Integrated skeleton and boundary shape representation for medical image interpretation

  • Glynn P. Robinson
  • Alan C. F. Colchester
  • Lewis D. Griffin
  • David J. Hawkes
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


We propose a method of extracting and describing the shape of features from medical images which provides both a skeleton and boundary representation. This method does not require complete closed boundaries nor regularly sampled edge points. Lines between edge points are connected into boundary sections using a measure of proximity. Alternatively, or in addition, known connectivity between points (such as that available from traditional edge detectors) can be incorporated if known. The resultant descriptions are objectcentred and hierarchical in nature with an unambiguous mapping between skeleton and boundary sections.


Voronoi Diagram Delaunay Triangulation Object Boundary Boundary Representation Edge Point 
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. [RC1]
    Robinson, G.P., Colchester, A.C.F., Griffin,L.D.: A hierarchical shape representation for use in anatomical object recognition. Proc. SPIE Biomedical Image Processing & 3D microscopy (1992)Google Scholar
  2. [Ma1]
    Marshall, S.: Review of Shape Coding Techniques. Image and Vision Computing. 7 (1989) 281–294Google Scholar
  3. [Fr1]
    Freeman, H.: On the encoding of arbitrary geometric configurations. IRE Trans. Electronic Computers. June (1961) 260–268Google Scholar
  4. [Ay1]
    Ayache, N. J.: A model-based vision system to identify and locate partially visible industrial parts. Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE, New York: (1983) 492–494Google Scholar
  5. [AB1]
    Asada, H., Brady, M.: The Curvature Primal Sketch. IEEE Trans. Pat. Anal. Machine Intel. PAMI-8 NO. 1 (1986) 2–14Google Scholar
  6. [Bl1]
    Blum, H.: Biological Shape and Visual Science. Int. Jour. Theory Biol. (1973) 205–287Google Scholar
  7. [NP1]
    Nackman, L. R., Pizer, S. M.: Three dimensional shape description using the symmetric axis transform. IEEE Trans. Pat. Anal. Machine Intel. PAMI-9 (1985) 505–511Google Scholar
  8. [Ar1]
    Arcelli, C.: Pattern thinning by contour tracing. Comp. Vis. Image Proces. 17 (1981) 130–144Google Scholar
  9. [Ah1]
    Ahuja, N.: Dot Pattern Processing Using Voronoi Neighbourhoods. IEEE Trans. Pat. Anal. Machine Intel. PAMI-4 (1982) 336–343Google Scholar
  10. [AT1]
    Ahuja, N., Tuceryan, M.: Extraction of Early Perceptual Structure in Dot Patterns: Integrating region, boundary & component Gestalt. Comp. Graph. Vis. Image Proc. 48 (1989) 304–346Google Scholar
  11. [Fa1]
    Fairfield, J. R. C.: Segmenting dot patterns by Voronoi diagram concavity. IEEE Trans. Pat. Anal. Machine Intel. PAMI-5 (1983) 104–110Google Scholar
  12. [OI1]
    Ogniewicz, R., Ilg, M.: Skeletons with Euclidean metric and correct topology and their application in object recognition and document analysis. Proceedings 4th International Symposium on Spatial Data Handling. Zurich, Switzerland: (1990) 15–24Google Scholar
  13. [Bol]
    Boissonnat, J. D.: Shape Reconstruction from planar cross section. Comp. Graph. Vis. Image Proc. 44 (1988) 1–29Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Glynn P. Robinson
    • 1
  • Alan C. F. Colchester
    • 1
  • Lewis D. Griffin
    • 1
  • David J. Hawkes
    • 2
  1. 1.Department of NeurologyGuy's HospitalLondonEngland
  2. 2.Department of Radiological SciencesGuy's HospitalLondonEngland

Personalised recommendations