A Comparative Analysis of Dimension Reduction Techniques for Representing DTI Fibers as 2D/3D Points

  • Xiaoyong Yang
  • Ruiyi Wu
  • Ziáng Ding
  • Wei Chen
  • Song Zhang
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)

Abstract

Dimension Reduction is the process of transfering high-dimensional data into lower dimensions while maintaining the original intrinsic structures. This technique of finding low-dimensional embedding from high-dimensional data is important for visualizing dense 3D DTI fibers because it is hard to visualize and analyze the fiber tracts with high geometric, spatial, and anatomical complexity. Color-mapping, selection, and abstraction are widely used in DTI fiber visualization to depict the properties of fiber models. Nonetheless, visual clutters and occlusion in 3D space make it hard to grasp even a few thousand fibers. In addition, real time interaction (exploring and navigating) on such complex 3D models consumes large amount of CPU/GPU power. Converting DTI fiber to 2D or 3D points with dimension reduction techniques provides a complimentary visualization for these fibers. This chapter analyzes and compares dimension reduction methods for DTI fiber models. An interaction interface augments the 3D visualization with a 2D representation that contains a low-dimensional embedding of the DTI fibers. To achieve real-time interaction, the framework is implemented with GPU programming.

References

  1. 1.
    Akers, D.: A cooperatively designed marking interface for 3D pathway selection. In: Proceedings of ACM UIST, Montreux (2006)Google Scholar
  2. 2.
    Anupam, S., Gupta, A.: An elementary proof of the johnson-lindenstrauss lemma. Technical report 99-006, University of California, Berkeley (1999)Google Scholar
  3. 3.
    Basser, P.J., Pajevic, S., Pierpaoli, C., Duda, J., Aldroubi, A.: In vivo fiber tractography using dt-mri data. Magn. Reson. Med. 44, 625–632 (2000)Google Scholar
  4. 4.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Diettrich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems 14. MIT Press, Cambridge (2002)Google Scholar
  5. 5.
    Borg, I., Groenen, P.J.F.: Modern Multidimensional Scaling: Theory and Applications. Springer, New York (2005)Google Scholar
  6. 6.
    Blaas, J., Botha, C., Peters, B., Vos, F., Post, F.: Fast and reproducible fiber bundle selection in dti visualization. In: Proceedings of IEEE Visualization, Minneapolis, pp. 59–64 (2005)Google Scholar
  7. 7.
    Brun, A., Knutsson, H., Park, H.J., Shenton, M.E., Westin, C.-F.: Clustering fiber tracts using normalized cuts. In: Seventh International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI’04), pp. 368–375, Rennes – Saint Malo. Springer, Berlin/Heidelberg (2004)Google Scholar
  8. 8.
    Brun, A., Westin, C.-F., Herberthson, M., Knutsson, H.: Fast manifold learning based on riemannian normal coordinates. In: Proceedings of the 14th Scandinavian Conference on Image Analysis (SCIA’05), Joensuu (2005)Google Scholar
  9. 9.
    Chalmers, M.: A linear iteration time layout algorithm for visualising high-dimensional data. In: IEEE Symposium on Information Visualization, San Francisco, pp. 127–132 (1996)Google Scholar
  10. 10.
    Chen, W., Zhang, S., Correia, S., Ebert, D.S.: Abstractive representation and exploration of hierarchically clustered diffusion tensor fiber tracts. Comput. Graph. Forum 27(3), 1071–1078 (2008)Google Scholar
  11. 11.
    Chen, W., Ding, Z., Zhang, S., Brandt, A.M., Stephen Correia, S., Qu, H., Crow, J.A., Tate, D.F., Yan, Z., Peng, Q.: Exploring 3D DTI fiber-tracts with linked 2D representations. IEEE Trans. Vis. Comput. Graph. (Proc. Visualization ’09) 15(6), 1433–1440 (2009)Google Scholar
  12. 12.
    Demiralp, C., Laidlaw, D.H.: Similarity coloring of dti fiber tracts. In: Proceedings of DMFC Workshop at MICCAI, London (2009)Google Scholar
