WBC Image Dataset 2
2D Semantic Segmentation
Medical
|...
License: GPL-3.0

Overview

This is two datasets of white blood cell (WBC) images used for “Fast and Robust Segmentation of White Blood Cell Images by Self-supervised Learning”, which can be used to evaluate cell image segmentation methods.

These two datasets are significantly different from each other in terms of the image color, cell shape, background, etc., which can better evaluate the robustness of WBC segmentation approach. The ground truth segmentation results are manually sketched by domain experts, where the nuclei, cytoplasms and background including red blood cells are marked in white, gray and black respectively. We also submitted the segmentation results by our approach, where the whole WBC region are marked in white and the others are marked in black.

Dataset 2 consists of one hundred 300×300 color images, which were collected from the CellaVision blog. The cell images are generally purple and may contain many red blood cells around the white blood cells.

Images from Dataset 2.

Instruction

The class labels of each image in Dataset 2 is shown in the files Class Labels of Dataset 2.csv. The labels (1- 5) represent neutrophil, lymphocyte, monocyte, eosinophil and basophil, respectively.

Citation

Please use the following citation when referencing the dataset:

@article{Zheng2018,
  title={Fast and Robust Segmentation of White Blood Cell Images by Self-supervised Learning},
  author={Xin Zheng and Yong Wang and Guoyou Wang and Jianguo Liu},
  journal={Micron},
  volume={107},
  pages={55--71},
  year={2018},
  publisher={Elsevier}
  doi={https://doi.org/10.1016/j.micron.2018.01.010},
  url={https://www.sciencedirect.com/science/article/pii/S0968432817303037}
}

License

GPL-3.0

Data Summary
Type
Image,
Amount
100
Size
--
Provided by
CellaVision's Blog
Our blog is created for laboratory professionals with a particular interest in hematology and digital cell morphology.
Issue
Start Building AI Now