Accession number BBBC045 · Version 1
Description of the biological application
This dataset is useful for measuring differential White Blood Cell Count. White blood cells play an important role in the immune system to protect against infections and diseases. There are 5 different types of white blood cells and each type can be affected by various health conditions. Thus, the number of white blood cells (i.e. white blood cell count) along with the ratio (percentage of each type of white blood cell, i.e. white blood cell differential) can have implications for disease and illness. For these reasons, white blood cell differential is used as a way to assess and monitor immune system health.
The images have been acquired using the ImageStream imaging flow cytometer. The image set consists of 13 subjects. Each subject data set consists of the following white blood cell types: B- and T-lymphocytes, eosinophils, monocytes and neutrophils. The following data is included: compensated image files (.cif; zip file "BBBC045_Stained_Populations.zip" below) and image montages as TIFF files (.tif; zip file "BBBC045_Stained_Montages.zip" below). Compensated image files and image montages contain images from the following channels: fluorescent, brightfield and darkfield. Each montage contains 900 single images.
Note that some images are partial images, like the example one above.
The ground truth has been obtained by gating based on the appropriate corresponding fluorescent channels. The ground truth is represented in form of directory names. Each subject contains one directory for each white blood cell type correspondingly named.
For more information
Please contact Andrew Filby, of the Centre for Nanohealth at Swansea University, Swansea, UK regarding this dataset.
Published results using this image set
The proposed data set has been evaluated in a publication: Nassar M, Doan M, Filby A, Wolkenhauer O, Fogg DK, Piasecka J, Thornton CA, Carpenter AE, Summers HD, Rees P, Hennig H. Label-Free Identification of White Blood Cells Using Machine Learning. Cytometry A. 2019 Aug;95(8):836-842. doi: 10.1002/cyto.a.23794. Epub 2019 May 13. PMID: 31081599; PMCID: PMC6767740.
To the extent possible under law, Mariam Nassar has waived all copyright and related or neighboring rights to BBBC045v1.