Evidential Segmentation Scheme of Bone Marrow Images

  • Mourtada Benazzouz Genie Biomedical Laboratory, Tlemcen University
  • Ismahan Baghli Genie Biomedical Laboratory, Tlemcen University
  • Amine Benomar Genie Biomedical Laboratory, Tlemcen University
  • Med Ammar Genie Biomedical Laboratory, Tlemcen University
  • Youcef Benmouna Genie Biomedical Laboratory, Tlemcen University
  • Med Amine Chikh Genie Biomedical Laboratory, Tlemcen University
Keywords: Fusion, SVM, Evidence theory, Leukocytes, color spaces.


The analysis of microscope images can provide useful information concerning health of patients. In this paper a new and ecient supervised method for color image segmentation is presented. The segmentation here is to extract leukocytes (white blood cells) and separate its constituents, nucleus and cytoplasm. Since red cells, leukocytes and background had dierent color in image of bone marrow smear, they were extracted according to their own colors. First, we train an SVM in dierent color spaces by a learning set. SVM with xed parameters is used here to yield several classications, and the basic technique consists on information fusion from dierent sources via evidence theory. This combination is performed by integrating uncertainties and redundancies for each one of the color spaces. From the experiments, we achieve good segmentation performances in the entire nucleus and cytoplasm segmentation. We evaluate the segmentation performance of the proposed technique by comparing its results with the cell images manually segmented by an expert.


(1) K.Y. Lin, J.H. Wu, and L.H. Xu. A survey on color image segmentation techniques. Journal of Image and Graphics, 10(1):1{9, 2005.

(2) Pascal Bamford. Empirical Comparison of Cell Segmentation Algorithms Using an Annotated Dataset. PhD thesis, University of Queensland, Brisbane, Australia, 2003.

(3) Hiremath P.S., Bannigidad Parashuram, and Geeta Sai. Automated identification and classification of white blood cells (leukocytes) in digital microscopic. IJCA Special Issue on 'Recent Trends in Image Processing and Pattern Recognition', pages 59{63, 2010.

(4) Pan Chen, Lu Huijuan, and Cao Feilong. Segmentation of blood and bone marrow cell images via learning by sampling. ICIC 2009, pages 336{345, 2009.

(5) Chen Pan, Dong Sun Park, Sook Yoon, and Ju Cheng Yang. Leukocyte image segmentation using simulated visual attention. Expert Systems with Applications, 39:74797494, 2012.

(6) Leyza Baldo Dorinin, Rodrigo Minetto, and Neucimar Jeronimo Leite. Semi-automatic white blood cell segmentation based on multiscale analysis. IEEE Trans Inf Technol Biomed, In press, 2012.

(7) Seyed Hamid Rezatofighi and Hamid Soltanian-Zadeh. Automatic recognition of five types of white blood cells in peripheral blood. Computerized Medical Imaging and Graphics, 35:333343, 2011.

(8) Quelhas P., Marcuzzo M., Mendonca A.M., and Campilho A. Cell nuclei and cytoplasm joint segmentation using the sliding band filter. IEEE Transactions on Medical Imaging,, 29:14631473, 2010.

(9) Ko BC, Gim JW, and Nam JY. Automatic white blood cell segmentation using stepwise merging rules and gradient vector ow snake. MICRON, 42:695{705, 2011.

(10) Ramin Soltanzadeh, Hossein Rabbani, and Ardeshir Talebi. Extraction of nucleolus candidate zone in white blood cells of peripheral blood smear images using curvelet transform. Computational and Mathematical Methods in Medicine, In press, 2012.

(11) Roli F. and Giacinto G. Design of multiple classifier systems. Hybrid methods in pattern recognition,2002.

(12) Goumas Stefanos K., Dimou Ioannis N., and Zervakis Michalis E. Combination of multiple classifiers for post-placement quality inspection of components: A comparative study. Information Fusion, 11:149{162, 2010.

(13) Mahdi Tabassian, Reza Ghaderi, and Reza Ebrahimpour. Knitted fabric defect classification for uncertain labels based on dempstershafer theory of evidence. Expert Systems with Applications, 38:5259{5267,

(14) Rottensteiner Franz, Trinder John, Clode Simon, and Kubik Kurt. Using the dempstershafer method for the fusion of lidar data and multi-spectral images for building detection. Information Fusion, 6:283{300,2005.

