The diagnosis of blood-based diseases often involves identifying and characterizing patient blood samples.
So, providing automated methods to detect and classify blood cell subtypes would be a huge benefit and would have important medical applications.
Note: You can find data in the Kaggle competttion linked below [2].
This dataset contains 12,500 augmented images of blood cells (JPEG) with accompanying cell type labels (CSV).
There are approximately 3,000 images for each of 4 different cell types grouped into 4 different folders (according to cell type).
This dataset is accompanied by an additional dataset containing the original 410 images (pre-augmentation) as well as two additional subtype labels (white blood cells WBC vs red blood cells RBC) and also bounding boxes for each cell in each of these 410 images (JPEG + XML metadata).
Types of blood cells are :
- Mononuclear
- Lymphocyte
- Monocyte
- Basophil
- Polynuclear
- Eosinophil
- Neutrophil
For more information about blood cells and blood cell subtypes, see the following links:
- https://www.ncbi.nlm.nih.gov/books/NBK2263/ - https://www.ncbi.nlm.nih.gov/books/NBK2263/box/A26/?report=objectonly
[1] Link to Kaggle Competition: https://www.kaggle.com/paultimothymooney/blood-cells/home
[2] You can find the dataset here: https://www.kaggle.com/paultimothymooney/blood-cells