White blood cell (WBC) counting analysis in blood smear images using various color segmentation methods

Abstract

White blood cells (WBCs) is closely related to human immunity system which is useful to fight viruses and bacteria. Cancer therapy effectiveness and some of the blood-related diseases can be determined from the count of cell region. Traditionally, WBC count is done manually which yields inaccurate results as the blood sample increases. Moreover, even though hematology counter device is fast and accurate, it is very costly. These problems has led to the invention of cost effective Computer Aided System (CAS) which analyzes the blood smeared images obtained from microscope. In CAS, the most important step is segmentation and any failure at this stage will cause inaccuracy in the subsequent stages. Realizing the importance of segmentation, this paper investigated various segmentation methods for the purpose of WBC counting based on color band thresholding procedure. Initially, color space correction based on L∗a∗b∗ color space was applied to standardize the image color intensity. Next, segmentation process was conducted to prune out the WBC region from the background by combining color analysis of RGB, CMYK and HSV with Otsu thresholding. Morphological filter was employed as the segmented image contained noises would affect the system performance. Henceforth, Connected Component Labelling (CCL) was done to distinguish the small particles that still existed in the image. Eventually, Circle Hough Transform (CHT) was applied to identify and count the WBC including the one in the clump region. Overall system performance was accessed and it was found that by using S color component of HSV, color space provided the highest WBC segmentation accuracy which was 96.92%. Meanwhile, for the combination of two color bands; S-C produced 96.56% of WBC counting accuracy. Another interesting finding was that the usage of nucleus based detection was superior compared to cytoplasm-based detection for WBC counting purpose.