Date-driven Based Image Enhancement for Segmenting of MS Lesions in T2-w and Flair MRI

  • Ziming Zeng
  • Zhonghua Han
  • Yitian Zhao
  • Reyer Zwiggelaar
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 269)


This paper proposed a data-driven based image enhancement scheme to segment Multiple Sclerosis (MS) lesions. It utilizes a class-adaptive Gaussian Markov random field modelling (HMRF) and mutual information to automatic enhance the MS lesions. Then an alpha matting technique is used to refine the segmentation results. The advantages of the approach lies in its date-driven processing. It can automatically enhance the density of MS lesions, which is guided by calculating the mutual information value of the segmentation results in the successive steps. In addition, the partial volume effects are considered and the regions of interests are segmented in a sub-pixel precision. The experiments on real MR images show the proposed segmentation method can effectively segment MS lesions.


Date-driven Enhancement MS lesions Segmentation Mutual information 


  1. 1.
    Dugas-Phocion G, Gonzalez MA, Lebrun C, Chanalet S, Bensa C, Ma- landain G, Ayache N (2004) Hierarchical segmentation of multiple sclerosis lesions in multi-sequence MRI. In: Biomedical imaging: nano to macroGoogle Scholar
  2. 2.
    Zeng Z, Zwiggelaar R (2011) Joint histogram modelling for segmentation multiple sclerosis lesions. LNCS 6930:133–144MathSciNetGoogle Scholar
  3. 3.
    Souplet JC, Lebrun C, Ayache N, Malandain G (2008) An automatic segmentation of T2-FLAIR multiple sclerosis lessions. In: The MIDAS journal—MS lesion segmentation (MICCAI 2008 workshop), pp 1–5Google Scholar
  4. 4.
    Collignon A, Vandermeulen D, Marchal G, Suetens P (1997) Multimodality image registration by maximization of mutual information. IEEE Trans Med Imaging 16(2):187C198Google Scholar
  5. 5.
    Stephen MS (2002) Fast robust automated brain extraction. Hum Brain Mapp 17(3):143–155CrossRefMathSciNetGoogle Scholar
  6. 6.
    Wang W, Feng Q, Liu L, Chen W (2008) Segmentation of brain MR images through class-adaptive Gauss-Markov random field model and the EM algorithm. J Image Graph 13(3):488–493Google Scholar
  7. 7.
    Grosman RI, Mcgowan JC (1998) Perspectives on multiple sclerosis. AJNR 19:176–186Google Scholar
  8. 8.
    Prima S, Ourselin S, Ayache N (2002) Computation of the mid-sagittal plane in 3-D brain images. IEEE Trans Med Imaging 21(2):122–138CrossRefGoogle Scholar
  9. 9.
    Levin A, Lischinski D, Weiss Y (2008) A closed form solution to natural image matting. IEEE Trans Pattern Anal Mach Intell 30(2):228–242CrossRefGoogle Scholar
  10. 10.
    Styner M, Lee J, Chin B, Chin MS, Commowick O, Tran HH, Jewells V, Warfield S (2008) 3D segmentation in the clinic: a grand challenge II: MS lesion segmentation. MIDAS J 1–5Google Scholar
  11. 11.
    Geremia E, Menze BH, Clatz O, Konukoglu E, Criminisi A, Ayache N (2010) Spatial decision forests for MS lesion segmentation in multi-channel MR images. LNCS 6361:111–118Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Ziming Zeng
    • 1
    • 2
  • Zhonghua Han
    • 1
  • Yitian Zhao
    • 2
  • Reyer Zwiggelaar
    • 2
  1. 1.Information and Control Engineering FacultyShenyang Jianzhu UniversityLiaoningChina
  2. 2.Department of Computer ScienceAberystwyth UniversityAberystwythUK

Personalised recommendations