Português Contacts Subscribe RSS

Document details

3D-2D image registration by nonlinear regression

Author(s): Gouveia, A. R. ; Metz, C. ; Freire, Luís ; Klein, S.

Date: 2012

Persistent ID: http://hdl.handle.net/10400.21/3029

Origin: Repositório Científico do Instituto Politécnico de Lisboa

Subject(s): 2D/3D Image registration; Image guided interventions; Regression; Feature extraction; Image registration; Neural networks; Optimization; Robustness; Training; X-ray imaging; 2D/3D Image registration; 2D/3D Image registration; Image guided interventions; Image guided interventions; Regression; Regression; Feature extraction; Feature extraction; Image registration; Image registration; Neural networks; Neural networks; Optimization; Optimization; Robustness; Robustness; Training; Training; X-ray imaging; X-ray imaging

Description

We propose a 3D-2D image registration method that relates image features of 2D projection images to the transformation parameters of the 3D image by nonlinear regression. The method is compared with a conventional registration method based on iterative optimization. For evaluation, simulated X-ray images (DRRs) were generated from coronary artery tree models derived from 3D CTA scans. Registration of nine vessel trees was performed, and the alignment quality was measured by the mean target registration error (mTRE). The regression approach was shown to be slightly less accurate, but much more robust than the method based on an iterative optimization approach.

Document Type Book part
Language English
Contributor(s) RCIPL

Document details

3D-2D image registration by nonlinear regression

Related documents