Free-form nonrigid image registration using generalized elastic nets

Andriy Myronenko, Xubo Song, Miguel Á Carreira-Perpiñán

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We introduce a novel probabilistic approach for non-parametric nonrigid image registration using generalized elastic nets, a model previously used for topographic maps. The idea of the algorithm is to adapt an elastic net (a constrained Gaussian mixture) in the spatial-intensity space of one image to fit the second image. The resulting net directly represents the correspondence between image pixels in a probabilistic way and recovers the underlying image deformation. We regularize the net with a differential prior and develop an efficient optimization algorithm using linear conjugate gradients. The nonparametric formulation allows for complex transformations having local deformation. The method is generally applicable to registering point sets of arbitrary features. The accuracy and effectiveness of the method are demonstrated on different medical image and point set registration examples with locally nonlinear underlying deformations.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - 2007
Event2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07 - Minneapolis, MN, United States
Duration: Jun 17 2007Jun 22 2007

Other

Other2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
CountryUnited States
CityMinneapolis, MN
Period6/17/076/22/07

Fingerprint

Image registration
Pixels

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Software
  • Control and Systems Engineering

Cite this

Myronenko, A., Song, X., & Carreira-Perpiñán, M. Á. (2007). Free-form nonrigid image registration using generalized elastic nets. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition [4270013] https://doi.org/10.1109/CVPR.2007.382988

Free-form nonrigid image registration using generalized elastic nets. / Myronenko, Andriy; Song, Xubo; Carreira-Perpiñán, Miguel Á.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007. 4270013.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Myronenko, A, Song, X & Carreira-Perpiñán, MÁ 2007, Free-form nonrigid image registration using generalized elastic nets. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 4270013, 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07, Minneapolis, MN, United States, 6/17/07. https://doi.org/10.1109/CVPR.2007.382988
Myronenko A, Song X, Carreira-Perpiñán MÁ. Free-form nonrigid image registration using generalized elastic nets. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007. 4270013 https://doi.org/10.1109/CVPR.2007.382988
Myronenko, Andriy ; Song, Xubo ; Carreira-Perpiñán, Miguel Á. / Free-form nonrigid image registration using generalized elastic nets. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2007.
@inproceedings{0cf3e32c6c2947a8a63827e8f4bb58fc,
title = "Free-form nonrigid image registration using generalized elastic nets",
abstract = "We introduce a novel probabilistic approach for non-parametric nonrigid image registration using generalized elastic nets, a model previously used for topographic maps. The idea of the algorithm is to adapt an elastic net (a constrained Gaussian mixture) in the spatial-intensity space of one image to fit the second image. The resulting net directly represents the correspondence between image pixels in a probabilistic way and recovers the underlying image deformation. We regularize the net with a differential prior and develop an efficient optimization algorithm using linear conjugate gradients. The nonparametric formulation allows for complex transformations having local deformation. The method is generally applicable to registering point sets of arbitrary features. The accuracy and effectiveness of the method are demonstrated on different medical image and point set registration examples with locally nonlinear underlying deformations.",
author = "Andriy Myronenko and Xubo Song and Carreira-Perpi{\~n}{\'a}n, {Miguel {\'A}}",
year = "2007",
doi = "10.1109/CVPR.2007.382988",
language = "English (US)",
isbn = "1424411807",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Free-form nonrigid image registration using generalized elastic nets

AU - Myronenko, Andriy

AU - Song, Xubo

AU - Carreira-Perpiñán, Miguel Á

PY - 2007

Y1 - 2007

N2 - We introduce a novel probabilistic approach for non-parametric nonrigid image registration using generalized elastic nets, a model previously used for topographic maps. The idea of the algorithm is to adapt an elastic net (a constrained Gaussian mixture) in the spatial-intensity space of one image to fit the second image. The resulting net directly represents the correspondence between image pixels in a probabilistic way and recovers the underlying image deformation. We regularize the net with a differential prior and develop an efficient optimization algorithm using linear conjugate gradients. The nonparametric formulation allows for complex transformations having local deformation. The method is generally applicable to registering point sets of arbitrary features. The accuracy and effectiveness of the method are demonstrated on different medical image and point set registration examples with locally nonlinear underlying deformations.

AB - We introduce a novel probabilistic approach for non-parametric nonrigid image registration using generalized elastic nets, a model previously used for topographic maps. The idea of the algorithm is to adapt an elastic net (a constrained Gaussian mixture) in the spatial-intensity space of one image to fit the second image. The resulting net directly represents the correspondence between image pixels in a probabilistic way and recovers the underlying image deformation. We regularize the net with a differential prior and develop an efficient optimization algorithm using linear conjugate gradients. The nonparametric formulation allows for complex transformations having local deformation. The method is generally applicable to registering point sets of arbitrary features. The accuracy and effectiveness of the method are demonstrated on different medical image and point set registration examples with locally nonlinear underlying deformations.

UR - http://www.scopus.com/inward/record.url?scp=34948830696&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34948830696&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2007.382988

DO - 10.1109/CVPR.2007.382988

M3 - Conference contribution

SN - 1424411807

SN - 9781424411801

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -