A Novel Algorithm for Automatic Brain Structure Segmentation from MRI

  • Qing He
  • Kevin Karsch
  • Ye Duan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5358)


This paper proposes an automatic segmentation algorithm that combines clustering and deformable models. First, a k-means clustering is performed based on the image intensity. A hierarchical recognition scheme is then used to recognize the structure to be segmented, and an initial seed is constructed from the recognized region. The seed is then evolved under certain deformable model mechanism. The automatic recognition is based on fuzzy logic techniques. We apply our algorithm for the segmentation of the corpus callosum and the thalamus from brain MRI images. Depending on the specific features of the segmented structures, the most suitable recognition schemes and deformable models are employed. The whole procedure is automatic and the results show that this framework is fast and robust.


Segmentation deformable models clustering corpus callosum thalamus 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 1(4), 321–331 (1988)CrossRefGoogle Scholar
  2. 2.
    Liang, J., McInerney, T., Terzopoulos, D.: United snakes. Medical Image Analysis 10, 215–233 (2006)CrossRefGoogle Scholar
  3. 3.
    McInerney, T., Sharif, M.R.: Sketch initialized snakes for rapid, accurate and repeatable interactive medical image segmentation. In: 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, pp. 398–401 (2006)Google Scholar
  4. 4.
    He, Q., Duan, Y., Miles, J., Takahashi, N.: A Context-Sensitive Active Contour for 2D Corpus Callosum Segmentation. International Journal of Biomedical Imaging 2007, Article ID 24826, 8 pages (2007)CrossRefGoogle Scholar
  5. 5.
    McInerney, T., Hamarneh, G., Shenton, M., Terzopoulos, D.: Deformable organisms for automatic medical image analysis. Medical Image Analysis 6, 251–266 (2002)CrossRefGoogle Scholar
  6. 6.
    Cootes, T., Cooper, D., Taylor, C., Graham, J.: Active shape models—their training and application. Computer Vision and Image Understanding 61(1), 38–59 (1995)CrossRefGoogle Scholar
  7. 7.
    Cootes, T., Beeston, C., Edwards, G., Taylor, C.: A Unified Framework for Atlas Matching Using Active Appearance Models. In: Proc. Image Processing in Medical Imaging Conf., Visegrad, Hungary, pp. 322–333 (1999)Google Scholar
  8. 8.
    Taron, M., Paragios, N., Jolly, M.P.: Uncertainty-driven non-parametric knowledge-based segmentation: the corpus callosum case. In: VLSM, pp. 198–207 (2005)Google Scholar
  9. 9.
    Stegmannac, M.B., Daviesb, R.H., Ryberg, C.: Corpus callosum analysis using MDL-based sequential models of shape and appearance. In: Proceedings of SPIE, vol. 5370, pp. 612–619 (2004)Google Scholar
  10. 10.
    Chakraborty, A., Duncan, J.S.: Integration of boundary finding and region-based segmentation using game theory. In: Bizais, Y., et al. (eds.) Information Processing in Medical Imaging, pp. 189–201. Kluwer, Dordrecht (1995)Google Scholar
  11. 11.
    Chakraborty, A., Worring, M., Duncan, J.S.: On multifeature integration for deformable boundary finding. In: Proc. Intl. Conf. on Computer Vision, pp. 846–851 (1995)Google Scholar
  12. 12.
    Ronfard, R.: Region-based strategies for active contour models. Intl. J. of Computer Vision 13(2), 229–251 (1994)CrossRefGoogle Scholar
  13. 13.
    Zhu, S.C., Lee, T.S., Yuille, A.L.: Region competition: Unifying snakes, region growing, and bayes/mdl for multiband image segmentation. In: Proc. Intl. Conf. on Compute Vision, pp. 416–423 (1995)Google Scholar
  14. 14.
    Jones, T.N., Metaxas, D.N.: Segmentation Using Deformable Models With Affinity-Based Localization. CVR Med. (1997)Google Scholar
  15. 15.
    Jones, T.N., Metaxas, D.N.: Image Segmentation based on the Integration of Pixel Affinity and Deformable Models. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 23-25, p. 330 (1998)Google Scholar
  16. 16.
    Ronsen, C., Denijver, P.A.: Connected components in binary images. In: The detection problem, Research Studies Press (1984)Google Scholar
  17. 17.
    Zadeh, L.A.: Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst. 90, 111–127 (1997)MathSciNetzbMATHCrossRefGoogle Scholar
  18. 18.
    Hata, Y., Kobashi, S., Hirano, S., Kitagaki, H., Mori, E.: Automated Segmentation of Human Brain MR Images Aided by Fuzzy Information Granulation and Fuzzy Inference. IEEE Transactions on Systems, Man, and Cybernetics—PART C: applications and reviews 30(3) (2000)Google Scholar
  19. 19.
    Kandel, A.: Fuzzy Expert Systems. CRC, Boca Raton (1992)Google Scholar
  20. 20.
    Pedrycz, W.: Control and Fuzzy Systems. Research Studies Press Ltd., London (1993)zbMATHGoogle Scholar
  21. 21.
    Kruse, R., Gebhardt, J., Klawonn, F.: Foundations of Fuzzy Systems. Wiley, New York (1994)Google Scholar
  22. 22.
    Bello, M., Ju, T., Carson, J., Warren, J., Chiu, W., Kakadiaris, I.A.: Learning-based segmentation framework for tissue images containing gene expression data. IEEE Transactions on Medical Imaging 26(5) (2007)Google Scholar
  23. 23.
    Chan, T.F., Vese, L.A.: Active Contours without Edges. IEEE Transactions on Image Processing 10(2) (2001)Google Scholar
  24. 24.
    Belyaev, A.G., Anoshkina, E.V., Yoshizawa, S., Yano, M.: Polygonal curve evolutions for planar shape modeling and analysis. International Journal of Shape Modeling 5(2), 195–217 (1999)CrossRefGoogle Scholar
  25. 25.
    Lorensen, W.E., Cline, H.E.: Marching Cubes: A High Resolution 3D Surface Construction Algorithm. In: Proceedings of SIGGRAPH 1987, vol. 21(4), pp. 163–1694 (1987)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Qing He
    • 1
  • Kevin Karsch
    • 1
  • Ye Duan
    • 1
  1. 1.Department of Computer ScienceUniversity of Missouri-ColumbiaColumbiaUSA

Personalised recommendations