, indicating less similarity in content.","language":"eng","journal":"Data in Brief","author":[{"propositions":[],"lastnames":["Asaf"],"firstnames":["Muhammad","Zeeshan"],"suffixes":[]},{"propositions":[],"lastnames":["Salam"],"firstnames":["Anum","Abdul"],"suffixes":[]},{"propositions":[],"lastnames":["Khan"],"firstnames":["Samavia"],"suffixes":[]},{"propositions":[],"lastnames":["Musolff"],"firstnames":["Noah"],"suffixes":[]},{"propositions":[],"lastnames":["Akram"],"firstnames":["Muhammad","Usman"],"suffixes":[]},{"propositions":[],"lastnames":["Rao"],"firstnames":["Babar"],"suffixes":[]}],"month":"December","year":"2024","pmid":"39498153","pmcid":"PMC11532812","keywords":"Bright field microscope, Histological staining, Virtual staining, Whole slide image segmentation","pages":"110997","bibtex":"@article{asaf_e-staining_2024,\n\ttitle = {E-{Staining} {DermaRepo}: {H}\\&{E} whole slide image staining dataset},\n\tvolume = {57},\n\tissn = {2352-3409},\n\tshorttitle = {E-{Staining} {DermaRepo}},\n\tdoi = {10.1016/j.dib.2024.110997},\n\tabstract = {In the era of artificial intelligence and machine learning, computer-aided diagnostic frameworks are data-hungry and require large amounts of annotated data to automate the disease diagnosis procedure. Moreover, to enhance the performance and accuracy of disease diagnosis, procedures need to be automated to ensure timely and accurate diagnosis. We are providing a whole slide image repository comprising unstained skin biopsy images acquired using a brightfield microscope, along with Hematoxylin and Eosin chemically and virtually stained image samples, to virtualize the staining procedure and enhance the efficiency of the disease diagnosis pipeline. The dataset was utilized to train a Dual Contrastive GAN to generate virtually stained image samples. The trained model achieved an FID score of 80.47 between virtually stained and chemically stained image samples, indicating a high correlation of content between synthesized and original images. In contrast, FID scores of 342.01 and 320.40 were observed between unstained images and virtually stained slides, and between unstained images and chemically stained images, respectively, indicating less similarity in content.},\n\tlanguage = {eng},\n\tjournal = {Data in Brief},\n\tauthor = {Asaf, Muhammad Zeeshan and Salam, Anum Abdul and Khan, Samavia and Musolff, Noah and Akram, Muhammad Usman and Rao, Babar},\n\tmonth = dec,\n\tyear = {2024},\n\tpmid = {39498153},\n\tpmcid = {PMC11532812},\n\tkeywords = {Bright field microscope, Histological staining, Virtual staining, Whole slide image segmentation},\n\tpages = {110997},\n}\n\n\n\n","author_short":["Asaf, M. Z.","Salam, A. A.","Khan, S.","Musolff, N.","Akram, M. U.","Rao, B."],"key":"asaf_e-staining_2024","id":"asaf_e-staining_2024","bibbaseid":"asaf-salam-khan-musolff-akram-rao-estainingdermarepohewholeslideimagestainingdataset-2024","role":"author","urls":{},"keyword":["Bright field microscope","Histological staining","Virtual staining","Whole slide image segmentation"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/raoresearch","dataSources":["aGgndugSyribdb2rd"],"keywords":["bright field microscope","histological staining","virtual staining","whole slide image segmentation"],"search_terms":["staining","dermarepo","whole","slide","image","staining","dataset","asaf","salam","khan","musolff","akram","rao"],"title":"E-Staining DermaRepo: H&E whole slide image staining dataset","year":2024}