Extraction of leukocyte in a cell image with touching red blood cells

The main difficulty in segmenting a cell image occurs when there are red blood cells touching the leukocyte. Similar brightness of the touched red blood cells with the cytoplasm in the leukocyte makes their separation quite difficult. Conventional approaches were based on the search of the concavities created by the contact points of two round boundaries. That is, a straight line between the two contacting points will be drawn for the separation of the red blood cell from the cytoplasm. In this paper, we propose a new scheme for the separation. We exploit the fact that the boundary of the leukocyte normally has a round shape and a small portion of it is disconnected due to the touching red blood cells. Specifically, at an initial central point of the nucleus in the leukocyte, we can generate the largest possible circle that covers an interior portion of the composite of nucleus and cytoplasm areas. Also, by perturbing the initial central points, we can generate the circles that do not cross the boundary. Then, the union of the interior areas of the circles can cover most of interior regions in the nucleus and the cytoplasm, separating the leukocyte from the touching red blood cells.