Counting the number of cells in immunocytochemical images using genetic algorithm

Immunocytochemistry (ICC) is a microscopic imaging technique that is used to assess the presence of a specific antigen in cells utilizing a specific antibody for allowing visualization and examination processes. Number of cells in an ICC image is considered as one of the most important indicators in the examination process. In this paper, an image analysis approach is proposed in order to count the number of cells in an ICC images. For this purpose, morphological filtering is done to clean up noise. Then, nucleuses and antibodies are separated by classifying relevant colors using a Nearest Neighbor classifier. Finally, the adherent cells are segmented by learning a Genetic model and the number of cells has been counted. The experiments have been conducted on a dataset of ICC images which are collected for this research. The results show the high efficiency of the proposed method.