Multi-scale Regularization Approaches of Non-parametric Deformable Registrations
- 83 Downloads
Most deformation algorithms use a single-value smoother during optimization. We investigate multi-scale regularizations (smoothers) during the multi-resolution iteration of two non-parametric deformable registrations (demons and diffeomorphic algorithms) and compare them to a conventional single-value smoother. Our results show that as smoothers increase, their convergence rate decreases; however, smaller smoothers also have a large negative value of the Jacobian determinant suggesting that the one-to-one mapping has been lost; i.e., image morphology is not preserved. A better one-to-one mapping of the multi-scale scheme has also been established by the residual vector field measures. In the demons method, the multi-scale smoother calculates faster than the large single-value smoother (Gaussian kernel width larger than 0.5) and is equivalent to the smallest single-value smoother (Gaussian kernel width equals to 0.5 in this study). For the diffeomorphic algorithm, since our multi-scale smoothers were implemented at the deformation field and the update field, calculation times are longer. For the deformed images in this study, the similarity measured by mean square error, normal correlation, and visual comparisons show that the multi-scale implementation has better results than large single-value smoothers, and better or equivalent for smallest single-value smoother. Between the two deformable registrations, diffeormophic method constructs better coherence space of the deformation field while the deformation is large between images.
Key wordsDeformation registration multi-scale regularization diffeomorphic algorithm demon algorithm
This study was based on the frame work of The Insight Segmentation and Registration Toolkit (ITK).
- 2.Bro-Nielsen M, Florack L, Deriche R: Regularization and Scale Space, INRIA Tech. Rep. RR-2352, 1–40, September 1994Google Scholar
- 3.Florack L, Duits R, Bierkens J: Tikhonov regularization versus scale space: a new result [image processing applications]: Image Processing, ICIP International Conference on 2004 V1:271–274, 2004Google Scholar
- 4.Bro-Nielsen M, Gramkow C: Fast fluid registration of medical images VBC ’96: Proc. Visualization in Biomedical Computing. Hamburg, Germany, September. Springer Lect Notes Comput Sci 1131:267–276, 1996Google Scholar
- 6.Thirion TJ: Non-rigid matching using demons, Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR'96), 245–251, 1996Google Scholar
- 7.Vercauteren T, Pennec X, Perchant A, Ayache N: Non-parametric diffeomorphic image registration with the demons algorithm. In: Proc. MICCAI, 319–326, 2007Google Scholar
- 11.Kuo HS, Mah D, Wu A, Chuang KS, Hong L, Yaparpalvi R, Sperier M, Kalniki S: A method incorporating 4D data for evaluating the dosimetric effects of respiratory motion in single arc IMAT. Phys Med Biol 55:3479–3497, 2010Google Scholar
- 12.Kuo HS, Liu WS, Wu A, Mah D, Chuang KS, Hong L, Yaparpalvi R, Guha C, Kalniki S: Biological impact of geometric uncertainties: what margin is needed for intra-hepatic tumors? Radiation Oncology. June, 2010.Google Scholar