Development of a robust algorithm for detection of nuclei of white blood cells in peripheral blood smear images

Microscopic evaluation of peripheral blood smear analysis is a commonly used laboratory procedure to diagnose various diseases such as anemia, malaria, leukemia, etc. Manual microscopic evaluation is laborious and hence many research groups have attempted to automate smear analysis. Variations in staining procedure and smear preparation introduces color shade variations into peripheral blood smear images. Illumination provided by point source bulb introduces brightness variations across the smear which affects the performance of an automated method. In this paper we present an image processing algorithm for detection of nuclei of white blood cells which is robust to color and brightness variations. In the proposed method we used two different datasets and also five datasets which were derived from original images by introducing brightness variations. We also compared the results of the proposed method with four state-of-the-art methods. The results demonstrate that the proposed method detects nuclei accurately with an average accuracy of 0.99 and Dice coefficient of 0.965.