Recognition of Marrow Cell Images Based on Fuzzy Clustering

Full Text (PDF, 742KB), PP.40-49

Views: 0 Downloads: 0


Xitao Zheng 1,* Yongwei Zhang 1 Yehua Yu 2 Jing Zhang 2 Jun Shi 2

1. College of Information Technology, Shanghai Ocean University No.999 HuCheng Circle Road, LinGang New City, Shanghai, 201306, China

2. Hematology Department, Shanghai Jiao Tong University Affiliated No.6 People’s Hospital No. 600 Yishan Road, Shanghai, 200233, China

* Corresponding author.


Received: 9 Apr. 2011 / Revised: 2 Aug. 2011 / Accepted: 21 Sep. 2011 / Published: 8 Feb. 2012

Index Terms

C-mean Fuzzy clustering, mouse marrow, pattern recognition, cell counting


In order to explore the leukocyte distribution of human being to predict the recurrent leukemia, the mouse marrow cells are investigated to get the possible indication of the recurrence. This paper uses the C-mean fuzzy clustering recognition method to identify cells from sliced mouse marrow image. In our image processing, red cells, leukocytes, megakaryocyte, and cytoplasm can not be separated by their staining color, RGB combinations are used to classify the image into 8 sectors so that the searching area can be matched with these sectors. The gray value distribution and the texture patterns are used to construct membership function. Previous work on this project involves the recognition using pixel distribution and probability lays the background of data processing and preprocessing. Constraints based on size, pixel distribution, and grayscale pattern are used for the successful counting of individual cells. Tests show that this shape, pattern and color based method can reach satisfied counting under similar illumination condition.

Cite This Paper

Xitao Zheng, Yongwei Zhang, Yehua Yu, Jing Zhang, Jun Shi, " Recognition of Marrow Cell Images Based on Fuzzy Clustering", International Journal of Information Technology and Computer Science(IJITCS), vol.4, no.1, pp.40-49, 2012. DOI:10.5815/ijitcs.2012.01.06


[1]Sufyan Y. Ababneh, Jeff W. Prescott, Metin N. Gurcan. Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research. Medical Image Analysis 15 (2011) 438–448

[2]Ethan S. Brown , Tony F. Chan , Xavier Bresson. Completely Convex Formulation of the Chan-Vese Image Segmentation Model. INTERNATIONAL JOURNAL OF COMPUTER VISION.2011.

[3]Xitao Zheng, Jun Shi, Yehua Yu, Yongwei Zhang. A New Method for Automatic Counting of Marrow Cells. Proceeding of the 4th International Conference on Biomedical Engineering and Informatics, 2011, page 44-48.

[4]Xitao Zheng, Jun Shi, Yehua Yu, Yongwei Zhang. Analysis of leukemia Development Based on Marrow Cell Images. Proceeding of the 4th International Congress on Image and Signal Processing, 2011, page 95-99.

[5]Javier Cruz-Mota, Iva Bogdanova , Benoît Paquier, Michel Bierlaire, Jean-Philippe Thiran. Scale Invariant Feature Transform on the Sphere: Theory and Applications. INTERNATIONAL JOURNAL OF COMPUTER VISION.

[6]En-yong Wang,Zhengpin Gou, Ai-min Miao, Shu-qing Peng, Zhen-yang Niu, and Xin-lin Shi. Recognition of Blood Cell Images Based on Color Fuzzy Clustering. Fuzzy Information and Engineering Volume 2. Advances in Soft Computing, 2009, Volume 62/2009, 69-75

[7]Nipon Theera-Umpon. Patch-Based White Blood Cell Nucleus Segmentation Using Fuzzy Clustering. Transactions on Electrical Eng, Electronics, and Communications, ECTI-EEC 3, 15-19 (2005). 

[8]AI Da-Ping, YIN, Xiao-Hong, LIU Bo-Qiang, LIU Zhong-Guo, YUAN Qing-Wei, LI Xiao-Mei. The Algorithm of Marrow Cell Identification and Classification. Chinese Journal of Biomedical Engineering, 2009, 28(4).

[9]Hiroshi Hatsuda. Automatic Cell Identification Using a Multiple Marked Point Process. The 2010 International Conference on Bioinformatics and Computational Biology.

[10]Xitao Zheng, Yongwei Zhang . A Fish Population Counting Method Using Fuzzy Artificial Neural Network. The 2010 International Conference on Progress in Informatics and Computing conference, page 225-228.

[11]Junlan Shang, Xitao Zheng, Yongwei Zhang. A Teeth Identification Method Based on Fuzzy Recognition. The 2nd International Conference on Intelligent Human-Machine Systems and Cybernetics, 2010, page 271-275.