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.
KeywordsVessel segmentation Minimal path method Fast marching algorithm Anisotropy Enhancement Multi-scale
Unable to display preview. Download preview PDF.
- Benmansour, F. (2009). Minimal path method applied to medical imaging: tubular structure and surface segmentation using multi-scaled anisotropy and recursive keypoints detection. Ph.D. Thesis, Université Paris Dauphine. Google Scholar
- Benmansour, F., & Cohen, L.D. (2009). Tubular anisotropy segmentation. In SSVM (pp. 14–25). Google Scholar
- Bornemann, F., & Rasch, C. (2006). Finite-element discretization of static Hamilton-Jacobi equations based on a local variational principle. Computing and Visualization in Science, 9(2). Google Scholar
- Caselles, V., Kimmel, R., & Sapiro, G. (1995). Geodesic active contours. In IEEE international conference in computer vision (ICCV’95) (pp. 694–699). Google Scholar
- Deschamps, T., & Cohen, L. D. (2002). Fast extraction of tubular and tree 3D surfaces with front propagation methods. In IEEE international conference on pattern recognition (ICPR’02) (pp. 731–734). Google Scholar
- Frangi, A. F., Niessen, W. J., Vincken, K. L., & Viergever, M. A. (1998). Multiscale vessel enhancement filtering. In Lecture notes in computer science (Vol. 1496, pp. 130–137). Berlin: Springer. Google Scholar
- Gooya, A., Dohi, T., Sakuma, I., & Liao, H. (2008c). R-PLUS: a Riemannian anisotropic edge detection scheme for vascular segmentation. In MICCAI’08: Proceedings of the 11th international conference on medical image computing and computer-assisted intervention—Part I (pp. 262–269). Berlin: Springer. Google Scholar
- Hameeteman, R., Freiman, M., Zuluaga, M. A., Joskowicz, L., Rozie, S., van Gils, M. J., van den Borne, L., Sosna, J., Berman, P., Cohen, N., Douek, P., Sánchez, I., Aissat, M., van der Lugt, A., Krestin, G. P., Niessen, W. J., & van Walsum, T. (2009). Carotid lumen segmentation and stenosis grading challenge. In Workshop in international conference on medical image computing and computer assisted intervention, September 2009. Google Scholar
- Konukoglu, E., Sermesant, M., Clatz, O., Peyrat, J.-M., Delingette, H., & Ayache, N. (2007). A recursive anisotropic fast marching approach to reaction diffusion equation: application to tumor growth modeling. In Lecture notes in computer science : Vol. 4584. Proceedings of the 20th international conference on information processing in medical imaging (IPMI’07) (pp. 686–699). Berlin: Springer. Google Scholar
- Krissian, K., Malandain, G., & Ayache, N. (1997). Directional anisotropic diffusion applied to segmentation of vessels in 3D images. In SCALE-SPACE’97: Proceedings of the first international conference on scale-space theory in computer vision, London, UK (pp. 345–348). Berlin: Springer. Google Scholar
- Law, W. K., & Chung, A. C. S. (2006). Segmentation of vessels using weighted local variances and an active contour model. In CVPRW ’06: Proceedings of the 2006 conference on computer vision and pattern recognition workshop, Washington, DC, USA (p. 83). Los Alamitos: IEEE Computer Society. CrossRefGoogle Scholar
- Law, M. W., & Chung, A. C. (2008). Three dimensional curvilinear structure detection using optimally oriented flux. In ECCV’08: Proceedings of the 10th European con computer vision, Berlin, Heidelberg (pp. 368–382). Berlin: Springer. Google Scholar
- Lesage, D., Angelini, E. D., Bloch, I., & Funka-Lea, G. (2009a). Bayesian maximal paths for coronary artery segmentation from 3d ct angiograms. In Yang, G.-Z., Hawkes, D. J., Rueckert, D., Noble, J. A., & Taylor, C. J. (Eds.), Lecture notes in computer science : Vol. 5761. International conference on medical image computing and computer assisted intervention (1) (pp. 222–229). Berlin: Springer. Google Scholar
- Li, H., & Yezzi, A. (2006). Vessels as 4D curves: global minimal 4D paths to extract 3D tubular surfaces. In IEEE conference on computer vision and pattern recognition (CVPR’06), Workshop MMBIA06 (p. 82). Google Scholar
- Lin, Q. (2003). Enhancement, extraction, and visualization of 3D volume data. Ph.D. Thesis, Linkopings Universitet. Google Scholar
- Lindeberg, T. (1998). Edge detection and ridge detection with automatic scale selection. International Journal of Computer Vision, 30, 465–470. Google Scholar
- Lorenz, C., Carlsen, I.-C., Buzug, T. M., Fassnacht, C., & Weese, J. (1997). Multi-scale line segmentation with automatic estimation of width, contrast and tangential direction in 2D and 3D medical images. In CVRMed-MRCAS’97: Proceedings of the first joint conference on computer vision, virtual reality and robotics in medicine and medial robotics and computer-assisted surgery, London, UK (pp. 233–242). Berlin: Springer. Google Scholar
- Mille, J., Benmansour, F., & Cohen, L. D. (2009). Carotid lumen segmentation based on tubular anisotropy and contours without edges. Insight Journal. http://www.insight-journal.org/browse/publication/670.
- Mohan, V., Sundaramoorthi, G., Melonakos, J., Niethammer, M., Kubicki, M., & Tannenbaum, A. (2008). Tubular surface evolution for segmentation of the cingulum bundle from DW-MRI. In Mathematical methods in computational anatomy. Google Scholar
- Nain, D., Yezzi, A., & Turk, G. (2004). Vessel segmentation using a shape driven flow. In Medical imaging computing and computer-assisted intervention (MICCAI’04) (pp. 51–59). Google Scholar
- Orkisz, M., Flórez Valencia, L., & Hernández Hoyos, M. (2008). Models, algorithms and applications in vascular image segmentation. Machine Graphics and Vision, 17(1), 5–33. Google Scholar
- Weber, O., Devir, Y. S., Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2008). Parallel algorithms for approximation of distance maps on parametric surfaces. ACM Transactions on Graphics, 27(4). http://portal.acm.org/citation.cfm?id=1409625.1409626.