The exact segmentation of nucleus and plasma of a white blood cell (leukocyte) is the basis for the creation of an automatic, image based differential white blood cell count(WBC). In this contribution we present an approach for the according segmentation of leukocytes. For a valid classification of the different cell classes, a precise segmentation is essential. Especially concerning immature cells, which can be distinguished from their mature counterparts only by small differences in some features, a segmentation of nucleus and plasma has to be as precise as possible, to extract those differences. Also the problems with adjacent erythrocyte cells and the usage of a LED illumination are considered. The presented approach can be separated into several steps. After preprocessing by a Kuwahara-filter, the cell is localized by a simple thresholding operation, afterwards a fast-marching method for the localization of a rough cell boundary is defined. To retrieve the cell area a shortest-path-algorithm is applied next. The cell boundary found by the fast-marching approach is finally enhanced by a post-processing step. The concluding segmentation of the cell nucleus is done by a threshold operation. An evaluation of the presented method was done on a representative sample set of 80 images recorded with LED illumination and a 63-fold magnification dry objective. The automatically segmented cell images are compared to a manual segmentation of the same dataset using the Dice-coefficient as well as Hausdorff-distance. The results show that our approach is able to handle the different cell classes and that it improves the segmentation quality significantly

No abstract