A New Class of Distance Measures for Registration of Tubular Models to Image Data
In some registration applications additional user knowledge is available, which can improve and accelerate the registration process, especially for non-rigid registration. This is particularly important in the transfer of pre-operative plans to the operating room, e.g. for navigation. In case of tubular structures, such as vessels, a geometric representation can be extracted via segmentation and skeletonization. We present a new class of distance measures based on global filter kernels to compare such models efficiently with image data. The approach is validated in a non-rigid registration application with Powerdoppler ultrasound data.
Unable to display preview. Download preview PDF.
- 2.Beller S, Hünerbein M, Lange T, Eulenstein S, Gebauer B, Schlag PM. Image-guided surgery of liver metastases by 3D ultrasound-based optoelectronic navigation. Brit J Surg accepted.Google Scholar
- 4.Modersitzki J. Numerical Methods for Image Registration. Oxford University Press; 2004.Google Scholar
- 6.Viola PA, III WMWells. Alignment by maximization of mutual information. Procs ICCV 1995; 16–23.Google Scholar
- 7.Weese J, Rösch P, Netsch T, Blaffert T, Quist M. Gray-value based registration of CT and MR images by maximization of local correlation. In: MICCAI; 1999. 656–663.Google Scholar
- 8.Haber E, Modersitzki J. Intensity gradient-based registration and fusion of multimodal images. Procs MICCAI 2006; 726–733.Google Scholar
- 10.Henn S, Hömke L, Witsch K. Lesion preserving image registration with applications to human brains. In: Procs DAGM; 2004. 143–154.Google Scholar
- 11.Schumacher H, Franz A, Fischer B. Weighted medical image registration with automatic mask generation. Procs SPIE 2006; in print.Google Scholar
- 13.Frangi AF, Niessen WJ, Vincken KL, Viergever MA. Multiscale vessel enhancement filtering. Procs MICCAI 1998; 130–137.Google Scholar