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

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.

[1]  Hans-Peter Seidel,et al.  Topological Visualization of Brain Diffusion MRI Data , 2007, IEEE Transactions on Visualization and Computer Graphics.

[2]  David H. Laidlaw,et al.  Exploring 3D DTI Fiber Tracts with Linked 2D Representations , 2009, IEEE Transactions on Visualization and Computer Graphics.

[3]  Santosh S. Vempala,et al.  The Random Projection Method , 2005, DIMACS Series in Discrete Mathematics and Theoretical Computer Science.

[4]  Carl-Fredrik Westin,et al.  Fast Manifold Learning Based on Riemannian Normal Coordinates , 2005, SCIA.

[5]  Patrick J. F. Groenen,et al.  Modern Multidimensional Scaling: Theory and Applications , 2003 .

[6]  P. Basser,et al.  In vivo fiber tractography using DT‐MRI data , 2000, Magnetic resonance in medicine.

[7]  Brian A. Wandell,et al.  Exploring connectivity of the brain's white matter with dynamic queries , 2005, IEEE Transactions on Visualization and Computer Graphics.

[8]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[9]  Carl-Fredrik Westin,et al.  Clustering Fiber Traces Using Normalized Cuts , 2004, MICCAI.

[10]  Matthew Chalmers,et al.  A linear iteration time layout algorithm for visualising high-dimensional data , 1996, Proceedings of Seventh Annual IEEE Visualization '96.

[11]  Jon Atli Benediktsson,et al.  Advanced processing of hyperspectral images , 2006, 2006 IEEE International Symposium on Geoscience and Remote Sensing.

[12]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[13]  Carl-Fredrik Westin,et al.  Uncertainty in White Matter Fiber Tractography , 2005, MICCAI.

[14]  David Akers,et al.  CINCH: a cooperatively designed marking interface for 3D pathway selection , 2006, UIST.

[15]  Alon Zakai,et al.  Manifold Learning: The Price of Normalization , 2008, J. Mach. Learn. Res..

[16]  David H. Laidlaw,et al.  Visualizing Diffusion Tensor MR Images Using Streamtubes and Streamsurfaces , 2003, IEEE Trans. Vis. Comput. Graph..

[17]  Gordon Kindlmann,et al.  Visualization and Analysis of Diffusion Tensor Fields , 2004 .

[18]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[19]  Anna Vilanova,et al.  Evaluation of fiber clustering methods for diffusion tensor imaging , 2005, VIS 05. IEEE Visualization, 2005..

[20]  Charl P. Botha,et al.  Fast and reproducible fiber bundle selection in DTI visualization , 2005 .

[21]  Joshua B. Tenenbaum,et al.  Mapping a Manifold of Perceptual Observations , 1997, NIPS.

[22]  J. Kruskal.  Nonmetric multidimensional scaling: A numerical method , 1964 .

[23]  David S. Ebert,et al.  Abstractive Representation and Exploration of Hierarchically Clustered Diffusion Tensor Fiber Tracts , 2008, Comput. Graph. Forum.

[24]  David H. Laidlaw,et al.  Connectivity-Aware Sectional Visualization of 3D DTI Volumes using Perceptual Flat-Torus Coloring and Edge Rendering , 2006, Eurographics.

[25]  Xie Jian-jun.  Multi-pose ear recognition based on locally linear embedding , 2008 .

[26]  Christopher Nimsky,et al.  Visualization of white matter tracts with wrapped streamlines , 2005, VIS 05. IEEE Visualization, 2005..