Topo-Geometric Filtration Scheme for Geometric Active Contours and Level Sets: Application to Cerebrovascular Segmentation

One of the main problems of the existing methods for the segmentation of cerebral vasculature is the appearance in the segmentation result of wrong topological artefacts such as the kissing vessels. In this paper, a new approach for the detection and correction of such errors is presented. The proposed technique combines robust topological information given by Persistent Homology with complementary geometrical information of the vascular tree. The method was evaluated on 20 images depicting cerebral arteries. Detection and correction success rates were 81.80% and 68.77%, respectively.

[1]  Afra Zomorodian,et al.  Computational topology , 2010 .

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

[3]  David R. Bull,et al.  Projective image restoration using sparsity regularization , 2013, 2013 IEEE International Conference on Image Processing.

[4]  Herbert Edelsbrunner,et al.  Computing Robustness and Persistence for Images , 2010, IEEE Transactions on Visualization and Computer Graphics.

[5]  Alexander Russell,et al.  Computational topology: ambient isotopic approximation of 2-manifolds , 2003, Theor. Comput. Sci..

[6]  Stephane Cotin,et al.  Robust RANSAC-based blood vessel segmentation , 2012, Medical Imaging.

[7]  L. Antiga.  Patient-specific modeling of ge-ometry and blood flow in large arteries , 2003 .

[8]  Richard L. Van Metter,et al.  Handbook of Medical Imaging , 2009 .

[9]  Georg Langs,et al.  Medical Computer Vision , 2011 .

[10]  Albert C. S. Chung,et al.  Probabilistic vessel axis tracing and its application to vessel segmentation with stream surfaces and minimum cost paths , 2007, Medical Image Anal..

[11]  Vicent Caselles,et al.  Geometric models for active contours , 1995, Proceedings., International Conference on Image Processing.

[12]  Chao Chen,et al.  Topology Noise Removal for Curve and Surface Evolution , 2010, MCV.

[13]  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.

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

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

[16]  Florent Ségonne,et al.  Active Contours Under Topology Control—Genus Preserving Level Sets , 2008, International Journal of Computer Vision.