Cell Nuclei Segmentation Using Marker-Controlled Watershed and Bayesian Object Recognition

Computer-assisted image analysis cytology play an important function in modern cancer diagnostics. A crucial task of such systems is segmentation of cell nuclei. Automatic procedure have to locate their exact position in cytological preparation and determine precise edges in order to extract morphometric features. Unfortunately, segmentation of individual nuclei is a huge challenge because they often creates complex clusters without clear edges. To deal with this problem we are proposing to combine Bayesian object recognition approach to approximate nuclei by circles with marker-controlled watershed employed to determine their exact shape. Watershed segmentation can reconstruct a precise shape of nuclei but only if their approximate location is known. On the other hand, Bayesian object recognition approach allows to isolate single nuclei even in complex nuclei structures but without determining their exact shape. Thus, we used Bayesian object recognition to generate markers required to form a topographic map for a watershed method. The effectiveness of the proposed approach was examined using artificially generated images and real cytological images of breast cancer. Tests carried out have shown that the proposed version of the marked-controlled watershed can be used with success to segment elliptic-shaped objects.