An Efficient Approach to Intensity Inhomogeneity Compensation Using c-Means Clustering Models

  • László Szilágyi
  • David Iclănzan
  • Lehel Crăciun
  • Sándor Miklós Szilágyi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)


Intensity inhomogeneity or intensity non-uniformity (INU) is an undesired phenomenon that represents the main obstacle for magnetic resonance (MR) image segmentation and registration methods. Various techniques have been proposed to eliminate or compensate the INU, most of which are embedded into clustering algorithms, and they generally have difficulties when INU reaches high amplitudes. This study reformulates the design of c-means clustering based INU compensation techniques by identifying and separating those globally working computationally costly operations that can be applied to gray intensity levels instead of individual pixels. The theoretical assumptions are demonstrated using the fuzzy c-means algorithm, but the proposed modification is compatible with a various range of c-means clustering based techniques. Experiments using synthetic phantoms and real MR images indicate that the proposed approach produces practically the same segmentation accuracy as the conventional formulation, but 20-30 times faster.


image segmentation magnetic resonance imaging intensity inhomogeneity c-means clustering histogram 


  1. 1.
    Ahmed, M.N., Yamany, S.M., Mohamed, N., Farag, A.A., Moriarty, T.: A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data. IEEE Trans. Med. Imag. 21(3), 193–199 (2002)CrossRefGoogle Scholar
  2. 2.
    Bezdek, J.C.: Pattern recognition with fuzzy objective function algorithms. Plenum, New York (1981)CrossRefzbMATHGoogle Scholar
  3. 3.
    Derganc, J., Likar, B., Pernus̆, F.: Nonparametric segmentation of multispectral MR images incorporating spatial and intensity information. Progr. Biomed. Opt. Imag. 3(1), 391–400 (2002)Google Scholar
  4. 4.
    Internet Brain Segmentation Repository,
  5. 5.
    Johnston, B., Atkins, M.S., Mackiewich, B., Anderson, M.: Segmentation of multiple sclerosis lesions in intensity corrected multispectral MRI. IEEE Trans. Med. Imag. 15(2), 154–169 (1996)CrossRefGoogle Scholar
  6. 6.
    Liew, A.W.C., Hong, Y.: An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation. IEEE Trans. Med. Imag. 22(9), 1063–1075 (2003)CrossRefGoogle Scholar
  7. 7.
    Pal, N.R., Pal, K., Keller, J.M., Bezdek, J.C.: A possibilistic fuzzy c-means clustering algorithms. IEEE Trans. Fuzzy Syst. 13(4), 517–530 (2005)CrossRefGoogle Scholar
  8. 8.
    Pham, D.L., Prince, J.L.: Adaptive fuzzy segmentation of magnetic resonance images. IEEE Trans. Med. Imag. 18(9), 737–752 (1999)CrossRefGoogle Scholar
  9. 9.
    Rajapakse, J.C., Kruggel, J.C.: Segmentation of MR images with intensity inhomogeneities. Image Vis. Comput. 16(3), 165–180 (1998)CrossRefGoogle Scholar
  10. 10.
    Siyal, M.Y., Yu, L.: An intelligent modified fuzzy c-means based algorithm for bias field estimation and segmentation of brain MRI. Patt. Recogn. Lett. 26(13), 2052–2062 (2005)CrossRefGoogle Scholar
  11. 11.
    Sled, J.G., Zijdenbos, A.P., Evans, A.C.: A nonparamtertic method for automatic correction of intensity nonuniformities. IEEE Trans. Med. Imag. 17(1), 87–97 (1998)CrossRefGoogle Scholar
  12. 12.
    Styner, M., Brechbuchler, C., Székely, G., Gerig, G.: Parametric estimate of intensity inhomogeneities applied to MRI. IEEE Trans. Med. Imag. 19(3), 153–165 (2000)CrossRefGoogle Scholar
  13. 13.
    Szilágyi, L., Szilágyi, S.M., Benyó, B., Benyó, Z.: Intensity inhomogeneity compensation and segmentation of MR brain images using hybrid c-means clustering models. Biomed. Sign. Proc. Contr. 6(1), 3–12 (2011)CrossRefzbMATHGoogle Scholar
  14. 14.
    Vemuri, P., Kholmovski, E.G., Parker, D.L., Chapman, B.E.: Coil sensitivity estimation for optimal SNR reconstruction and intensity inhomogeneity correction in phased array MR imaging. In: Christensen, G.E., Sonka, M. (eds.) IPMI 2005. LNCS, vol. 3565, pp. 603–614. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  15. 15.
    Vovk, U., Pernus̆, F., Likar, B.: MRI intensity inhomogeneity correction by combining intensity and spatial information. Phys. Med. Biol. 49(17), 4119–4133 (2004)Google Scholar
  16. 16.
    Vovk, U., Pernus̆, F., Likar, B.: A review of methods for correction of intensity inhomogeneity in MRI. IEEE Trans. Med. Imag. 26(3), 405–421 (2007)Google Scholar
  17. 17.
    Zhang, Y., Brady, M., Smith, S.: Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imag. 20(1), 45–57 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • László Szilágyi
    • 1
  • David Iclănzan
    • 1
  • Lehel Crăciun
    • 1
  • Sándor Miklós Szilágyi
    • 1
  1. 1.Faculty of Technical and Human ScienceSapientia - Hungarian Science University of TransylvaniaTîrgu-MureşRomania

Personalised recommendations