Vascular Segmentation Using Level Set Method

In this paper, we propose a two-stage level set segmentation framework to extract vascular tree from magnetic resonance angiography(MRA). First, we smooth the isosurface of MRA by anisotropic diffusion filter. Then this smoothed surface is treated as the initial localization of the desired contour, and used in the following geodesic active contours method, which provides accurate vascular structure. Results on cases demonstrate the effectiveness and accuracy of the approach.

[1]  Jerry L Prince,et al.  Image Segmentation Using Deformable Models , 2000 .

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

[3]  David E. Breen,et al.  A Framework for Level Set Segmentation of Volume Datasets , 2001 .

[4]  Jerry L. Prince,et al.  Medical image seg-mentation using deformable models , 2000 .

[5]  David E. Breen,et al.  A framework for Level Set segmentation of volumetric datasets , 2001 .

[6]  Xiao Han,et al.  A topology preserving deformable model using level sets , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

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

[8]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[9]  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.

[10]  Francis K. H. Quek,et al.  Vessel extraction techniques and algorithms: a survey , 2003, Third IEEE Symposium on Bioinformatics and Bioengineering, 2003. Proceedings..

[11]  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.

[12]  Aly A. Farag,et al.  Cerebrovascular segmentation for MRA data using level sets , 2003, CARS.