Segmentation of Overlapped and Touching Human Chromosome images

Abstract

Chromosomes are essential genomic information carriers. The identification of chromosome abnormalities is an essential part of diagnosis and treatment of genetic disorders such as chromosomal syndromes and many types of cancer. Currently available cytogenetic imaging software is designed to classify only normal chromosomes. The automation of chromosome analysis is involving segmentation of chromosomes and classification into 24 groups. Segmentation of the overlapped chromosomes is a major step toward the realization of homolog classification. Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis. Current systems for automatic chromosome classification are mostly interactive and require human intervention. In this paper, an automatic procedure is proposed to obtain the separated chromosomes. The separations of overlapped and touching chromosomes are obtained by finding the intersecting (concave and convex) points with the help of Novel algorithm. The intersecting points are located on contour of the image and then the curvature function is used to find out concave points. Then the possible separation lines are plotted by using all concave points and finally construct the hypotheses for possible separation lines between concave points. The segmentation is carried out by means of a curvature function scheme, which proved to be successful.