AUTOMATED ACUTE MYELOGENOUS LUKEMIA DETECTION IN BLOOD MICROSCOPIC IMAGE

Keywords:

Acute myelogenous, leukemia, k-means clustering, RGB color space, Segmentation.

Abstract

Acute Myelogenous leukemia (AML) is a subtype of acute leukemia. The current method of leukemia detection is by manual examination of the blood cells through the microscope. It very time consuming and also it depend on the operator’s ability. Current method is very costly .The leukemia is very dangerous if it is left untreated. So the need of automatic detection of leukemia essential. Leukemia can be automatically detected mainly by 5 steps .The first step is preprocessing the image. In preprocessing the RGB color space is converted into CIEL*a*b color space. This is done due to three reasons. First the RGB (red ,green, blue) color space is difficult to segment, second in RGB image background varies greatly with respect to color and intensity. After the preprocessing, noises in the image will remove using a wiener filter. Then the image is segmented into three clusters using K-means clustering algorithm. The segmented white blood cell nucleus feature is then extracted. By using the SVM classifier the image is classified into cancerous or noncancerous image.

Downloads

How to Cite

AUTOMATED ACUTE MYELOGENOUS LUKEMIA DETECTION IN BLOOD MICROSCOPIC IMAGE. (2020). International Journal of Advances in Scientific Research and Engineering (IJASRE), ISSN:2454-8006, DOI: 10.31695/IJASRE, 2(1), 08–15. Retrieved from https://ijasre.net/index.php/ijasre/article/view/13