Detection of Blood Cancer-Leukemia using K-means Algorithm

Blood cancer (Leukemia) is one of the leading causes of death among humans. The pace of healing depends mainly on early detection and diagnosis of a disease. The main reason behind occurrence of Leukemia is when bone marrow produces a lot of abnormal white blood cells this happens. Microscopic study on images is done by Hematologists who make use of human blood samples, from which it leads to the requirement of following methods, which are microscopic color imaging, image segmentation, clustering and classification which allows easy identification of patients suffering from this disease. Microscopic imaging allows for various methods of detecting blood cancer in visible and immature white blood cells. Identifying Leukemia early and quickly greatly helps practitioners in providing appropriate treatment to patients. Initially to start with, Segmentation stage is achieved by segregating white blood cells from other blood components i.e. erythrocytes and platelets by using Statistical parameters such as mean, standard deviation. For diagnosing prediction of Leukemia, geometrical features such as area, perimeter of the white blood cell nucleuses investigated. In the proposed methodology we make use of K-means, for identifying cancerous stages and its early detection. Experimentation and results were found to be promising with the accuracy of 90% identification of the cancer cells.