Now days, blood testing is one of the most
important clinical examinations. The characteristics
(quantity, shape and color) of the white blood cell (WBC) can
give vital information about a patient’s health. But, the
manual inspection is time-consuming and requires adequate
technical knowledge. Therefore, automatic medical diagnosis
systems are necessary to help physicians to diagnose diseases
in a fast and competent way. The main aim of blood cell
segmentation is to extract the cells from complicated
background and to segment every cell into morphological
components such as nucleus, cytoplasm, and some others.
Accuracy of earlier algorithms depends momentously on the
initial contrast of the image. This limitation leads to
capturing of all objects with gray-levels close to that of the
WBCs. To overcome this disadvantage we propose to use the
nucleus minimum segment size as a constraint to eliminate
the non-nucleus objects. The proposed algorithm used,
reduces noise effect and enhances accuracy of segmentation.
All previous methods use different techniques for
segmentation which gives less efficiency compared to
proposed method for nucleus and cytoplasm segmentation. In
this paper, we propose a new method based on gray scale
contrast enhancement and filtering. For removal of false
objects minimum segment size is implemented. Near about
365 blood images will be tested for this technique. Each of
the five normal white blood cell types can be evaluated to
compare separate performance.
Sonali Sonar : North Maharashtra University,
Department of Electronics and Telecommunication Engineering,
J. T. Mahajan College of Engineering, Faizpur,India
Kanchan Bhagat : North Maharashtra University,
Department of Electronics and Telecommunication Engineering,
J. T. Mahajan College of Engineering, Faizpur, India
Blood cell
Dataset
Leucocyte
MATLAB Code
Segmentation
WBC
Segmentation accuracy results for each cell type using
both the proposed algorithm and algorithm proposed by
Madhloom et al. [4]. It shows that the superiority of
proposed algorithm for each cell type and for the overall
performance of 79.7% compared to 55.9%.
[1] “Blood Diseases," The British Medical Journal, vol. 2,
no. 3907, pp. 998 - 999, 1935.
[2] "What Are Blood Tests?" National Heart, Lung, and
Blood Institute (NHLBI), online].
Available:http://www.nhlbi.nih.gov/health/healthtopics/
topics/bdt/. [Accessed 2 May 2012].
[3] J. Wu, P. Zeng, Y. Zhou and C. Olivier, "A novel color
image segmentation method and its application to white
blood cell image analysis," in 8th international Con. on
Signal Processing, 2006.
[4] H. T. Madhloom, S. A. Kareem, H. Ariffin, A. A. Zaidan,
H. O. Alanazi and B. B. Zaidan, "An Automated White
Blood Cell Nucleus Localization and Segmentation using
Image Arithmetic ad Automatic Threshold," Journal of
Applied Sciences, vol. 10, no. 11, pp. 959-966, 2010.
[5] G. Ongun, U. Halici, K. Leblebicioglu and V. Atala, "An
automated differential blood count system," in Int. Conf.
of the IEEE Engineering in Medicine and Biology
Society, 2001, Istanbul.
[6] R. Adollah, M. Y. Mashor, N. F. Mohd Nasir and H.
Rosli, "Blood Cell Image Segmentation: A Review," in
IFMBE, Kuala Lumpur, 2008.
[7] J. Theerapattanakul, J. Plodpai and C. Pintavirooj, "An
efficient method for segmentation step of automated
white blood cell classifications," in TENCON, Bangkok,
2004.
[8] F. Sadeghian, Z. Seman, A. Ramli and B. H. Abdul-
Kahar, "A Framework for White Blood Cell
Segmentation in Microscopic Blood Images Using Digital
Image Processing," Biological Procedures Online, pp.
196-206, 2009.
[9] T. Markiewicz, S. Osowski and B. Mariaiska, "White
Blood Cell Automatic Counting System Based on
Support Vector Machine," Lecture Notes in Computer
Science - ICANNGA, pp. 318-326, 2007.
[10] N. Theera-Umpon, "White Blood Cell Segmentation and
Classification in Microscopic Bone Marrow Images,"
Lecture Notes in Computer Science - FSKD, p. 787–796,
2005.
[11] J. Angulo and G. Flandrin, "Automated detection of
working area of peripheral blood smears using
mathematical morphology," Analytical Cellular
Pathology, pp. 37-49, 1 January 2003.
[12] G. Cao, C. Zhong, L. Li and J. Dong, "Detection of
Red Blood Cell in Urine Micrograph," in ICBBE,
2009.
[13] H. Ramoser, V. Laurain, H. Bischof and R. Ecker,
"Leukocyte segmentation and classification in bloodsmear
images," in IEEE Engineering in Medicine and
Biology, Shanghai, 2005.
[14] J. Vromen and B. McCane, "Red Blood Cell
Segmentation from SEM Images," in Image and
Vision Computing (IVCNZ), New Zealand, 2009.
[15] J. Poomcokrak and C. Neatpisarnvanit, "Red Blood
Cells Extraction and Counting," in International
Symposium on Biomedical Engineering (ISBME),
2008.
[16] N. Sharma and L. M. Aggarwal, "Automated medical
image segmentation techniques," Journal of Medical
Physics, vol. 35, no. 1, pp. 3-14, 2010.
[17] S. E. Umbaugh, Computer Imaging: Digital Image
Analysis and Processing, CRC Press, 2005.
[18] R. M. Haralick and L. d. Shapiro, "Computer and
Robot Vision," in Computer and Information Science,
Addison-Wesley, 1992, pp. 28- 48.
[19] "Source code and blood image dataset," Mathworks
File Exchange website, [Online].
Available:http://www.mathworks.com/matlabcentral/fil
eexchange/36634.
[20] D. Tagliasacchi and G. Carbon, "The blood cells,"
April 1997. [Online]. Available:
http://www.funsci.com/fun3_en/blood/blood.htm.
[Accessed 2 May 2012].
[21] G. Lebrun, C. Charrier, “A fast and efficient
segmentation scheme for cell microscopic image,”
in Cellular and Molecular Biology TM 53, N°2, 51-61,
2007
[22] S. Chinwaraphat, A. Sanpanich, C. Pintavirooj, “A
Modified Fuzzy Clustering For White Blood Cell
Segmentation,” in the 3rd International Symposium on
Biomedical Engineering (ISBME 2008)
[23] Zhaozheng Yin, Ryoma Bise, Mei Chen and Takeo
Kanade,Carnegie Mellon University, Intel Labs
Pittsburgh,” cell segmentation in microscopy imagery
using a bag of Local bayesian classifiers,” in the IEEE
International Symposium on Biomedical Imaging,
April, 2010.
[24] Marco Antonio Garcia de Carvalho, Tiago William
Pinto, Roberto Marcondes C´esar J´unior,” Image
Segmentation Using Watershed and Normalized Cut”