Leukocytes (WBCs) and Masks

Leukocytes (WBCs) and Masks: Automatic differential counting of leukocytes (also known as white blood cells (WBCs)) provides invaluable information to pathologist for diagnosis and treatment of many diseases. In automatic systems leukocytes are detected from a blood smear and are classified into their types: Neutrophil, Eosinophil, Basophil, Lymphocyte and Monocyte. There are some criteria that pathologists consider to differentiate leukocytes; color, geometric and texture of cells. Colors of nucleus and cytoplasm vary among the leukocytes. Lymphocytes have single, large, round or oval and Monocytes have singular convoluted shape nucleus. Nucleus of Eosinophils is divided into 2 segments and nucleus of Neutrophils into 2 to 5 segments. Lymphocytes often have no granules, Monocytes have tiny granules, Neutrophils have fine granules and Eosinophils have large granules in cytoplasm. This dataset contains four types of leukocytes: Neutrophil, Eosinophil, Lymphocyte and Monocyte which are extracted from microscopic images of blood smear. Their mask are also provides which are manually segmented by an expert. This dataset can be used for automatic distinguishing of different leukocytes. Blood smear of 10 patients have been used in this work. Digital microscopic images of WBCs are captured with Canon V1 camera mounted on Canon optical microscope. The data are stored in jpg format with 3872×2592 pixels and 300 dpi resolution. The images are in sRGB color space.

Please reference the following paper if you would like to use any part of this dataset :

Sarrafzadeh, O., Rabbani, H., Talebi, A. & Banaem, H.U. (2014) Selection of the best features for leukocytes classification in blood smear microscopic images. In Proceedings of the SPIE Medical Imaging, International Society for Optics and Photonics, Medical Imaging 2014: Digital Pathology, SPIE 9041, SPIE, San Diego, California, USA.

You can skip to the end and leave a response. Pinging is currently not allowed.

2 Responses to “Leukocytes (WBCs) and Masks

  1. mbenomar says:

    i need a dataset

  2. faeze says:

    I need a dataset, I am forever grateful and I would be very grateful for your kind help.
    Thanks for your time, and I hope to hear from you .

Leave a Reply