Estimation of White Blood Cell Abnormality

Abstract

Blood cancer is the most frequent and dangerous among all types of cancer. Leukemia is a type of blood cancer, which is produced by uncontrolled and abnormal production of white blood cells in the bone marrow. However, early identification of Leukemia gives an opportunity to cure cancer by appropriate treatment. One way of finding the leukemia is to count the number of white blood cells and red blood cells. The conventional way of counting white blood cells and red blood cells is by using a special device called Haemocytometer. However, these types of tests are time-consuming and extremely complex leading to inaccurate results. Image processing of microscopic images also helps in cancer cell detection, which is inexpensive as the circuitry is simple. Several researchers have detected the presence of cancer cells but still failed to consider all parameters simultaneously viz., noise reduction, image enhancement, stage identification and so on which leads to a reduction in the accuracy. Therefore, the aim of this paper is to introduce a new system by considering all the above aspects. The process includes stages like image acquisition, image pre-processing, image segmentation along with edge detection and feature extraction to detect the presence of cancer and cancer stages. The paper helps in estimating the white blood cells and red blood cells count along with their average cell sizes (regular/irregular) through which the presence of cancer can be detected.