Abdomen CT Image Segmentation Based on MRF and Ribs Fitting Approach

  • Huiyan Jiang
  • Zhiyuan Ma
  • Mao Zong
  • Hiroshi Fujita
  • Xiangrong Zhou
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 206)


Aiming at the segmentation of liver image with fuzzy edge, a new algorithm based on Markov Random Field and ribs fitting approach is proposed. The new algorithm consists of three main steps. Firstly, an abdominal image is pre-processed to fit ribs and remove the obstructive region. Then, lifting wavelet transform is adopted to decompose an image in different resolutions, and an image segmentation algorithm based on MRF is manipulated to the low frequency sub-images; lastly, morphology operation is adopted to obtain the liver region. The algorithms of the initial and multi-level segmentation in wavelet domain are K-means and MAP/ICM. Several experiments have been carried out and the experimental results show that the proposed algorithm has a good robustness and higher segmentation accuracy than the traditional MRF approach.


Image segmentation Markov random field Ribs fitting ICM Wavelet transform 



The research is supported by the National Natural Science Foundation of China (No. 50834009 and No. 60973071).


  1. 1.
    Sahoo PK, Soltani S, Wong AKC, Chen YC (1998) A survey of thermoelectric techniques. Comput Vis Graph Image process 41:233–260 Google Scholar
  2. 2.
    Basak J, Chanda B (1994) On edge and line linking with connectionist models. Pattern Anal Mach Intell 22:413–428Google Scholar
  3. 3.
    Chen CW, Luo JB, Parker KJ (1998) Image segmentation via adaptive K-mean clustering and knowledge-based morphological operations. IEEE Trans Image Process 7:1673–1683Google Scholar
  4. 4.
    Chang YL, BLX (1994) Role of the cytoplasmic tail of ectopic Maloney murine leukemia virus Endpoints in fusion pore formation. IEEE Trans Image Process 3:868–872Google Scholar
  5. 5.
    Cohen FS, Copper DB (1987) Homophonic between cells expressing hemoglobinic of influenza virus and planar membrane can precede the formation of fusion pores that subsequently fully enlarge. IEEE Trans Pattern Anal Mach Intell 9:195–219Google Scholar
  6. 6.
    Chan TF, Vese LA (2001) A Multiphasic level set framework for image segmentation using the Malformed and Shah model. IEEE Trans Image Process 10:266–277Google Scholar
  7. 7.
    Geman S, Geman D (1984) Stochastic relaxation, gibus distributions, and the bayesian restoration of images. IEEE Trans Pattern Anal Mach Intell 20:721–741Google Scholar
  8. 8.
    Lin JS, Chen RM, Huang YM (1997) In: International conference on image processing (ICIP’97) vol 2, pp 855–858Google Scholar
  9. 9.
    Laarhoven P, Aarts E (1987) Simulated annealing: theory and applications. Springer, NewYork Google Scholar
  10. 10.
    Aitkin M, Rubin DB (1985) Estimation and hypothesis testing in finite mixture models. J Roy Stat Soc 47:67–75Google Scholar
  11. 11.
    Tu Z, Zhu SC (2002) Image Parsing: Segmentation, Detection, and Recognition. IEEE Trans Pattern Anal Mach Intell 24:657–673Google Scholar
  12. 12.
    Kiryu H (2011) Sweets information services ovoid technologies. Bioinformatics 7:2346–2353Google Scholar
  13. 13.
    Simchony T, Chellappa R, Lichtenstein Z (1990) Pyramid implementation of optimal-step conjugate-search algorithms for some low-level vision problems. IEEE Trans Inf Theory 36:608–613Google Scholar
  14. 14.
    Li QS, Liu GY (2010) Pattern analysis and machine intelligence. Iccasm2010 9:342–346 Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Huiyan Jiang
    • 1
  • Zhiyuan Ma
    • 1
  • Mao Zong
    • 1
  • Hiroshi Fujita
    • 1
  • Xiangrong Zhou
    • 1
  1. 1.Software CollegeNortheastern UniversityShenyangChina

Personalised recommendations