Share Email Print

Proceedings Paper

2D/3D registration using a rotation-invariant cost function based on Zernike moments
Author(s): Wolfgang Birkfellner; Xinhui Yang; Wolfgang Burgstaller; Bernard Baumann; Augustinus Ludwig Jacob; Peter F. Niederer; Pietro Regazzoni; Peter Messmer
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

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 nad the DRR under comparision into orhogonal Zernike moments. As a result, only five dof have to be optimized, and the number of iteration 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 intersting new perspectives for the field of 2D/3D registration.

Paper Details

Date Published: 12 May 2004
PDF: 7 pages
Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); doi: 10.1117/12.531976
Show Author Affiliations
Wolfgang Birkfellner, Univ. Hospital Basel (Switzerland)
Vienna General Hospital (Austria)
Xinhui Yang, Univ. Hospital Basel (Switzerland)
ETH Zürich (Switzerland)
Wolfgang Burgstaller, Univ. Hospital Basel (Switzerland)
Bernard Baumann, Univ. Hospital Basel (Switzerland)
Augustinus Ludwig Jacob, Univ. Hospital Basel (Switzerland)
Peter F. Niederer, ETH Zurich (Switzerland)
Pietro Regazzoni, Univ. Hospital Basel (Switzerland)
Peter Messmer, Univ. Hospital Basel (Switzerland)
Univ. Hospital Zurich (Switzerland)

Published in SPIE Proceedings Vol. 5370:
Medical Imaging 2004: Image Processing
J. Michael Fitzpatrick; Milan Sonka, Editor(s)

© SPIE. Terms of Use
Back to Top