Multiresolution adaptive K-means algorithm for segmentation of brain MRI

  • B. C. Vemuri
  • S. Rahman
  • J. Li
Session IA2b — Biomedical Imaging
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1024)


Segmentation of MR brain scans has received an enormous amount of attention in the medical imaging community over the past several years. In this paper we propose a new and general segmentation algorithm involving 3D adaptive K-Means clustering in a multiresolution wavelet basis. The voxel image of the brain is segmented into five classes namely, cerebrospinal fluid, gray matter, white matter, bone and background (remaining pixels). The segmentation problem is formulated as a maximum a posteriori (MAP) estimation problem wherein, the prior is assumed to be a Markov Random Field (MRF). The MAP estimation is achieved using an iterated conditional modes technique (ICM) in wavelet basis. Performance of the segmentation algorithm is demonstrated via application to phantom images as well as MR brain scans.


Segmentation Algorithm Markov Random Field Wavelet Basis Phantom Image Iterate Conditional Mode 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    R. A. Hummel A. Rosenfeld and S. W. Zucker. Scene labelling by relaxation operations. IEEE transactions on Systems, Man, and Cybernatics, SMC-6(6):420–433, June 1976.Google Scholar
  2. [2]
    J. Besag. On statistical analysis of dirty pictures. Journal of Royal Statistical Society B, 48(3):259–302, 1986.Google Scholar
  3. [3]
    C. Bouman and B. Liu. Multiple resolution segmentation of textured images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13(2):99–113, 1991.Google Scholar
  4. [4]
    H. E. Cline, C. L. Doumulin, H. R. Hart, W. E. Lorensen, and S. Ludke. 3-D reconstruction of the brain from magnetic resonance images using a connectivity algorithm. Magnetic Resonance Imaging, 5:345–352, 1987.Google Scholar
  5. [5]
    Ingrid Daubechies. Ten Lectures on Wavelet. Society for Industrial and Applied Mathematics, Philadelphia, PA, 1992.Google Scholar
  6. [6]
    C. DeCarli, J. Moisog, D. G. M. Murphy, D. Teichberg, S. I. Rapoport, and B. Horwitz. Method of quantification of brain, ventricular, and subarachnoid csf volumes for mri images. Journal of Computer assisted Tomography, 16(2):274–284, 1992.Google Scholar
  7. [7]
    H. Derin and H. Elliott. Modelling and segmentation of noisy and textured images using Gibbs random field. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-9(1):39–55, 1987.Google Scholar
  8. [8]
    S. Geman and D. Geman. Stochastic relaxation, Gibbs distributions, and the bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-6(6):721–741, 1984.Google Scholar
  9. [9]
    R. A. Hummel and S. W. Zucker. On the foundation of relaxation labelling process. IEEE Transactions on Pattern Analysis and Machine Intelligence, 5(3):267–287, May 1983.Google Scholar
  10. [10]
    M. Joliot and B. M. Majoyer. Three dimensional segmentation and interpolation of magnetic resonance brain images. IEEE Transactions on Medical Imaging, 12(2):269–277, 1993.Google Scholar
  11. [11]
    S. Lakshmanan and H. Derin. Simultaneous parameter estimation and segmentation of Gibbs random fields using simulated annealing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11:799–813, August 1989.Google Scholar
  12. [12]
    S. G. Mallat. A theory of multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-11:674–693, 1989.Google Scholar
  13. [13]
    T. N. Pappas. An adaptive clustering algorithm for image segmentation. IEEE Transactions on Signal Processing, 40(4):901–914, 1992.Google Scholar
  14. [14]
    B. C. Vemuri and A. Radisavljevic. Multiresolution stochastic shape models with fractal priors. acm Transactions on Graphics, 13(2):177–207, 1994.Google Scholar
  15. [15]
    B. C. Vemuri, A. Radisavljevic, and C. M. Leonard. Multiresolution stochastic 3D shape models for image segmentation. In 13th International Conference, IPMI. Springer-Verlag, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • B. C. Vemuri
    • 1
  • S. Rahman
    • 2
  • J. Li
    • 2
  1. 1.Department of Computer & Information SciencesUniversity of FloridaGainesville
  2. 2.Department of Electrical & Computer EngineeringUniversity of FloridaGainesville

Personalised recommendations