• About the Journal
• Content
• 2021
• 2020
• 2019
• 2018
• 2017
• 2016
• 2014
• 2013
• 2012
• 2011
• 2010
• 2009
• Editorial Board
• For Authors
• Indexing
• Bibliography
• Prices and Ordering
• Copyright
• Impressum

Abstract

The human metaspread images contain the chromosomes of an individual that are imaged during the metaphase stage of cell division. The chromosomes are the genetic information carriers, any alteration either in the number of chromosomes or the structure of chromosomes, results in a medical condition termed as genetic defects. The genetic defects can be cause of many diseases that are difficult to cure. In order to uncover the genetic defects the metaspread images are segmented, to count the number of chromosomes present or to study the structure of the chromosomes. The metaspread images suffer from intensity in homogeneity, because of which it is very difficult to extract the individual chromosomes by using conventional segmentation techniques. In this work various segmentation approaches are implemented and studied, to segment the chromosomes from the metaspread images. The minimization of region scalable fitting energy for image segmentation proposed by Chumming li et. al, is effective in segmenting the metaspread images that have intensity in homogeneity, as this technique uses the local intensity values of the nearby regions of the objects and find the approximate intensity values along both sides of the contour. The paper compares the level set based segmentation algorithms based upon their implementation techniques and the segmentation results. The methods have been compared in terms of number of objects segmented, time taken, complexity, type of segmentation approach. The ADIR dataset of metspread images has been taken for the purpose of experimentation.

Keywords: Metaspreads, Chromosomes, Segmentation, Level Set Methods

Download Paper (638 KB)