A Weighted K-means Algorithm applied to Brain Tissue Classification


  • Guillermo N. Abras Signal Processing Laboratory, School of Engineering, Universidad Nacional de Mar del Plata, Argentina
  • Virginia Laura Ballarín Signal Processing Laboratory, School of Engineering, Universidad Nacional de Mar del Plata, Argentina


Pattern-Recognition, Classification, Images, Brain, Tissue


Tissue classification in Magnetic Resonance (MR) brain images is an important issue in the analysis of several brain dementias. This paper presents a modification of the classical K-means algorithm taking into account the number of times specific features appear in an image, employing, for that purpose, a weighted mean to calculate the centroid of every cluster. Pattern Recognition techniques allow grouping pixels based on features similarity. In this paper, multispectral gray-level intensity MR brain images are used. T1, T2 and PD-weighted images provide different and complementary information about the tissues. Segmentation is performed in order to classify each pixel of the resulting image according to four possible classes: cerebro-spinal fluid (CSF), white matter (WM), gray matter (GM) and background. T1, T2 and PD-weighted images are used as patterns. The proposed algorithm weighs the number of pixels corresponding to each set of gray levels in the feature vector. As a consequence, an automatic segmentation of the brain tissue is obtained. The algorithm provides faster results if compared with the traditional K-means, thereby retrieving complementary information from the images.


Download data is not yet available.


[1] P. Davis, A. Gray, M. Albert, et al. “The Consortium to Establish a Registry for Alzheimer's Disease, ” Neurology, Vol. 42, 1992, pp. 1676-1680.
[2] N. Fox, and P. Freeborough, “Brain atrophy progression measured from registered serial MRI: validation and application to Alzheimer's disease,” J. Magn. Reson. Imaging, Vol. 7 No.6, 1997, pp. 1069-1075.
[3] J. Tanabe, D. Amend, N. Scuff, et al. “Tissue segmentation of the brain in Alzheimer Disease,” Am. J. Neuroradiol., Vol. 18, 1997, pp. 115-123.
[4] S.P. Raya, “Low level segmentation of 3D resonance brain images,” IEEE Trans. Med. Imaging, vol. 9 , 1990, pp. 2.
[5] S. Chen, L. Wei-chun, and C. Chen, “Medical image understanding system based on DempsterShafer reasoning,” SPIE Biomedical Imag. Processing II, 1991, San Jose, California.
[6] Clarke, L.P. et al. (1992): ‘Comparison of Supervised Pattern Recognition Techniques and Unsupervised Methods for MRI Segmentation," Proc. SPIE Medical Imaging VI Conference, Vol. 1652 , SPIE Press, Bellingham, WA, 668-677, 1992.
[7] Vannier, M.W., Brunsden, B.S., Hildebolt, C.F., Falk, D., Cheverud, J.M., Figiel, G.S., Perman, W.H., Kohn, A., Robb, R.A. and Yoffie R.L. ‘Brain surface cortical sulcal lengths: quantification with three- dimensional MR imaging’ Radiology, Vol 180, 479-484 1991.
[8] R. Duda, P. Hart, and D. Stork, “Pattern Classification and Scene Analysis”. Ed. Wiley New York, 2000.
[9] A. Jain, R. Duin, and J. Mao, “Statistical pattern recognition: A review”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 22 No.1, 2000, pp. 4-37.
[10] G. Gerig, J. Martin, and R. Kikinis, “Unsupervised tissue type segmentation of 3D dualecho MR head data,” Image Vision Computer, Vol.10, 1992, pp. 349–360.
[11] B. Alfano, B. Brunetti, et al. “Unsupervised, automated segmentation of the normal brain using multispectral relaxometric magnetic resonance approach,” Magn. Reson. Med., Vol. 37, 1997, pp. 84-93.
[12] R. De La Paz, E. Herskovits, V. Gesu, et al. “Cluster analysis of medical magnetic resonance images MRI data: Diagnostic application and evaluation,” SPIE Extracting Meaning from Complex Data: Processing, Display, Interaction, Vol. 1259, 1990, pp. 176 –181.
[13] Y. Wei, J. Fritts, and S. Fangting, “A hierarchical image segmentation algorithm,” ICME '02. Proceedings. IEEE International Conference, Vol. 2, 2002, pp. 221-224.
[14] J.C. Bezdek, “Pattern Recognition with fuzzy objective function algorithms,” New York: Plenum Press, 1981.
[15] K. Krishna, K.R. Ramakrishnan, M.A.L. Thathachar, “Vector quantization using genetic Kmeans algorithm for image compression,” Proceedings of the International Conference on Information, Communications and Signal Processing, ,Vol. 3, 1997, pp. 1585-1587.
[16] K. Krishna, and M. Narasimha Murty, “Genetic K-means algorithm,” IEEE Trans. on Systems, Man and Cybernetics, Vol. 29,1999, pp. 3.
[17] L.O Hall,, A.M. Bensaid, L.P. Clarke, R.P. Velthuizen, M.S. Silbiger and J.C. Bezdek, “A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain,” IEEE Trans. on Neural Networks, Vol. 3, No. 5, 1992, pp. 672- 682.
[18] J. Tou and R. Gonzalez, “Pattern Recognition Principles,” Ed. Adisson-Wesley, 1974.
[19] T. Bartlett, M. Vannier, D. Mc Keel, M. Gado, C. Hildebolt and R. Walkup, “Interactive segmentation of cerebral gray matter, white matter, and CSF: photographic and MR images,” Comp. Med. Imag. Graphics, Vol. 18 No. 6, 1994, pp. 449-460.
[20] G. Abras, V. Ballarin, y M.González, “Aplicación de Reconocimiento de Patrones en la Clasificación de Tejido Cerebral,” Actas del Congreso Argentino de Bioingeniería. Tafí del Valle. Septiembre 2001. (Publicadas en CD).




How to Cite

Abras, G. N., & Ballarín, V. L. (2005). A Weighted K-means Algorithm applied to Brain Tissue Classification. Journal of Computer Science and Technology, 5(03), p. 121–126. Retrieved from https://journal.info.unlp.edu.ar/JCST/article/view/860



Original Articles