Accurate Localization of Chromosome Centromere Based On Concave Points

Abstract

Many genetic disorders or possible abnormalities that may occur in the future generations can be predicted through analyzing the features of the chromosomes. For this purpose, karyotype is often used which to make it, there is necessary to identify each one of the 24 chromosomes from the microscopic images. The first step of this process is to define the morphological and band pattern based features for each chromosome. An important class of morphological features is the location of the chromosome’s centromere. Thus, centromere localization is an initial step in designing an automatic karyotyping system. In this paper, a novel algorithm for centromere localization is presented. The procedure is based on the calculation and analyzing the concavity degree of the chromosome’s boundary pixels. In this method, the centerline of the chromosome is computed and the score of each pixel on the centerline is considered as the sum of the concavity degree of two pixels on the chromosome’s boundary that are perpendicular to it. Finally, location of centromere is estimated as one pixel on the centerline which is corresponding to maximum score. When applied the proposed algorithm on 50 images, an average error of 2.25 pixels for centromere localization is achieved.