Automated Acute Myelogenous Lukemia Detection in Blood Microscopic Image
Journal: International Journal of Science and Research (IJSR) (Vol.4, No. 12)Publication Date: 2015-12-05
Authors : Jesly James; Kavitha N. Nair;
Page : 1136-1139
Keywords : Acute myelogenous leukemia; RGB color space; Segmentation; k-means clustering;
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 operators 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.
Other Latest Articles
- Robust Approach for Product Label Reading
- Prevalence of Asymptomatic Bacteriuria in Pregnant Women, Westren Region, Taif, Sudia Arabia
- Geo-Spatial Ground Water Quality Mapping and Assessment of Mining Region ? A Case Study
- Effect of Rare Earth (Sm) ion Substitution on Structural, Dielectric, and Transport Properties of PZT Ceramics
- Survey on EMI: Privacy-Preserving Public Auditing for Regenerating-Code-Based Cloud Storage
Last modified: 2021-07-01 14:28:06