Accurate inverse consistent non-rigid image registration and its application on automatic re-contouring

Authors:
Qingguo Zeng;Yunmei Chen
Affiliations:
Department of Mathematics, University of Florida, Gainesville, FL;Department of Mathematics, University of Florida, Gainesville, FL
Venue:
ISBRA'08 Proceedings of the 4th international conference on Bioinformatics research and applications
Year:
2008

Citing 7
Cited 2

Multiresolution elastic matching

Computer Vision, Graphics, and Image Processing
Variational Methods for Multimodal Image Matching

International Journal of Computer Vision
Alignment by maximization of mutual information

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multi-Modality Image Registration Maximization of Mutual Information

MMBIA '96 Proceedings of the 1996 Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA '96)
Inverse consistent mapping in 3d deformable image registration: its construction and statistical properties

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Robust nonrigid multimodal image registration using local frequency maps

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Efficient and reliable schemes for nonlinear diffusion filtering

IEEE Transactions on Image Processing

A New Algorithm for Inverse Consistent Image Registration

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Local joint entropy based non-rigid multimodality image registration

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper provides a novel algorithm for invertible nonrigidimage registration. The proposed model minimizes two energy functionalscoupled by a natural inverse consistent constraint. Both of theenergy functionals for forward and backward deformation fields consista smoothness measure of the deformation field, and a similarity measurebetween the deformed image and the one to be matched. In this proposedmodel the similarity measure is based on maximum likelihood estimationof the residue image. To enhance algorithm efficiency, the Additive OperatorSplitting (AOS) scheme is used in solving the minimization problem.The inverse consistent deformation field can be applied to automatic recontouringto get an accurate delineation of Regions Of Interest(ROIs).The experimental results on synthetic images and 3D prostate data indicatethe effectiveness of the proposed method in inverse consistency andautomatic re-contouring.