A Detection of Leukemia by Using K-Means Clustering Algorithm and Support Vector Machine

Abstract

Leukemia is a type of blood cancer that normally originates in the bone marrow. It causes a relatively large number of abnormal blood cells to be produced. In a normal, healthy state, blood cells originate in the bone marrow as stem cells and later mature to form different types of blood cells (red blood cells, white blood cells, or platelets) and transfer to the bloodstream. As for a person suffering from leukemia, his/her bone marrow begins to produce abnormal white blood cells that enter the bloodstream and begin to compete against the normal healthy blood cells and prevent them from performing their functions properly. This paper aims to detect blood cancer disease (Leukemia) at the earliest stage possible through the use of image processing techniques, k-means clustering algorithm, and support vector machine (SVM). The process will be further supported by processing tools such as MATLAB to ensure the early identification of any leukemia existence, thus enabling early administration of appropriate treatment to mitigate possible pestilent outcomes. The detection through using the images is a cheap, fast, and safe method as there is no need for specialized equipment used for lab testing.