2D/3D registration using a rotation-invariant cost function based on Zernike moments

摘要

We present a novel in-plane rotation invariant cost function for 2D/3D registration utilizing projection-invariant transformation properties and the decomposition of the X-ray and the DRR under comparison into orthogonal Zernike moments. As a result, only five dof have to be optimized, and the number of iterations necessary for registration can be significantly reduced. Results in a phantom study show that an accuracy of approximately 0.7° and 2 mm can be achieved using this method. We conclude that reduction of coupled dof and usage of linear independent coefficients for cost function evaluation provide interesting new perspectives for the field of 2D/3D registration.