Coronary Artery MultiScale Enhancement Methods: A Comparative Study

Cardiovascular diseases are the first cause of deaths all over the world and therefore, researches in modern medical image processing aim at developing reliable and robust medical tools to assist clinicians in vessel extraction, motion detection and 3D reconstruction. Vessel extraction is an important non trivial step which depends extremely in the used enhancement method. Multiscale-based vessel enhancement methods are very famous. These methods are based on the analysis of the Hessian matrix at multiple scales in a linear normalized scale space to define a filter using a vesselness measure which is the likelihood of a point belonging to a vessel. The purpose of the present paper is to conduct a comparative study between four well-cited filters using different approaches. Hence, we propose methods for evaluating those filters performance in terms of noise sensitivity and the behavior of each filter at junctions, for nearby vessels and thin vessels.

[1]  Tae-Seong Kim,et al.  Vessel enhancement filter using directional filter bank , 2009, Comput. Vis. Image Underst..

[2]  Nicholas Ayache,et al.  Preprocessing : data selection , pseudo ECG III . 3 − D centerlines reconstruction , 2011 .

[3]  Tony Lindeberg,et al.  Principles for Automatic Scale Selection , 1999 .

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

[5]  Hongen Liao,et al.  Medical Imaging and Augmented Reality , 2004 .

[6]  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.

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

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

[9]  Marcel Breeuwer,et al.  Evaluation of Hessian-based filters to enhance the axis of coronary arteries in CT images , 2003, CARS.

[10]  Jocelyne Troccaz,et al.  CVRMed-MRCAS'97 , 1997, Lecture Notes in Computer Science.

[11]  Marius Erdt,et al.  Automatic Hepatic Vessel Segmentation Using Graphics Hardware , 2008, MIAR.

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

[13]  Nicholas Ayache,et al.  The Correlation Ratio as a New Similarity Measure for Multimodal Image Registration , 1998, MICCAI.

[14]  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.

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

[16]  Klaus Drechsler,et al.  Comparison of vesselness functions for multiscale analysis of the liver vasculature , 2010, Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine.

[17]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .