Tubular Structure Segmentation Based on Minimal Path Method and Anisotropic Enhancement

We present a new interactive method for tubular structure extraction. The main application and motivation for this work is vessel tracking in 2D and 3D images. The basic tools are minimal paths solved using the fast marching algorithm. This allows interactive tools for the physician by clicking on a small number of points in order to obtain a minimal path between two points or a set of paths in the case of a tree structure. Our method is based on a variant of the minimal path method that models the vessel as a centerline and surface. This is done by adding one dimension for the local radius around the centerline. The crucial step of our method is the definition of the local metrics to minimize. We have chosen to exploit the tubular structure of the vessels one wants to extract to built an anisotropic metric. The designed metric is well oriented along the direction of the vessel, admits higher velocity on the centerline, and provides a good estimate of the vessel radius. Based on the optimally oriented flux this measure is required to be robust against the disturbance introduced by noise or adjacent structures with intensity similar to the target vessel. We obtain promising results on noisy synthetic and real 2D and 3D images and we present a clinical validation.

[1]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

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

[3]  J. Sethian,et al.  Fast methods for the Eikonal and related Hamilton- Jacobi equations on unstructured meshes. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Joachim Weickert,et al.  Coherence-Enhancing Diffusion Filtering , 1999, International Journal of Computer Vision.

[5]  J A Sethian,et al.  A fast marching level set method for monotonically advancing fronts. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

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

[7]  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.

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

[9]  P. Lions.  Generalized Solutions of Hamilton-Jacobi Equations , 1982 .

[10]  E. Rouy,et al.  A viscosity solutions approach to shape-from-shading , 1992 .

[11]  Ken Masamune,et al.  A Variational Method for Geometric Regularization of Vascular Segmentation in Medical Images , 2008, IEEE Transactions on Image Processing.

[12]  L. Cohen,et al.  Geodesic Methods for Shape and Surface Processing , 2009 .

[13]  Max W. K. Law,et al.  Segmentation of Vessels Using Weighted Local Variances and an Active contour Model , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[14]  Nicholas Ayache,et al.  Directional Anisotropic Diffusion Applied to Segmentation of Vessels in 3D Images , 1997, Scale-Space.

[15]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[17]  Jean Daunizeau,et al.  Accurate Anisotropic Fast Marching for Diffusion-Based Geodesic Tractography , 2007, Int. J. Biomed. Imaging.

[18]  Guido Gerig,et al.  Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images , 1998, Medical Image Anal..

[19]  Alfred M. Bruckstein,et al.  Regularized Laplacian Zero Crossings as Optimal Edge Integrators , 2003, International Journal of Computer Vision.

[20]  Anthony J. Yezzi,et al.  Vessels as 4D Curves: Global Minimal 4D Paths to Extract 3D Tubular Surfaces , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[21]  W. D. Evans,et al.  PARTIAL DIFFERENTIAL EQUATIONS , 1941 .

[22]  R. M. Natal Jorge,et al.  Advances in Computational Vision and Medical Image Processing , 2009 .

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

[24]  Maxime Descoteaux,et al.  A geometric flow for segmenting vasculature in proton-density weighted MRI , 2008, Medical Image Anal..

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

[26]  Isabelle E. Magnin,et al.  Evaluation of semi-automatic arterial stenosis quantification , 2006, International Journal of Computer Assisted Radiology and Surgery.

[27]  Hongen Liao,et al.  Anisotropic Haralick Edge Detection Scheme with Application to Vessel Segmentation , 2008, MIAR.

[28]  Pierrick Coupé,et al.  3D Wavelet Subbands Mixing for Image Denoising , 2008, Int. J. Biomed. Imaging.

[29]  Mathews Jacob,et al.  Design of steerable filters for feature detection using canny-like criteria , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Shiing-Shen Chern,et al.  Finsler Geometry Is Just Riemannian Geometry without the Quadratic Restriction , 1997 .

[31]  F. Bornemann,et al.  Finite-element Discretization of Static Hamilton-Jacobi Equations based on a Local Variational Principle , 2004, math/0403517.

[32]  Hongen Liao,et al.  R-PLUS: A Riemannian Anisotropic Edge Detection Scheme for Vascular Segmentation , 2008, MICCAI.

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

[34]  Max W. K. Law,et al.  Weighted Local Variance-Based Edge Detection and Its Application to Vascular Segmentation in Magnetic Resonance Angiography , 2007, IEEE Transactions on Medical Imaging.

[35]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[36]  D L Chopp.  Replacing iterative algorithms with single-pass algorithms , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[37]  Anthony J. Yezzi,et al.  Vessel Segmentation Using a Shape Driven Flow , 2004, MICCAI.

[38]  Leo Joskowicz,et al.  Carotid Lumen Segmentation and Stenosis Grading Challenge , 2010, The MIDAS Journal.

[39]  Qingfen Lin,et al.  Enhancement, Extraction, and Visualization of 3D Volume Data , 2001 .

[40]  Guillermo Sapiro,et al.  New Possibilities with Sobolev Active Contours , 2007, SSVM.

[41]  Kaleem Siddiqi,et al.  3D Flux Maximizing Flows , 2001, EMMCVPR.

[42]  Marc Niethammer,et al.  Tubular Surface Evolution for Segmentation of the Cingulum Bundle From DW-MRI , 2008 .

[43]  J. Tsitsiklis,et al.  Efficient algorithms for globally optimal trajectories , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[44]  Ron Kimmel,et al.  Segmentation of thin structures in volumetric medical images , 2006, IEEE Transactions on Image Processing.

[45]  OrkiszMaciej,et al.  Models, algorithms and applications in vascular image segmentation , 2008 .

[46]  L. Evans,et al.  Partial Differential Equations , 1941 .

[47]  L. Cohen,et al.  Segmentation of 3D tubular objects with adaptive front propagation and minimal tree extraction for 3D medical imaging , 2007, Computer methods in biomechanics and biomedical engineering.

[48]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

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

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

[51]  Laurent D. Cohen,et al.  Tubular Anisotropy Segmentation , 2009, SSVM.

[52]  Marcela Hernández Hoyos,et al.  Models, algorithms and applications in vascular image segmentation , 2008 .

[53]  Alexander M. Bronstein,et al.  Parallel algorithms for approximation of distance maps on parametric surfaces , 2008, TOGS.

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

[55]  Hervé Delingette,et al.  A Recursive Anisotropic Fast Marching Approach to Reaction Diffusion Equation: Application to Tumor Growth Modeling , 2007, IPMI.

[56]  Laurent D. Cohen,et al.  Carotid Lumen Segmentation Based on Tubular Anisotropy and Contours Without Edges , 2009, The MIDAS Journal.

[57]  Rachid Deriche,et al.  Brain Connectivity Mapping Using Riemannian Geometry, Control Theory, and PDEs , 2009, SIAM J. Imaging Sci..

[58]  Ross T. Whitaker,et al.  Anisotropic Curvature Motion for Structure Enhancing Smoothing of 3D MR Angiography Data , 2007, Journal of Mathematical Imaging and Vision.

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

[60]  Sigurd B. Angenent,et al.  Finsler Active Contours , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[61]  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.

[62]  Laurent D. Cohen,et al.  Fast extraction of tubular and tree 3D surfaces with front propagation methods , 2002, Object recognition supported by user interaction for service robots.

[63]  Guillermo Sapiro,et al.  New Possibilities with Sobolev Active Contours , 2007, International Journal of Computer Vision.

[64]  Jerry L. Prince,et al.  An active contour model for mapping the cortex , 1995, IEEE Trans. Medical Imaging.