Red Blood Cells and White Blood Cells Detection, Differentiation and Counting using Image Processing

Urinalysis is a diagnostic test that evaluates a sample of the urine for detection and assessment of a wide range of disorders such as urinary tract infection (UTI), kidney diseases and diabetes. Epithelial (or flat cells), red and white blood cells may be seen in the urine. The high amount of red blood cells (RBCs) in the urine may indicate infection, trauma, or kidney stones. Since the urine is a sterile body fluid, the presence of white blood cells (WBCs) or bacteria in it is considered abnormal and may indicate a urinary tract infection. The appearance of these cells can be observed through a high power field microscopic examination and is quantitatively recorded based on the manual counting performed by a registered medical technologist. In this study, an automated detection and counting of red and white blood cells in the urine using image processing was proposed. Sample images were captured looking at the microscope used in a standard diagnostic laboratory. The images were processed and a blob detection algorithm was used to detect and differentiate RBCs from WBCs. A cell counting method was also used to provide an actual count of the RBCs and WBCs detected. The automation comes with a graphical user interface backed-up with a working database system to keep the records of the users (e.g. patients, respondents). The performance of the system was statistically described as compared to the manual method of counting. Results show an accuracy of 93.64% for RBCs and 91.6% for WBCs. Hence, the proposed system can benchmark with the manual methods of detection and counting of RBCs and WBCs in urine samples.