You are here
White Blood Cell Detection and Segmentation in Microscopy Images of Thin Blood Smears [Poster].
Analysis of microscopic images of blood smears for parasiteinfected red blood cells can assist with screening and monitoring malarial infection. Millions of blood slides are manually screened for parasites every year, which is a time consuming and subjective process. We have developed a smartphone-based software to perform this task using machine learning and image analysis methods for counting infected red blood cells automatically. The software runs on a standard Android smartphone attached to a microscope by a low-cost adapter. Images of thin blood smear slides are obtained through the eyepiece of the microscope using the smartphone’s built-in camera. The method we have implemented first needs to detect and segment red blood cells. However, the presence of white blood cells (WBCs) is adversely affecting the accuracy of red blood cell detection and segmentation since WBCs are often mistaken for red blood cells by current automatic cell detection methods. As a result, a pre-processing step for WBC elimination is necessary. Segmentation of WBCs is a complex process due to the morphological diversity of WBCs and staining differences. We propose a novel method for white blood cell segmentation in microscopic images of blood smears that combines a WBCs detection method based on range filtering with a customized level-set algorithm to estimate the boundary of each WBC in an image.