Local Gaussian Distribution Fitting Based FCM Algorithm for Brain MR Image Segmentation

  • Zexuan Ji
  • Yong Xia
  • Quansen Sun
  • Deshen Xia
  • David Dagan Feng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7202)


Automated segmentation of brain MR images into gray matter, white matter and cerebrospinal fluid (CSF) has been extensively studied with many algorithms being proposed. However, most of those algorithms suffer from limited accuracy, due to the presence of intrinsic noise, low contrast and intensity inhomogeneity (INU) in MR images. In this paper, we propose the local Gaussian distribution fitting based fuzzy c-means (LGDFFCM) algorithm for automated and accurate brain MR image segmentation. In this algorithm, an energy function is defined by using the kernel function to characterize the fitting of local Gaussian distributions to the local image data within the neighborhood of each pixel. A new local scale computing method is developed to estimate the variances of local Gaussian distributions. We compared our algorithm to several state-of-the-art segmentation approaches in both synthetic and clinical data. Our results show that the proposed LGDFFCM algorithm can substantially reduce the impact of by noise, low contrast and INU, and produce satisfying segmentation of brain MR images.


MR image segmentation local Gaussian distribution fitting adaptive local scale 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pham, D., Prince, J.: Adaptive fuzzy segmentation of magnetic resonance images. IEEE Trans. Med. Imag. 18, 737–752 (1999)CrossRefGoogle Scholar
  2. 2.
    Ahmed, M., Yamany, S., Mohamed, N., Farag, A., Moriarty, T.: A modified fuzzy c-means algorithm for bias field estimation and segmentation of MRI data. IEEE Trans. Med. Imag. 21, 193–199 (2002)CrossRefGoogle Scholar
  3. 3.
    Liew, A., Yan, H.: An adaptive spatial fuzzy clustering algorithm for 3-D MR image segmentation. IEEE Trans. Med. Imag. 22, 1063–1075 (2003)CrossRefGoogle Scholar
  4. 4.
    Chen, S.C., Zhang, D.Q.: Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure. IEEE Trans. Systems Man Cybernet. 34, 1907–1916 (2004)CrossRefGoogle Scholar
  5. 5.
    Yang, M.S., Tsai, H.S.: A Gaussian kernel-based fuzzy c-means algorithm with a spatial bias correction. Pattern Recognition Letters 29, 1713–1725 (2008)CrossRefGoogle Scholar
  6. 6.
    Liao, L., Lin, T., Li, B.: MRI brain image segmentation and bias field correction based on fast spatially constrained kernel clustering approach. Pattern Recognition Letters 29, 1580–1588 (2008)CrossRefGoogle Scholar
  7. 7.
    Wang, L., He, L., Mishra, A., Li, C.: Active contours driven by local Gaussian distribution fitting energy. Signal Processing 89, 2435–2447 (2009)MATHCrossRefGoogle Scholar
  8. 8.
    Li, C., Xu, C., Anderson, A., Gore, J.: MRI Tissue Classification and Bias Field Estimation Based on Coherent Local Intensity Clustering: A Unified Energy Minimization Framework. In: Prince, J.L., Pham, D.L., Myers, K.J. (eds.) IPMI 2009. LNCS, vol. 5636, pp. 288–299. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  9. 9.
    Saha, P.K., Udupa, J.K.: Optimum image thresholding via class uncertainty and region homogeneity. IEEE Trans. Pattern Anal. Mach. Intell. 23, 689–706 (2001)CrossRefGoogle Scholar
  10. 10.
    Madabhushi, A., Udupa, J.K., Souza, A.: Generalized scale: theory, algorithms, and application to image inhomogeneity correction. Computer Vision and Image Understanding 21, 101–121 (2006)Google Scholar
  11. 11.
    Katkovnik, V., Shmulevich, I.: Nonparametric density estimation with adaptive varying window size. In: Image and Signal Processing for Remote Sensing VI, vol. 4170, pp. 141–150 (2001)Google Scholar
  12. 12.
    Brainweb, Simulated Brain Database, http://www.bic.mni.mcgill.ca/brainweb/

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zexuan Ji
    • 1
    • 2
  • Yong Xia
    • 2
  • Quansen Sun
    • 1
  • Deshen Xia
    • 1
  • David Dagan Feng
    • 2
    • 3
    • 4
  1. 1.School of Computer Science and TechnologyNanjing University of Science and TechnologyNanjingChina
  2. 2.Biomedical and Multimedia Information Technology (BMIT) Research Group, School of Information TechnologiesUniversity of SydneyAustralia
  3. 3.Centre for Multimedia Signal Processing (CMSP), Department of Electronic, & Information EngineeringHong Kong Polytechnic UniversityHong Kong
  4. 4.Med-X Research InstituteShanghai JiaoTong UniversityChina

Personalised recommendations