A Higher-Order Tensor Vessel Tractography for Segmentation of Vascular Structures

A new vascular structure segmentation method, which is based on a cylindrical flux-based higher order tensor (HOT), is presented. On a vessel structure, the HOT naturally models branching points, which create challenges for vessel segmentation algorithms. In a general linear HOT model embedded in 3D, one has to work with an even order tensor due to an enforced antipodal-symmetry on the unit sphere. However, in scenarios such as in a bifurcation, the antipodally-symmetric tensor embedded in 3D will not be useful. In order to overcome that limitation, we embed the tensor in 4D and obtain a structure that can model asymmetric junction scenarios. During construction of a higher order tensor (e.g. third or fourth order) in 4D, the orientation vectors lie on the unit 3-sphere, in contrast to the unit 2-sphere in 3D tensor modeling. This 4D tensor is exploited in a seed-based vessel segmentation algorithm, where the principal directions of the 4D HOT is obtained by decomposition, and used in a HOT tractography approach. We demonstrate quantitative validation of the proposed algorithm on both synthetic complex tubular structures as well as real cerebral vasculature in Magnetic Resonance Angiography (MRA) datasets and coronary arteries from Computed Tomography Angiography (CTA) volumes.

[1]  Rachid Deriche,et al.  Apparent diffusion profile estimation from high angular resolution diffusion images , 2006, SPIE Medical Imaging.

[2]  Clemens M. Hentschke,et al.  Automatic cerebral aneurysm detection in multimodal angiographic images , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[3]  Stephen T. C. Wong,et al.  VOLES: Vascularity-Oriented LEvel Set algorithm for pulmonary vessel segmentation in image guided intervention therapy , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[4]  Nicholas Ayache,et al.  Model-Based Detection of Tubular Structures in 3D Images , 2000, Comput. Vis. Image Underst..

[5]  T. Mareci,et al.  Generalized diffusion tensor imaging and analytical relationships between diffusion tensor imaging and high angular resolution diffusion imaging , 2003, Magnetic resonance in medicine.

[6]  Alejandro F. Frangi,et al.  Anatomical Labeling of the Circle of Willis Using Maximum A Posteriori Probability Estimation , 2013, IEEE Transactions on Medical Imaging.

[7]  Francis K. H. Quek,et al.  A review of vessel extraction techniques and algorithms , 2004, CSUR.

[8]  Ghassan Hamarneh,et al.  Vascular bifurcation detection in scale-space , 2012, 2012 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis.

[9]  Hans-Peter Seidel,et al.  A Higher-Order Structure Tensor , 2009 .

[10]  Kecheng Liu,et al.  A review on MR vascular image processing algorithms: acquisition and prefiltering: part I , 2002, IEEE Transactions on Information Technology in Biomedicine.

[11]  Guido Gerig,et al.  Multiscale detection of curvilinear structures in 2-D and 3-D image data , 1995, Proceedings of IEEE International Conference on Computer Vision.

[12]  Laurent D. Cohen,et al.  Global Minimum for Active Contour Models: A Minimal Path Approach , 1997, International Journal of Computer Vision.

[13]  Laurent Risser,et al.  Gap Filling of 3-D Microvascular Networks by Tensor Voting , 2008, IEEE Transactions on Medical Imaging.

[14]  D. Tuch.  High Angular Resolution Diffusion Imaging of the Human Brain , 1999 .

[15]  Baba C. Vemuri,et al.  Approximating Symmetric Positive Semidefinite Tensors of Even Order , 2012, SIAM J. Imaging Sci..

[16]  Ghassan Hamarneh,et al.  VascuSynth: Simulating vascular trees for generating volumetric image data with ground-truth segmentation and tree analysis , 2010, Comput. Medical Imaging Graph..

[17]  Armin Kanitsar,et al.  Vessel tracking in peripheral CTA datasets-an overview , 2001, Proceedings Spring Conference on Computer Graphics.

[18]  Anthony J. Yezzi,et al.  Vessel Tractography Using an Intensity Based Tensor Model With Branch Detection , 2013, IEEE Transactions on Medical Imaging.

[19]  Joos Vandewalle,et al.  On the Best Rank-1 and Rank-(R1 , R2, ... , RN) Approximation of Higher-Order Tensors , 2000, SIAM J. Matrix Anal. Appl..

[20]  Liqun Qi,et al.  Eigenvalues of a real supersymmetric tensor , 2005, J. Symb. Comput..

[21]  Baba C. Vemuri,et al.  Extracting Tractosemas from a Displacement Probability Field for Tractography in DW-MRI , 2008, MICCAI.

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

[23]  D. Pace,et al.  TubeTK : an open-source toolkit of algorithms operating on images of tubes , 2012 .

[24]  Max A. Viergever,et al.  Vessel Axis Tracking Using Topology Constrained Surface Evolution , 2007, IEEE Transactions on Medical Imaging.

[25]  Laurent D. Cohen,et al.  Tubular anisotropy for 2D vessel segmentation , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  David A. Steinman,et al.  Robust and objective decomposition and mapping of bifurcating vessels , 2004, IEEE Transactions on Medical Imaging.

