Learning-based deformation estimation for fast non-rigid registration

Min Jeong Kim, Myoung Hee Kim, Dinggang Shen

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

13 Citations (Scopus)

Abstract

This paper presents a learning-based deformation estimation method for fast non-rigid registration. First, a PCA-based statistical deformation model is constructed using the deformation fields obtained by conventional registration algorithms between a template image and training subject images. Then, the constructed statistical model is used to generate a large number of sample deformation fields by resampling in the PCA space. In the meanwhile, by warping the template using these sample deformation fields, the respective sample images in the PCA space can be also generated. Finally, after learning the correlation between the features of the sample images and their deformation coefficients, given a new test image, we can immediately estimate its relative deformations to the template based on its image information. Using this estimated deformation, we can warp the template to generate an intermediate template close to the test image. Since the intermediate template is more similar to the test image compared to the original template, the registration via the intermediate template becomes much easier and faster. Experimental results show that the proposed learning-based registration method can fast register MR brain image with robust performance.

Original languageEnglish
Title of host publication2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
DOIs
Publication statusPublished - 2008 Sep 22
Externally publishedYes
Event2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops - Anchorage, AK, United States
Duration: 2008 Jun 232008 Jun 28

Other

Other2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops
CountryUnited States
CityAnchorage, AK
Period08/6/2308/6/28

Fingerprint

Brain
Statistical Models

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Kim, M. J., Kim, M. H., & Shen, D. (2008). Learning-based deformation estimation for fast non-rigid registration. In 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops [4563006] https://doi.org/10.1109/CVPRW.2008.4563006

Learning-based deformation estimation for fast non-rigid registration. / Kim, Min Jeong; Kim, Myoung Hee; Shen, Dinggang.

2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008. 4563006.

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

Kim, MJ, Kim, MH & Shen, D 2008, Learning-based deformation estimation for fast non-rigid registration. in 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops., 4563006, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops, Anchorage, AK, United States, 08/6/23. https://doi.org/10.1109/CVPRW.2008.4563006
Kim MJ, Kim MH, Shen D. Learning-based deformation estimation for fast non-rigid registration. In 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008. 4563006 https://doi.org/10.1109/CVPRW.2008.4563006
Kim, Min Jeong ; Kim, Myoung Hee ; Shen, Dinggang. / Learning-based deformation estimation for fast non-rigid registration. 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops. 2008.
@inproceedings{1095f2e711e941bcabbbb4597e7a1840,
title = "Learning-based deformation estimation for fast non-rigid registration",
abstract = "This paper presents a learning-based deformation estimation method for fast non-rigid registration. First, a PCA-based statistical deformation model is constructed using the deformation fields obtained by conventional registration algorithms between a template image and training subject images. Then, the constructed statistical model is used to generate a large number of sample deformation fields by resampling in the PCA space. In the meanwhile, by warping the template using these sample deformation fields, the respective sample images in the PCA space can be also generated. Finally, after learning the correlation between the features of the sample images and their deformation coefficients, given a new test image, we can immediately estimate its relative deformations to the template based on its image information. Using this estimated deformation, we can warp the template to generate an intermediate template close to the test image. Since the intermediate template is more similar to the test image compared to the original template, the registration via the intermediate template becomes much easier and faster. Experimental results show that the proposed learning-based registration method can fast register MR brain image with robust performance.",
author = "Kim, {Min Jeong} and Kim, {Myoung Hee} and Dinggang Shen",
year = "2008",
month = "9",
day = "22",
doi = "10.1109/CVPRW.2008.4563006",
language = "English",
isbn = "9781424423408",
booktitle = "2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops",

}

TY - GEN

T1 - Learning-based deformation estimation for fast non-rigid registration

AU - Kim, Min Jeong

AU - Kim, Myoung Hee

AU - Shen, Dinggang

PY - 2008/9/22

Y1 - 2008/9/22

N2 - This paper presents a learning-based deformation estimation method for fast non-rigid registration. First, a PCA-based statistical deformation model is constructed using the deformation fields obtained by conventional registration algorithms between a template image and training subject images. Then, the constructed statistical model is used to generate a large number of sample deformation fields by resampling in the PCA space. In the meanwhile, by warping the template using these sample deformation fields, the respective sample images in the PCA space can be also generated. Finally, after learning the correlation between the features of the sample images and their deformation coefficients, given a new test image, we can immediately estimate its relative deformations to the template based on its image information. Using this estimated deformation, we can warp the template to generate an intermediate template close to the test image. Since the intermediate template is more similar to the test image compared to the original template, the registration via the intermediate template becomes much easier and faster. Experimental results show that the proposed learning-based registration method can fast register MR brain image with robust performance.

AB - This paper presents a learning-based deformation estimation method for fast non-rigid registration. First, a PCA-based statistical deformation model is constructed using the deformation fields obtained by conventional registration algorithms between a template image and training subject images. Then, the constructed statistical model is used to generate a large number of sample deformation fields by resampling in the PCA space. In the meanwhile, by warping the template using these sample deformation fields, the respective sample images in the PCA space can be also generated. Finally, after learning the correlation between the features of the sample images and their deformation coefficients, given a new test image, we can immediately estimate its relative deformations to the template based on its image information. Using this estimated deformation, we can warp the template to generate an intermediate template close to the test image. Since the intermediate template is more similar to the test image compared to the original template, the registration via the intermediate template becomes much easier and faster. Experimental results show that the proposed learning-based registration method can fast register MR brain image with robust performance.

UR - http://www.scopus.com/inward/record.url?scp=51849089599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51849089599&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2008.4563006

DO - 10.1109/CVPRW.2008.4563006

M3 - Conference contribution

AN - SCOPUS:51849089599

SN - 9781424423408

BT - 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops

ER -