Fast, Quality, Segmentation of Large Volumes – Isoperimetric Distance Trees

  • Leo Grady
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3953)


For many medical segmentation tasks, the contrast along most of the boundary of the target object is high, allowing simple thresholding or region growing approaches to provide nearly sufficient solutions for the task. However, the regions recovered by these techniques frequently leak through bottlenecks in which the contrast is low or non-existent. We propose a new approach based on a novel speed-up of the isoperimetric algorithm [1] that can solve the problem of leaks through a bottleneck. The speed enhancement converts the isoperimetric segmentation algorithm to a fast, linear-time computation by using a tree representation as the underlying graph instead of a standard lattice structure. In this paper, we show how to create an appropriate tree substrate for the segmentation problem and how to use this structure to perform a linear-time computation of the isoperimetric algorithm. This approach is shown to overcome common problems with watershed-based techniques and to provide fast, high-quality results on large datasets.


Gaussian Elimination Laplacian Matrix Graph Partitioning Cholesky Factor Distance Tree 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Grady, L., Schwartz, E.L.: The isoperimetric algorithm for graph partitioning. SIAM Journal on Scientific Computing (2006) (in press)Google Scholar
  2. 2.
    Brice, C.R., Fennema, C.L.: Scene analysis using regions. Artificial Intelligence 1(3), 205–226 (1970)CrossRefGoogle Scholar
  3. 3.
    Roerdink, J., Meijster, A.: The watershed transform: definitions, algorithms, and parallellization strategies. Fund. Informaticae 41, 187–228 (2000)MATHMathSciNetGoogle Scholar
  4. 4.
    Grady, L., Schwartz, E.L.: Isoperimetric graph partitioning for image segmentation. IEEE Trans. on Pat. Anal. and Mach. Int. 28(3), 469–475 (2006)CrossRefGoogle Scholar
  5. 5.
    Sethian, J.A.: Level Set Methods and Fast Marching Methods. Cambridge University Press, Cambridge (1999)MATHGoogle Scholar
  6. 6.
    Krissian, K., Westin, C.-F.: Fast sub-voxel re-initialization of the distance map for level set methods. Pattern Rec. Let. 26(10), 1532–1542 (2005)CrossRefGoogle Scholar
  7. 7.
    Zahn, C.: Graph theoretical methods for detecting and describing Gestalt clusters. IEEE Transactions on Computation 20, 68–86 (1971)MATHCrossRefGoogle Scholar
  8. 8.
    Urquhart, R.: Graph theoretical clustering based on limited neighborhood sets. Pattern Recognition 15(3), 173–187 (1982)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. of Computer Vision 59(2), 167–181 (2004)CrossRefGoogle Scholar
  10. 10.
    Wan, M., Liang, Z., Ke, Q., Hong, L., Bitter, I., Kaufman, A.: Automatic centerline extraction for virtual colonoscopy. IEEE Trans. on Medical Imaging 21(12), 1450–1460 (2002)CrossRefGoogle Scholar
  11. 11.
    Wu, C.-H., Doerschuk, P.C.: Tree approximations to Markov random fields. IEEE Trans. on Pat. Anal. and Mach. Int. 17(4), 391–402 (1995)CrossRefGoogle Scholar
  12. 12.
    Jain, A.: Fundamentals of Digital Image Processing. Prentice-Hall, Englewood Cliffs (1989)MATHGoogle Scholar
  13. 13.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. On Pat. Anal. and Mach. Int. 22(8), 888–905 (2000)CrossRefGoogle Scholar
  14. 14.
    Boykov, Y., Jolly, M.-P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proc. of ICCV 2001, pp. 105–112 (2001)Google Scholar
  15. 15.
    Grady, L., Funka-Lea, G.: Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials. In: Sonka, M., Kakadiaris, I.A., Kybic, J. (eds.) CVAMIA/MMBIA 2004. LNCS, vol. 3117, pp. 230–245. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  16. 16.
    John, P.E., Schild, G.: Calculating the characteristic polynomial and the eigenvectors of a tree. MATCH 34, 217–237 (1996)MATHMathSciNetGoogle Scholar
  17. 17.
    Cheeger, J.: A lower bound for the smallest eigenvalue of the Laplacian. In: Gunning, R. (ed.) Problems in Analysis, pp. 195–199. Princeton University Press, Princeton (1970)Google Scholar
  18. 18.
    Merris, R.: Laplacian matrices of graphs: A survey. Linear Algebra and its Applications 197, 198, 143–176 (1994)CrossRefMathSciNetGoogle Scholar
  19. 19.
    Gremban, K.: Combinatorial preconditioners for sparse, symmetric diagonally dominant linear systems. Ph.D. dissertation, Carnegie Mellon University, Pittsburgh, PA (October 1996)Google Scholar
  20. 20.
    Branin Jr., F.H.: The inverse of the incidence matrix of a tree and the formulation of the algebraic-first-order differential equations of an RLC network. IEEE Transactions on Circuit Theory 10(4), 543–544 (1963)Google Scholar
  21. 21.
    Gibbons, A.: Algorithmic Graph Theory. Cambridge University Press, Cambridge (1989)Google Scholar
  22. 22.
    Rosenfeld, A., Pfaltz, J.L.: Sequential operations in digital picture processing. J. of the Assoc. for Computing Machinery 13(4), 471–494 (1966)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Leo Grady
    • 1
  1. 1.Department of Imaging and VisualizationSiemens Corporate ResearchPrincetonUSA

Personalised recommendations