[27]  Kecheng Liu,et al.  A review on MR vascular image processing: skeleton versus nonskeleton approaches: part II , 2002, IEEE Transactions on Information Technology in Biomedicine.

[28]  Feiniu Yuan,et al.  Modeling n-Furcated Liver vessels From a 3-D Segmented Volume Using Hole-Making and Subdivision Methods , 2012, IEEE Transactions on Biomedical Engineering.

[29]  Maciej Orkisz,et al.  Efficient computation of Hessian-based enhancement filters for tubular structures in 3D images , 2009 .

[30]  D. Tuch.  Q‐ball imaging , 2004, Magnetic resonance in medicine.

[31]  Alejandro F. Frangi,et al.  Automated segmentation of cerebral vasculature with aneurysms in 3DRA and TOF-MRA using geodesic active regions: an evaluation study. , 2010, Medical physics.

[32]  Hans-Peter Seidel,et al.  Estimating Crossing Fibers: A Tensor Decomposition Approach , 2008, IEEE Transactions on Visualization and Computer Graphics.

[33]  Thomas Schultz,et al.  Towards Resolving Fiber Crossings with Higher Order Tensor Inpainting , 2012 .

[34]  Baba C. Vemuri,et al.  Symmetric Positive 4th Order Tensors & Their Estimation from Diffusion Weighted MRI , 2007, IPMI.

[35]  Heinz-Otto Peitgen,et al.  Multiple hypothesis template tracking of small 3D vessel structures , 2010, Medical Image Anal..

[36]  Olivier D. Faugeras,et al.  CURVES: Curve evolution for vessel segmentation , 2001, Medical Image Anal..

[37]  Katja Bühler,et al.  Geometric Methods for Vessel Visualization and Quantification — A Survey , 2004 .

[38]  Carl-Fredrik Westin,et al.  Estimation of fiber Orientation Probability Density Functions in High Angular Resolution Diffusion Imaging , 2009, NeuroImage.

[39]  Stephen R. Aylward,et al.  Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction , 2002, IEEE Transactions on Medical Imaging.

[40]  Guido Gerig,et al.  3D Multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1997, CVRMed.

[41]  Jürgen Weese,et al.  Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images , 1997, CVRMed.

[42]  Max A. Viergever,et al.  Vessel enhancing diffusion: A scale space representation of vessel structures , 2006, Medical Image Anal..

[43]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[44]  T van Walsum,et al.  Evaluation of a multi-atlas based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study. , 2010, Medical physics.

[45]  Isabelle Bloch,et al.  Bayesian Maximal Paths for Coronary Artery Segmentation from 3D CT Angiograms , 2009, MICCAI.

[46]  Anthony J. Yezzi,et al.  Vessels as 4-D Curves: Global Minimal 4-D Paths to Extract 3-D Tubular Surfaces and Centerlines , 2007, IEEE Transactions on Medical Imaging.

[47]  Laurent D. Cohen,et al.  Fast extraction of minimal paths in 3D images and applications to virtual endoscopy , 2001, Medical Image Anal..

[48]  Duan Xu,et al.  Q‐ball reconstruction of multimodal fiber orientations using the spherical harmonic basis , 2006, Magnetic resonance in medicine.

[49]  Martin Styner,et al.  Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms , 2009, Medical Image Anal..

[50]  Tong Fang,et al.  Automated Structured All-Quadrilateral and Hexahedral Meshing of Tubular Surfaces , 2012, IMR.

[51]  Alejandro F. Frangi,et al.  Muliscale Vessel Enhancement Filtering , 1998, MICCAI.

[52]  Isabelle Bloch,et al.  A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes , 2009, Medical Image Anal..

[53]  Rachid Deriche,et al.  Riemannian Framework for Estimating Symmetric Positive Definite 4th Order Diffusion Tensors , 2008, MICCAI.

[54]  K. Castleman,et al.  Flux-based anisotropic diffusion applied to enhancement of 3-D angiogram , 2002 .

[55]  Yefeng Zheng,et al.  Robust and Accurate Coronary Artery Centerline Extraction in CTA by Combining Model-Driven and Data-Driven Approaches , 2013, MICCAI.

[56]  Karl Rohr,et al.  Segmentation and Quantification of Human Vessels Using a 3-D Cylindrical Intensity Model , 2007, IEEE Transactions on Image Processing.

[57]  Max W. K. Law,et al.  Three Dimensional Curvilinear Structure Detection Using Optimally Oriented Flux , 2008, ECCV.

[58]  Rachid Deriche,et al.  Deterministic and Probabilistic Tractography Based on Complex Fibre Orientation Distributions , 2009, IEEE Transactions on Medical Imaging.

[59]  J. K. Smith,et al.  Vessel tortuosity and brain tumor malignancy: a blinded study. , 2005, Academic radiology.

[60]  David A. Steinman,et al.  A Framework for Geometric Analysis of Vascular Structures: Application to Cerebral Aneurysms , 2009, IEEE Transactions on Medical Imaging.