Leukocyte subtypes classification by means of image processing

Abstract

The classification of leukocyte subtypes is a routine method to diagnose many diseases, infections, and inflammations. By applying an automated cell counting procedure, it is possible to decrease analysis time and increase the number of analyzed cells per patient, thereby making the analysis more robust. Here we propose a method, which automatically differentiate between two white blood cell subtypes, which are present in blood in the highest fractions. We apply generalized pseudo-Zernike moments to transfer morphological information of the cells to features and subsequently to a classification model. The first results indicate that information from the morphology can be used to obtain efficient automatic classification, which was demonstrated for the leukocyte subtype classification of neutrophils and lymphocytes. The approach can be extended to other imaging modalities, like different types of staining, spectroscopic techniques, dark field or phase contrast microscopy.