Table of Contents Author Guidelines Submit a Manuscript
Computational and Mathematical Methods in Medicine
Volume 2012, Article ID 574184, 12 pages
http://dx.doi.org/10.1155/2012/574184
Research Article

Extraction of Nucleolus Candidate Zone in White Blood Cells of Peripheral Blood Smear Images Using Curvelet Transform

1Biomedical Engineering Department, Medical Image and Signal Processing Research Center, Isfahan University of Medical Sciences, Isfahan, Iran
2Department of Pathology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

Received 5 December 2011; Revised 8 February 2012; Accepted 11 February 2012

Academic Editor: Bill Crum

Copyright © 2012 Ramin Soltanzadeh et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

The main part of each white blood cell (WBC) is its nucleus which contains chromosomes. Although white blood cells (WBCs) with giant nuclei are the main symptom of leukemia, they are not sufficient to prove this disease and other symptoms must be investigated. For example another important symptom of leukemia is the existence of nucleolus in nucleus. The nucleus contains chromatin and a structure called the nucleolus. Chromatin is DNA in its active form while nucleolus is composed of protein and RNA, which are usually inactive. In this paper, to diagnose this symptom and in order to discriminate between nucleoli and chromatins, we employ curvelet transform, which is a multiresolution transform for detecting 2D singularities in images. For this reason, at first nuclei are extracted by means of K-means method, then curvelet transform is applied on extracted nuclei and the coefficients are modified, and finally reconstructed image is used to extract the candidate locations of chromatins and nucleoli. This method is applied on 100 microscopic images and succeeds with specificity of 80.2% and sensitivity of 84.3% to detect the nucleolus candidate zone. After nucleolus candidate zone detection, new features that can be used to classify atypical and blast cells such as gradient of saturation channel are extracted.