A new statistically-constrained deformable registration framework for MR brain images

Zhong Xue, Dinggang Shen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Statistical models of deformations (SMD) capture the variability of deformations from the template image onto a group of sample images and can be used to constrain the traditional deformable registration algorithms to improve their robustness and accuracy. This paper employs a wavelet-PCA-based SMD to constrain the traditional deformable registration based on the Bayesian framework. The template image is adaptively warped by an intermediate deformation field generated based on the SMD during the registration procedure, and the traditional deformable registration is performed to register the intermediate template image with the input subject image. Since the intermediate template image is much more similar to the subject image, and the deformation is relatively small and local, it is less likely to be stuck into undesired local minimum using the same deformable registration in this framework. Experiments show that the proposed statistically-constrained deformable registration framework is more robust and accurate than the conventional registration.

Original languageEnglish
Pages (from-to)357-367
Number of pages11
JournalInternational Journal of Medical Engineering and Informatics
Volume1
Issue number3
DOIs
Publication statusPublished - 2009 Jan 1
Externally publishedYes

Fingerprint

Statistical Models
Brain
Passive Cutaneous Anaphylaxis
Experiments

Keywords

  • Biomedical image processing
  • Image registration
  • Magnetic resonance imaging
  • Statistical model

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Medicine (miscellaneous)
  • Biomaterials

Cite this

A new statistically-constrained deformable registration framework for MR brain images. / Xue, Zhong; Shen, Dinggang.

In: International Journal of Medical Engineering and Informatics, Vol. 1, No. 3, 01.01.2009, p. 357-367.

Research output: Contribution to journalArticle

@article{03e846a47ad246238b480206ad4611b7,
title = "A new statistically-constrained deformable registration framework for MR brain images",
abstract = "Statistical models of deformations (SMD) capture the variability of deformations from the template image onto a group of sample images and can be used to constrain the traditional deformable registration algorithms to improve their robustness and accuracy. This paper employs a wavelet-PCA-based SMD to constrain the traditional deformable registration based on the Bayesian framework. The template image is adaptively warped by an intermediate deformation field generated based on the SMD during the registration procedure, and the traditional deformable registration is performed to register the intermediate template image with the input subject image. Since the intermediate template image is much more similar to the subject image, and the deformation is relatively small and local, it is less likely to be stuck into undesired local minimum using the same deformable registration in this framework. Experiments show that the proposed statistically-constrained deformable registration framework is more robust and accurate than the conventional registration.",
keywords = "Biomedical image processing, Image registration, Magnetic resonance imaging, Statistical model",
author = "Zhong Xue and Dinggang Shen",
year = "2009",
month = "1",
day = "1",
doi = "10.1504/IJMEI.2009.022646",
language = "English",
volume = "1",
pages = "357--367",
journal = "International Journal of Medical Engineering and Informatics",
issn = "1755-0653",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

TY - JOUR

T1 - A new statistically-constrained deformable registration framework for MR brain images

AU - Xue, Zhong

AU - Shen, Dinggang

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Statistical models of deformations (SMD) capture the variability of deformations from the template image onto a group of sample images and can be used to constrain the traditional deformable registration algorithms to improve their robustness and accuracy. This paper employs a wavelet-PCA-based SMD to constrain the traditional deformable registration based on the Bayesian framework. The template image is adaptively warped by an intermediate deformation field generated based on the SMD during the registration procedure, and the traditional deformable registration is performed to register the intermediate template image with the input subject image. Since the intermediate template image is much more similar to the subject image, and the deformation is relatively small and local, it is less likely to be stuck into undesired local minimum using the same deformable registration in this framework. Experiments show that the proposed statistically-constrained deformable registration framework is more robust and accurate than the conventional registration.

AB - Statistical models of deformations (SMD) capture the variability of deformations from the template image onto a group of sample images and can be used to constrain the traditional deformable registration algorithms to improve their robustness and accuracy. This paper employs a wavelet-PCA-based SMD to constrain the traditional deformable registration based on the Bayesian framework. The template image is adaptively warped by an intermediate deformation field generated based on the SMD during the registration procedure, and the traditional deformable registration is performed to register the intermediate template image with the input subject image. Since the intermediate template image is much more similar to the subject image, and the deformation is relatively small and local, it is less likely to be stuck into undesired local minimum using the same deformable registration in this framework. Experiments show that the proposed statistically-constrained deformable registration framework is more robust and accurate than the conventional registration.

KW - Biomedical image processing

KW - Image registration

KW - Magnetic resonance imaging

KW - Statistical model

UR - http://www.scopus.com/inward/record.url?scp=77953394225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953394225&partnerID=8YFLogxK

U2 - 10.1504/IJMEI.2009.022646

DO - 10.1504/IJMEI.2009.022646

M3 - Article

AN - SCOPUS:77953394225

VL - 1

SP - 357

EP - 367

JO - International Journal of Medical Engineering and Informatics

JF - International Journal of Medical Engineering and Informatics

SN - 1755-0653

IS - 3

ER -