Detection of leukemia using Machine Learning

Abstract: The counting of blood cells plays a very important role in the health sector. The old conventional method used in hospital laboratories involves the manual counting of blood cells using a device called a hemocytometer. But this process is extremely monotonous and time-consuming, which leads to inaccurate results. In order to overcome these complications, this project presents an automated software solution, enriched with image processing and machine learning techniques, to detect and count the number of RBC, WBC, and platelet cells in the blood sample images and to classify diverse types of leukemia. This approach identifies various color feature statistics with geographical measures for machine learning centered on supervised learning.

Keywords: Counting of blood cell, Health sector, image processing, RBC, WBC, Platelets cells.