Surface Reconstruction of Bone from X-ray Images and Point Distribution Model Incorporating a Novel Method for 2D-3D Correspondence

Authors:
Guoyan Zheng;Lutz-Peter Nolte
Affiliations:
University of Bern, CH-3014, Bern, Switzerland;University of Bern, CH-3014, Bern, Switzerland
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Year:
2006

Citing 0
Cited 5

Automatic Extraction of Proximal Femur Contours from Calibrated X-Ray Images Using 3D Statistical Models

MIAR '08 Proceedings of the 4th international workshop on Medical Imaging and Augmented Reality
Particle filter based automatic reconstruction of a patient-specific surface model of a proximal femur from calibrated X-ray images for surgical navigation

ACIVS'07 Proceedings of the 9th international conference on Advanced concepts for intelligent vision systems
Automatic reconstruction of a patient-specific surface model of a proximal femur from calibrated x-ray images via Bayesian filters

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
An integrated approach for reconstructing surface models of the proximal femur from sparse input data for surgical navigation

ICDHM'07 Proceedings of the 1st international conference on Digital human modeling
Diagnostic radiograph based 3D bone reconstruction framework: application to osteotomy surgical planning

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

Surface reconstruction of bone from a few X-ray images and point distribution model (PDM) is discussed. We present a robust approach combining regularized morphing and shape deformation, and show its application to surface reconstruction of proximal femur. The robustness of the presented approach relies on the development of a novel method to establish correspondence between the X-ray images and the model estimated from the PDM. The correspondence is based on an iterative non-rigid twodimensional (2D) point matching process, which iteratively uses a symmetric injective nearest-neighbor mapping operator (SIN-MO) and 2D thin-plate splines (2D-TPS) based deformation to find a fraction of best matched 2D point pairs between edge points detected from the X-ray images and projections of the points on the apparent contours extracted from the estimated model. The advantages of this novel method include robustness with respect to outliers, and automatic exclusion of cross matching, which is an important property for preservation of topology. Initial quantitative and qualitative evaluation results are given which indicate the validity of our approach.