A Scale-Space Approach for Image Registration of Vessel Structures
We present a multi-scale approach for non-rigid image registration of tubular tree-like structures such as vessels. Therefore, we consider a Gaussian and a combined morphological and Gaussian scale-space. Similar to a multi-level framework, we solve a sequence of registration problems on several scale-space levels using a standard variational approach for non-liner volumetric image registration. The overall idea is to avoid locally ambiguous mappings between parts of the images by removing morphological details but also finding a global optimal solution by spreading remaining local information using Gaussian scaling. We successfully tested our method on registration of 3D CT and ultrasound images of hepatic vessels.
Unable to display preview. Download preview PDF.
- 1.Charnoz A, Agnus V, Malandain G, et al. Design of robust vascular tree matching: Validation on liver. LNCS. 2005;3566:443–455.Google Scholar
- 4.Bühler K, Felkel P, La Cruz A. Geometric methods for vessel visualization and quantification: A survey. In: Brünett G, Hamman B, Müller H, editors. Geometric Modelling for Scientific Visualization. Springer; 2003.Google Scholar
- 6.Modersitzki J. Numerical Methods for Image Registration. Numerical Mathematics and Scientific Computation. Oxford University Press; 2003.Google Scholar
- 7.Weickert J. Anisotropic Diffusion in Image Processing. Teubner; 1998.Google Scholar