Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping

Zhong Xue, Dinggang Shen, Christos Davatzikos

Research output: Contribution to journalArticle

70 Citations (Scopus)

Abstract

This paper proposes a 3D statistical model aiming at effectively capturing statistics of high-dimensional deformation fields and then uses this prior knowledge to constrain 3D image warping. The conventional statistical shape model methods, such as the active shape model (ASM), have been very successful in modeling shape variability. However, their accuracy and effectiveness typically drop dramatically in high-dimensionality problems involving relatively small training datasets, which is customary in 3D and 4D medical imaging applications. The proposed statistical model of deformation (SMD) uses wavelet-based decompositions coupled with PCA in each wavelet band, in order to more accurately estimate the pdf of high-dimensional deformation fields, when a relatively small number of training samples are available. SMD is further used as statistical prior to regularize the deformation field in an SMD-constrained deformable registration framework. As a result, more robust registration results are obtained relative to using generic smoothness constraints on deformation fields, such as Laplacian-based regularization. In experiments, we first illustrate the performance of SMD in representing the variability of deformation fields and then evaluate the performance of the SMD-constrained registration, via comparing a hierarchical volumetric image registration algorithm, HAMMER, with its SMD-constrained version, referred to as SMD+HAMMER. This SMD-constrained deformable registration framework can potentially incorporate various registration algorithms to improve robustness and stability via statistical shape constraints.

Original languageEnglish
Pages (from-to)740-751
Number of pages12
JournalMedical Image Analysis
Volume10
Issue number5
DOIs
Publication statusPublished - 2006 Oct 1
Externally publishedYes

Fingerprint

Statistical Models
Passive Cutaneous Anaphylaxis
Diagnostic Imaging
Image registration
Medical imaging
Statistics

Keywords

  • Active shape model
  • Deformable registration
  • Shape statistics
  • Statistical shape model
  • Wavelet packet transform

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Medicine (miscellaneous)
  • Computer Science (miscellaneous)

Cite this

Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping. / Xue, Zhong; Shen, Dinggang; Davatzikos, Christos.

In: Medical Image Analysis, Vol. 10, No. 5, 01.10.2006, p. 740-751.

Research output: Contribution to journalArticle

@article{d4859fc73e504a56aa0d98b88fa7e1b1,
title = "Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping",
abstract = "This paper proposes a 3D statistical model aiming at effectively capturing statistics of high-dimensional deformation fields and then uses this prior knowledge to constrain 3D image warping. The conventional statistical shape model methods, such as the active shape model (ASM), have been very successful in modeling shape variability. However, their accuracy and effectiveness typically drop dramatically in high-dimensionality problems involving relatively small training datasets, which is customary in 3D and 4D medical imaging applications. The proposed statistical model of deformation (SMD) uses wavelet-based decompositions coupled with PCA in each wavelet band, in order to more accurately estimate the pdf of high-dimensional deformation fields, when a relatively small number of training samples are available. SMD is further used as statistical prior to regularize the deformation field in an SMD-constrained deformable registration framework. As a result, more robust registration results are obtained relative to using generic smoothness constraints on deformation fields, such as Laplacian-based regularization. In experiments, we first illustrate the performance of SMD in representing the variability of deformation fields and then evaluate the performance of the SMD-constrained registration, via comparing a hierarchical volumetric image registration algorithm, HAMMER, with its SMD-constrained version, referred to as SMD+HAMMER. This SMD-constrained deformable registration framework can potentially incorporate various registration algorithms to improve robustness and stability via statistical shape constraints.",
keywords = "Active shape model, Deformable registration, Shape statistics, Statistical shape model, Wavelet packet transform",
author = "Zhong Xue and Dinggang Shen and Christos Davatzikos",
year = "2006",
month = "10",
day = "1",
doi = "10.1016/j.media.2006.06.007",
language = "English",
volume = "10",
pages = "740--751",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "5",

}

TY - JOUR

T1 - Statistical representation of high-dimensional deformation fields with application to statistically constrained 3D warping

AU - Xue, Zhong

AU - Shen, Dinggang

AU - Davatzikos, Christos

PY - 2006/10/1

Y1 - 2006/10/1

N2 - This paper proposes a 3D statistical model aiming at effectively capturing statistics of high-dimensional deformation fields and then uses this prior knowledge to constrain 3D image warping. The conventional statistical shape model methods, such as the active shape model (ASM), have been very successful in modeling shape variability. However, their accuracy and effectiveness typically drop dramatically in high-dimensionality problems involving relatively small training datasets, which is customary in 3D and 4D medical imaging applications. The proposed statistical model of deformation (SMD) uses wavelet-based decompositions coupled with PCA in each wavelet band, in order to more accurately estimate the pdf of high-dimensional deformation fields, when a relatively small number of training samples are available. SMD is further used as statistical prior to regularize the deformation field in an SMD-constrained deformable registration framework. As a result, more robust registration results are obtained relative to using generic smoothness constraints on deformation fields, such as Laplacian-based regularization. In experiments, we first illustrate the performance of SMD in representing the variability of deformation fields and then evaluate the performance of the SMD-constrained registration, via comparing a hierarchical volumetric image registration algorithm, HAMMER, with its SMD-constrained version, referred to as SMD+HAMMER. This SMD-constrained deformable registration framework can potentially incorporate various registration algorithms to improve robustness and stability via statistical shape constraints.

AB - This paper proposes a 3D statistical model aiming at effectively capturing statistics of high-dimensional deformation fields and then uses this prior knowledge to constrain 3D image warping. The conventional statistical shape model methods, such as the active shape model (ASM), have been very successful in modeling shape variability. However, their accuracy and effectiveness typically drop dramatically in high-dimensionality problems involving relatively small training datasets, which is customary in 3D and 4D medical imaging applications. The proposed statistical model of deformation (SMD) uses wavelet-based decompositions coupled with PCA in each wavelet band, in order to more accurately estimate the pdf of high-dimensional deformation fields, when a relatively small number of training samples are available. SMD is further used as statistical prior to regularize the deformation field in an SMD-constrained deformable registration framework. As a result, more robust registration results are obtained relative to using generic smoothness constraints on deformation fields, such as Laplacian-based regularization. In experiments, we first illustrate the performance of SMD in representing the variability of deformation fields and then evaluate the performance of the SMD-constrained registration, via comparing a hierarchical volumetric image registration algorithm, HAMMER, with its SMD-constrained version, referred to as SMD+HAMMER. This SMD-constrained deformable registration framework can potentially incorporate various registration algorithms to improve robustness and stability via statistical shape constraints.

KW - Active shape model

KW - Deformable registration

KW - Shape statistics

KW - Statistical shape model

KW - Wavelet packet transform

UR - http://www.scopus.com/inward/record.url?scp=33747837711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747837711&partnerID=8YFLogxK

U2 - 10.1016/j.media.2006.06.007

DO - 10.1016/j.media.2006.06.007

M3 - Article

C2 - 16887376

AN - SCOPUS:33747837711

VL - 10

SP - 740

EP - 751

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 5

ER -