Segmentation of Overlapping Chromosome Images Using Computational Geometry

Current systems for automatic chromosome classification are interactive and require human intervention for correct separation between touching and overlapping chromosomes. Special separation methods are required to segregate chromosomes because they are non-rigid objects. This study develops a new technique to separate overlapping chromosomes based on computational geometry. This technique requires the identification of all possible cut points from the contour line of overlapping chromosomes, using Voronoi diagrams and Delaunay triangulations to select the four target cut points and cut overlapping chromosomes into two chromosomes. We test our algorithm on 35 overlapping chromosome images and find that 28 out of 35 overlapping chromosomes images can be separated correctly (i.e. 80.0 %). Three out of the 35 images are separate incorrectly (i.e. 8.6 %) and four out of 35 images are not separable by our algorithm (i.e. 11.4 %).