Segmentation of Folds in Tissue Section Images

Abstract

An automated image analysis method for identifying folds in tissue section images is presented. Tissue folding is a common artifact in histological images. Folding artifacts form when tissue folds over twice or more when placing it on the microscope slide. As analyzing cell nuclei automatically, the existence of these artifacts causes algorithms easily to give false output. Thus, their identification is essential in order to obtain reliable analysis. The proposed multistage algorithm consists of three phases. First, the section image is converted to HSI color-space and the saturation and intensity components are processed in order to enhance the discrimination of the objective pixels. Next, segmentation is performed using K-means clustering and the cluster containing fold pixels is extracted from the others. Finally, unavoidable segmentation errors caused mostly by the nuclei of similar characteristics with folds are corrected based on the size and component values of the faulty segmented objects. The method is tested on different tissue section images and the results are compared with manually obtained ones with promising results.