  13. 13.
    Demiralp, C., Zhang, S., Tate, D., Correia, S., Laidlaw, D.H.: Connectivity-aware sectional visualization of 3D dti volumes using perceptual flat-torus coloring and edge rendering. In: Proceedings of Eurographics, Vienna (2006)Google Scholar
  14. 14.
    Enders, F., Sauber, N., Merhof, D., Hastreiter, P., Nimsky, C., Stamminger, M.: Visualization of white matter tracts with wrapped streamlines. In: Proceedings of IEEE Visualization, Minneapolis, pp. 51–58 (2005)Google Scholar
  15. 15.
    Friman, O., Westin, C.-F.: Uncertainty in white matter fiber tractography. In: Proceedings of MICCAI, Palm Springs, pp. 107–114 (2005)Google Scholar
  16. 16.
    Goldberg, Y., Zakai, A., Kushnir, D., Ritov, Y.: Manifold learning: the price of normalization. Mach. Learn. Res. 9, 1909–1939 (2008)Google Scholar
  17. 17.
    Jianu, D., Zhou, W., Demiralp, C., Laidlaw, D.H.: Visualizing spatial relations between 3D-dti integral curves using texture patterns. In: Proceedings of IEEE Visualization Poster Compendium, Sacramento (2007)Google Scholar
  18. 18.
    Jianu, R., Demiralp, C., Laidlaw, D.H.: Exploring 3D DTI fiber-tracts with linked 2D representations. IEEE Trans. Vis. Comput. Graph. (Proc. Visualization ’09) 15(6), 1449–1456 (2009). http://vis.cs.brown.edu/docs/pdf/g/Jianu-2009-E3D.pdf.html(pdf) http://vis.cs.brown.edu/results/bibtex/Jianu-2009-E3D.bib(bibtex: Jianu-2009-E3D)
  19. 19.
    Kindlmann, G.: Visualization and analysis of diffusion tensor fields. Ph.D. Thesis, University of Utah (2004)Google Scholar
  20. 20.
    Kruskal, J.B.: Nonmetric multidimensional scaling: a numerical method. Psychometrika 29, 115–129 (1964)Google Scholar
  21. 21.
    Mardia, K.V., Kent, J.T., Bibby, J.M.: Multivariate Analysis. Probability and Mathematical Statistics. Academic, London (1995)Google Scholar
  22. 22.
    Moberts, B., Vilanova, A., vanWijk, J.J.: Evaluation of fiber clustering methods for diffusion tensor imaging. In: Proceedings of IEEE Visualization, Minneapolis (2005)Google Scholar
  23. 23.
    Vempala, S.: The Random Projection Method, volume 65 of DIMACS Series in Discrete Mathematics and Theoretical Computer Science. American Mathematical Society, Providence (2004)Google Scholar
  24. 24.
    Robila, S.: Distributed Processing of Hyperspectral Images, Proceedings ASPRS Annual Conference, Denver, CO (2004)Google Scholar
  25. 25.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)Google Scholar
  26. 26.
    Pearson, K.: On Lines and Planes of Closest Fit to Systems of Points in Space. Philosophical Magazine 2(6), 559–572 (1901)Google Scholar
  27. 27.
    Schultz, T., Theisel, H., Seidel, H.-P.: Topological visualization of brain diffusion mri data. IEEE Trans. Vis. Comput. Graph. 13(6), 1496–1503 (2007)Google Scholar
  28. 28.
    Sherbondy, A., Akers, D., Mackenzie, R., Dougherty, R., Wandell, B.: Exploring connectivity of the brainś white matter with dynamic queries. IEEE Trans. Vis. Comput. Graph. 11(4), 419–430 (2005)Google Scholar
  29. 29.
    Tenenbaum, J.B.: Mapping a Manifold of Perceptual Observations. MIT Press, Cambridge (1998)Google Scholar
  30. 30.
    Xie, Z.X., Mu, Z.C., Xie, J.J.: Multi-pose ear recognition based on locally linear embedding. CAAI Trans. Intell. Syst. 3(4), 454–462 (2008)Google Scholar
  31. 31.
    Zhang, S., Demiralp, C., Laidlaw, D.H.: Visualizing diffusion tensor mr images using streamtubes and streamsurfaces. IEEE Trans. Vis. Comput. Graph. 9(4), 454–462 (2003)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2012

Authors and Affiliations

  • Xiaoyong Yang
    • 1
  • Ruiyi Wu
    • 1
  • Ziáng Ding
    • 2
  • Wei Chen
    • 2
  • Song Zhang
    • 1
  1. 1.Department of Computer Science and EngineeringMississippi State UniversityStarkvilleUSA
  2. 2.State Key Laboratory of CAD & CGZhejiang UniversityHangzhouChina

Personalised recommendations