Point-Based Geometric Deformable Models for Medical Image Segmentation

  • Hon Pong Ho
  • Yunmei Chen
  • Huafeng Liu
  • Pengcheng Shi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3749)


Conventional level set based image segmentations are performed upon certain underlying grid/mesh structures for explicit spatial discretization of the problem and evolution domains. Such computational grids, however, lead to typically expensive and difficult grid refinement/remeshing problems whenever tradeoffs between time and precision are deemed necessary. In this paper, we present the idea of performing level set evolution in a point-based environment where the sampling location and density of the domains are adaptively determined by level set geometry and image information, thus rid of the needs for computational grids and the associated refinements. We have implemented the general geometric deformable models using this representation and computational strategy, including the incorporation of region-based prior information in both domain sampling and curve evolution processes, and have evaluated the performance of the method on synthetic data with ground truth and performed surface segmentation of brain structures from three-dimensional magnetic resonance images.


Point Cloud Move Less Square Medical Image Segmentation Marching Cube Algorithm Geometric Active Contour 
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.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. IJCV 22, 61–79 (1997)zbMATHCrossRefGoogle Scholar
  2. 2.
    Chen, Y., Tagare, H., et al.: Using prior shapes in geometric active contours in a variational framework. International Journal of Computer Vision 50, 315–328 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Droske, M., Meyer, B., Rumpf, M., Schaller, C.: An adaptive level set method for medical image segmentation. In: Information Processing in Medical Imaging, pp. 416–422 (2001)Google Scholar
  4. 4.
    Han, X., Xu, C., Prince, J.L.: A 2d moving grid geometric deformable model. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 153–160 (2003)Google Scholar
  5. 5.
    Ho, H.P., Chen, Y., Liu, H., Shi, P.: Level set active contours on unstructured point cloud. In: IEEE Conference on Computer Vision and Pattern Recognition (2005)Google Scholar
  6. 6.
    Liu, H., Shi, P.: Meshfree particle method. In: ICCV, pp. 289–296 (October 2003)Google Scholar
  7. 7.
    Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape modeling with front porpagation: a level set approach. IEEE Trans. on Pattern Analysis and Machine Intelligence 17, 158–175 (1995)CrossRefGoogle Scholar
  8. 8.
    Osher, S., Fedkiw, R.: Level set methods and dynamic implicit surfaces. Springer, New York Inc. (2002)Google Scholar
  9. 9.
    Paragios, N., Mellina-Gottardo, O., Ramesh, V.: Gradient vector flow fast geometric active contours. IEEE Trans. on Pattern Analysis and Machine Intelligence 26(3) (March 2004)Google Scholar
  10. 10.
    Pauly, M., Keiser, R., Kobbelt, L.P., Gross, M.: Shape modeling with point-sampled geometry. ACM SIGGRAPH (Trans. Graphics) 22(3), 641–650 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Hon Pong Ho
    • 1
  • Yunmei Chen
    • 2
  • Huafeng Liu
    • 1
    • 3
  • Pengcheng Shi
    • 1
  1. 1.Dept. of EEEHong Kong University of Science & TechnologyHong Kong
  2. 2.Dept. of MathematicsUniversity of FloridaGainesvilleUSA
  3. 3.State Key Lab of Modern Optical InstrumentationZhejiang UniversityHangzhouChina

Personalised recommendations