Comparison and application of selected statistical shape models in medical imaging

  • Anke Neumann
  • Cristian Lorenz
Session 11: Biomedical Applications
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)


This paper reviews several kinds of 2D shape representations by a set of parameters based on labeled points, Fourier descriptors and wavelet descriptors, resp.. Shape models are derived by statistical analysis of parameters corresponding to a set of example shapes. Each model consists of a parameter vector describing mean shape and a set of modes of variation for parameters characterizing shape variability. Seven shape models, some of them differing in parameter normalization, for axial slices of spinal vertebra are compared with respect both to their compactness in parameter space and to their scope in corresponding space of shapes. A model based method for segmenting 2D gray level images is developed by formulating boundary finding as an optimization problem with respect to parameters varying according to the modes of variation. Our method includes an easy and fast interactive improvement of segmentation outcome.


Shape Model Shape Sample Segmentation Procedure Fourier Descriptor Statistical Shape Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    P.J. Besl. Geometric Modeling and Computer Vision Proc.IEEE 76(8), Aug. 1988, pp. 936–958CrossRefGoogle Scholar
  2. 2.
    C.K. Chui. An Introduction to Wavelets. Academic Press, San Diego, 1992Google Scholar
  3. 3.
    I.L. Dryden, K.V. Mardia. Multivariate Shape Analysis. Sankhyā, vol. 55, series A, pt. 3, 1993, pp. 460–480Google Scholar
  4. 4.
    R.O. Duda, P.E. Hart. Pattern Classification and Scene Analysis. John Wiley & Sons, New York, 1973Google Scholar
  5. 5.
    T. Pavlidis. Structural Pattern Recognition. Springer-Verlag, 1977Google Scholar
  6. 6.
    W.H. Press, S.A. Teukolsky, W.T. Vetterling, B.P. Flannery. Numerical Recipes in C: The Art of Scientific Programming. Cambridge University Press, 1992Google Scholar
  7. 7.
    L.H. Staib, J.S. Duncan. Boundary Finding with Parametrically Deformable Models. IEEE PAMI 14(11), 1992, pp. 1061–1075Google Scholar
  8. 8.
    G. Székely, A. Kelemen, Ch. Brechbühler, G. Gerig. Segmentation of 3D Objects from MRI Volume Data Using Constrained Elastic Deformations of Flexible Fourier Surface Models. Proc. Computer Vision, Virtual Reality and Robotics in Medicine, Nice, April 1995, pp. 495–505Google Scholar
  9. 9.
    C.J. Taylor, T.F. Cootes, A. Hill, J. Haslam. Medical Image Segmentation Using Active Shape Models. in Medical Imaging, L. Beolchi, M.H. Kuhn (eds.), IOS Press, Amsterdam, 1994, pp. 121–144Google Scholar
  10. 10.
    B.C. Vemuri, A. Radisavljevic. Multiresolution Stochastic Hybrid Shape Models with Fractal Priors. ACM Trans. Graphics, 13(2), April 1994, pp. 177–207CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Anke Neumann
    • 1
  • Cristian Lorenz
    • 2
  1. 1.University of the Federal Armed Forces HamburgHamburgGermany
  2. 2.Philips Research Laboratories HamburgHamburgGermany

Personalised recommendations