An Automatic System For Segmenting Coronary Arteries from CTA

In this paper, we introduce a system for coronary arteries in CTA (computed tomography angiography) data sets which allows the coronary patholo-gies to be quickly and reliably detected with minimal user efforts as well as providing tools for corrections. Specifically, the system automatically isolates heart and coronary arteries from surrounding structures, detects ostia locations, extracts centerline and lumen representations of coronary arteries and visualizes each coronary artery for quick diagnosis. The main focus of this paper is the coronary modeling starting from automatically detected ostia locations. More specifically, centerlines and lumens of coronary arteries are extracted by an iterative breadth-first type minimal path detection and local vessel segmentation algorithm which starts from each ostia location and operates only inside the heart mask. This coupled centerline and lumen segmentation algorithm extends into vessel branches without excessive computations and constructs correct tree structure due to the breadth-first type of exploration. In addition, veins can be removed from the arterial tree with simple user interactions.

[1]  Gernot Brockmann,et al.  Automatic Aorta Segmentation and Valve Landmark Detection in C-Arm CT: Application to Aortic Valve Implantation , 2010, MICCAI.

[2]  Badrinath Roysam,et al.  Robust 3-D Modeling of Vasculature Imagery Using Superellipsoids , 2007, IEEE Transactions on Medical Imaging.

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

[4]  Dorin Comaniciu,et al.  Fast and Automatic Heart Isolation in 3D CT Volumes: Optimal Shape Initialization , 2010, MLMI.

[5]  T van Walsum,et al.  Coronary centerline extraction from CT coronary angiography images using a minimum cost path approach. , 2009, Medical physics.

[6]  Leo Grady,et al.  Isoperimetric graph partitioning for image segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[8]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[9]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

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

[13]  Dorin Comaniciu,et al.  Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features , 2008, IEEE Transactions on Medical Imaging.

[14]  Hüseyin Tek,et al.  Robust Vessel Tree Modeling , 2008, MICCAI.

[15]  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.

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

[17]  Albert C. S. Chung,et al.  Multi-resolution Vessel Segmentation Using Normalized Cuts in Retinal Images , 2006, MICCAI.

[18]  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.