Automatic Segmentation of Chromosome Cells

Abstract

Chromosome’s segmentation is an essential step in the automated chromosome classification system. It is important for chromosomes to be separated from noise or background before the identification and classification. Chromosomes image (Metaphase) is generated in the third phase of mitosis. During metaphase, the cell’s chromosomes arrange themselves in the middle of the cell through a cellular. The analysis of metaphase chromosomes is one of the essential tools of cancer studies and cytogenetics. The Chromosomes are thickened and highly twisted in metaphase which make them very appropriate for visual analysis to determine the kind of each chromosome within the 24 classes (Chromosome karyotyping). This paper represents a chromosome segmentation method of high-resolution digitized metaphase images. Segmentation is done using Difference of Gaussian (DoG) as a sharpening filter before the classic technique (Otsu’s thresholding followed by morphological operations). The proposed method is tested using 130 metaphase images (6011 chromosomes) provided by The Diagnostic Genomic Medicine Unit (DGMU) laboratory at King Abdulaziz University. The experimental results show that the proposed method can successfully segment the metaphase chromosome images with 99.8% segmentation accuracy.