Detection of Leukemia in microscopic images using image processing

Leukemia occurs when lot of abnormal white blood cells produced by the bone marrow. Hematologist makes use of microscopic study of human blood, which leads to need of methods, including microscopic color imaging, segmentation, classification and clustering that can allow identification of patients suffering from Leukemia. The microscopic images will be inspected visually by hematologists and the process is time consuming and tiring. The automatic image processing system is urgently needed and can overcome related constraints in visual inspection. The proposed system will be on microscopic images to detect Leukemia. The early and fast identification of Leukemia greatly aids in providing the appropriate treatment. Initial segmentation is done using Statistical parameters such as mean, standard deviation which segregates white blood cells from other blood components i.e. erythrocytes and platelets. Geometrical features such as area, perimeter of the white blood cell nucleusis investigated for diagnostic prediction of Leukemia. The proposed method is successfully applied to a large number of images, showing promising results for varying image quality. Different image processing algorithms such as Image Enhancement, Thresholding, Mathematical morphology and Labelling are implemented using LabVIEW and MATLAB.