Skip to Main Content
With the increasing use of Fluorescence In Situ Hybridization (FISH) probes as markers for certain genetic sequences, the requirement of a proper image processing framework is becoming a necessity to accurately detect these probe signal locations in relation to the centerline of the chromosome. Although many image processing techniques have been developed for chromosomal analysis, they fail to provide reliable results in segmenting and extracting the centerline of chromosomes due to the high variability in shape of chromosomes on microscope slides. In this paper we propose a hybrid algorithm that utilizes Gradient Vector Flow active contours, Discrete Curve Evolution based skeleton pruning and morphological thinning to provide a robust and accurate centerline of the chromosome, which is then used for the measurement of the FISH probe signals. The ability to accurately detect FISH probe locations with respective to the centerline and other landmarks can provide the cytogeneticists with detailed information that could lead to a faster diagnosis.