Single versus Multi-step Non-Rigid Medical Image Registration of 3D Medical Images
Single versus Multi-step Non-Rigid Medical Image Registration of 3D Medical Images
Keywords:
Medical image registration, deformations, radial basis functions, computer assisted surgery, radiotherapyAbstract
Multi-model medical image registration is very important in medical image analysis and computer assisted surgery. Accuracy and speed are the two crucial factor of any registration algorithm. A Fast Radial Basis Function algorithm for non-rigid medical image registration with improved accuracy is presented in this article. The accuracy of the technique is improved by converting the one-step registration algorithm to multi-step i.e. three-step registration algorithm. The global transformation accuracy of this technique has been evaluated by using two different anatomical landmarks sets. The former is to calculate the model parameters, and the later is used to assess registration accuracy. Finally, we demonstrate that the multi-step technique yields better accuracy (using NMI) as compared to the one-step approach and target registration errors of about 2.91mm on the registration of CT with its synthetically deformed version obtained from the Vanderbilt database. Our study shows that the multi-step fast RBF based registration is more effective in recovering larger deformation and do kept transformation smoothness than the one-step fast RBF based registration.
References
Rohr, K. Landmark-based Image Analysis Using Geometric and Intensity Models. Kluwer Academic Publishers (2001).
Rueckert, D., L.I. Sonoda, C. Hayes, D.L.G. Hill, M.O. Leach, & D.J. Hawkes. Nonrigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging 18(8): 712- 721(1999).
Shah, S.K., & R.J. Lapeer. Fast non-rigid registration of medical image data for image guided surgery. In: Proceedings of AMI-ARCS Workshop in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI,09) 21: 12-24 (2009).
Lapeer, R.J., & S.K. Shah. Rowland, R.S. An optimised radial basis function algorithm for fast non-rigid registration of medical images. Computers in Biology and Medicine 40(1): 1-7 (2009).
Buhmann, M.D. Radial Basis Functions: Theory and Implementations. Cambridge University Press, UK (2004)
Rowland, R., Lapeer, R. Fast non-rigid registration of medical images: comparing the thin-plate and biharmonic splines. In: Medical Image Understanding and Analysis, MIUA 2008, Dundee, p. 246-250 (2008).
Livne, O.E., & G.B. Wright. Fast multilevel evaluation of smooth radial basis function expansions. Electronic Transactions on Numerical Analysis 23: 263-287 (2006).
Levin, D., D. Dey, & P. Slomka. Efcient 3D nonlinear warping of computed tomography: two high-performance implementations using OpenGL. In: Medical Imaging 2005: Visualization, Image-Guided Procedures, and Display. Galloway, Jr., R., Cleary, K. (Ed.), Proceedings of the SPIE. Volume 5744. p. 34-42 (2005).
Rowland, R. Fast Registration of Medical Imaging Data using Optimised Radial Basis Functions. PhD thesis, University of East Anglia, Norwich, Norfolk , UK (2007)
Studholme, C., D.L.G. Hill, & D.J. Hawkes. An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognition 32: 71-86 (1999).
Wells III, W.M., P. Viola, H. Atsumi, S. Nakajima, & R., Kikinis. Multi-modal volume registration by maximization of mutual information. Medical Image Analysis 1(1): 35-51 (1996).
Fitzpatrick, J.: Retrospective image registration and evaluation project (RIRE). http://www.inisght-journal.org/rireindex.php (1997).
