Multiscale Boundary Identification for Medical Images

  • ZuYing Wang
  • Mrinal Mandal
  • Zoltan Koles
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4815)


Boundary identification in medical images plays a crucial role in helping physicians in patient diagnosis. Manual identification of object boundaries is a time-consuming task and is subject to operator variability. Fully automatic procedures are still far from satisfactory in most real situations. In this paper, we propose a boundary identification method based on multiscale technique. Experimental results have shown that the proposed method provides superior performance in medical image segmentation.


Boundary identification multiscale edge detection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Withey, D.: Dynamic edge tracing: recursive methods for medical image segmentation, Ph.D. Thesis, University of Alberta, Canada (2006)Google Scholar
  2. 2.
    Marr, D., Hildreth, E.: Theory of edge detection. Proc. of the Royal Society of London 207, 187–217 (1980)CrossRefGoogle Scholar
  3. 3.
    Mallat, S., Zhong, S.: Characterization of signals from multiscale edges. IEEE Trans. on PAMI 14(7), 710–732 (1992)Google Scholar
  4. 4.
    Tang, Y.Y., Yang, L., Feng, L.: Characterization and detection of edges by Lipschitz exponents and MASW wavelet transform. Proc. Intl. Conf. on Pattern Recognition 2, 1572–1574 (1998)Google Scholar
  5. 5.
    Bertsekas, D.P., Castanon, D.A.: A forward/reverse auction algorithm for asymmetric assignment problems. Computational Optimization and Applications 1, 277–297 (1992)MATHMathSciNetGoogle Scholar
  6. 6.
    MNI data set (August 2005),
  7. 7.
    Wang, Z.Y.: Multiscale Boundary Identification for Medical Images. M.Sc. Thesis, University of Alberta, Canada  (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • ZuYing Wang
    • 1
  • Mrinal Mandal
    • 1
  • Zoltan Koles
    • 1
  1. 1.Department of Electrical and Computer Engineering, University of Alberta, Edmonton, ABCanada

Personalised recommendations