(15) Hicham Laanaya, Arnaud Martin, Driss Aboutajdine, and Ali Khenchaf. Support vector regression of membership functions and belief functions application for pattern recognition. Information Fusion,11:338{350, 2010.10

(16) A.-S. Capelle, O. Colot, and C. Fernandez-Maloigne. Evidential segmentation scheme of multi-echo mr images for the detection of brain tumors using neighborhood information. Information Fusion, 5:203{216,2004.

(17) Zhang Nan, Ruan Su, Lebonvallet Stephane, Liao Qingmin, and Zhu Yuemin. Kernel feature selection to fuse multi-spectral mri images for brain tumor segmentation. Computer Vision and Image Understanding, 115:256{269, 2011.

(18) W. Lin, J. Xiao, and E. Micheli-Tzanakou. A computational intelligence system for cell classification. IEEE international conference on information technology applications to biomedecine, May 1998.

(19) Adollah R., Mashor M.Y., Mohd Nasir N.F., Rosline H., Mahsin H., and Adilah H. Blood cell image segmentation: A review. Biomed 2008, Proceedings, 21:141{144, 2008.

(20) [20] K. Jiang, Q. Liao, and Y. Xiong. A novel white blood cell segmentation scheme based on feature space clustering. Soft Computing, 10:12{19, 2006.

(21) Meas-Yedid V., Glory E., morelon E., Pinset Ch., Stamon G., , and Olivo-Marin J-C. Automatic color space selection for biological image segmentation. IAPR 17th International Conference on Pattern Recognition, 3:514{517, August 2004.

(22) Cyril Meurie, Olivier Lezoray, Louahdi Khoudour, and Abderrahim Elmoataz. Morphological hierarchical segmentation and color spaces. International Journal of Imaging Systems and Technologies, 20:167178,

(23) N. Vandenbroucke. Segmentation d'images couleur par classi_cation de pixels dans des espaces d'attributs colorimtriques adapts. Application l'analyse d'image de football. PhD thesis, University of Lille 1, France, 2000.

(24) Andreas Koschan and Mongi Abidi. Digital color image processing. John Wiley and Sons, Inc, 2008.

(25) V. Vapnik. Statistical Learning Theory. John Wiley and Sons, Chichester, 1998.

(26) Chih-Chung Chang and Chih-Jen Lin. ibsvmg: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 27(2,3):1{27, 2011. Software available at http://www.csie.ntu.edu.tw/cjlin/libsvm.

(27) H. Zouari, L. Heutte, Y. Lecourier, and A. Alimi. An overview of classifier combination methods in pattern recognition. RFIA'2002, 2:449{508, 2002.

(28) K. Ghosh, Y. Seng Ng, and R. Srinivasan. Evaluation of decision fusion strategies for effective collaboration among heterogeneous fault diagnostic methods. Computers and Chemical Engineering Vol, 35:342{355, February 2011.

(29) M. Tabassian, R. Ghaderi, and R. Ebrahimpour. Knitted fabric defect classification for uncertain labels based on dempster-shafer theory of evidence. Expert Systems with Applications, 38:5259{5267, May 2011.

(30) T. Denoeux. A k-nearest neighbor classification rule based on dempster-shafer theory. IEEE Transactions on Systems, Man and Cybernetics, 25(5):804{813, 1995.

(31) L. M. Zouhal and T. Denoeux. An evidence-theoritic k-nn rule with parameter optimization. IEEE Transactions on Systems, Man and Cybernetics, 28:263{271, 1998.

(32) Salim Chitroub. combinaison de classifiers : une approche pour l'amlioration de la classification d'images multisources/multidates de tldtection. Tldection, 4(3):289{301, 2004.

(33) Mourtada Benazzouz, Ismahan Baghli, and Med Amine Chikh. Microscopic image segmentation based on pixel classification and dimensionality reduction. International Journal of Imaging Systems and Technology, 23(1):22{28, 2013.