Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations.

Zhong Xue, Dinggang Shen, Bilge Karacali, Christos Davatzikos

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This paper proposes an approach to effectively representing the statistics of high-dimensional deformations, when relatively few training samples are available, and conventional methods, like PCA, fail due to insufficient training. Based on previous work on scale-space decomposition of deformation fields, herein we represent the space of "valid deformations" as the intersection of three subspaces: one that satisfies constraints on deformations themselves, one that satisfies constraints on Jacobian determinants of deformations, and one that represents smooth deformations via a Markov Random Field (MRF). The first two are extensions of PCA-based statistical shape models. They are based on a wavelet packet basis decomposition that allows for more accurate estimation of the covariance structure of deformation or Jacobian fields, and they are used jointly due to their complementary strengths and limitations. The third is a nested MRF regularization aiming at eliminating potential discontinuities introduced by assumptions in the statistical models. A randomly sampled deformation field is projected onto the space of valid deformations via iterative projections on each of these subspaces until convergence, i.e. all three constraints are met. A deformation field simulator uses this process to generate random samples of deformation fields that are not only realistic but also representative of the full range of anatomical variability. These simulated deformations can be used for validation of deformable registration methods. Other potential uses of this approach include representation of shape priors in statistical shape models as well as various estimation and hypothesis testing paradigms in the general fields of computational anatomy and pattern recognition.

Original languageEnglish
Title of host publicationMedical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Pages500-508
Number of pages9
Volume8
EditionPt 2
Publication statusPublished - 2005 Dec 1
Externally publishedYes

Fingerprint

Statistical Models
Passive Cutaneous Anaphylaxis
Brain
Anatomy

Cite this

Xue, Z., Shen, D., Karacali, B., & Davatzikos, C. (2005). Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention (Pt 2 ed., Vol. 8, pp. 500-508)

Statistical representation and simulation of high-dimensional deformations : application to synthesizing brain deformations. / Xue, Zhong; Shen, Dinggang; Karacali, Bilge; Davatzikos, Christos.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 8 Pt 2. ed. 2005. p. 500-508.

Research output: Chapter in Book/Report/Conference proceedingChapter

Xue, Z, Shen, D, Karacali, B & Davatzikos, C 2005, Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations. in Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 edn, vol. 8, pp. 500-508.
Xue Z, Shen D, Karacali B, Davatzikos C. Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations. In Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Pt 2 ed. Vol. 8. 2005. p. 500-508
Xue, Zhong ; Shen, Dinggang ; Karacali, Bilge ; Davatzikos, Christos. / Statistical representation and simulation of high-dimensional deformations : application to synthesizing brain deformations. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention. Vol. 8 Pt 2. ed. 2005. pp. 500-508
@inbook{ae4b86c02b1948e8973798d8c9d09481,
title = "Statistical representation and simulation of high-dimensional deformations: application to synthesizing brain deformations.",
abstract = "This paper proposes an approach to effectively representing the statistics of high-dimensional deformations, when relatively few training samples are available, and conventional methods, like PCA, fail due to insufficient training. Based on previous work on scale-space decomposition of deformation fields, herein we represent the space of {"}valid deformations{"} as the intersection of three subspaces: one that satisfies constraints on deformations themselves, one that satisfies constraints on Jacobian determinants of deformations, and one that represents smooth deformations via a Markov Random Field (MRF). The first two are extensions of PCA-based statistical shape models. They are based on a wavelet packet basis decomposition that allows for more accurate estimation of the covariance structure of deformation or Jacobian fields, and they are used jointly due to their complementary strengths and limitations. The third is a nested MRF regularization aiming at eliminating potential discontinuities introduced by assumptions in the statistical models. A randomly sampled deformation field is projected onto the space of valid deformations via iterative projections on each of these subspaces until convergence, i.e. all three constraints are met. A deformation field simulator uses this process to generate random samples of deformation fields that are not only realistic but also representative of the full range of anatomical variability. These simulated deformations can be used for validation of deformable registration methods. Other potential uses of this approach include representation of shape priors in statistical shape models as well as various estimation and hypothesis testing paradigms in the general fields of computational anatomy and pattern recognition.",
author = "Zhong Xue and Dinggang Shen and Bilge Karacali and Christos Davatzikos",
year = "2005",
month = "12",
day = "1",
language = "English",
volume = "8",
pages = "500--508",
booktitle = "Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention",
edition = "Pt 2",

}

TY - CHAP

T1 - Statistical representation and simulation of high-dimensional deformations

T2 - application to synthesizing brain deformations.

AU - Xue, Zhong

AU - Shen, Dinggang

AU - Karacali, Bilge

AU - Davatzikos, Christos

PY - 2005/12/1

Y1 - 2005/12/1

N2 - This paper proposes an approach to effectively representing the statistics of high-dimensional deformations, when relatively few training samples are available, and conventional methods, like PCA, fail due to insufficient training. Based on previous work on scale-space decomposition of deformation fields, herein we represent the space of "valid deformations" as the intersection of three subspaces: one that satisfies constraints on deformations themselves, one that satisfies constraints on Jacobian determinants of deformations, and one that represents smooth deformations via a Markov Random Field (MRF). The first two are extensions of PCA-based statistical shape models. They are based on a wavelet packet basis decomposition that allows for more accurate estimation of the covariance structure of deformation or Jacobian fields, and they are used jointly due to their complementary strengths and limitations. The third is a nested MRF regularization aiming at eliminating potential discontinuities introduced by assumptions in the statistical models. A randomly sampled deformation field is projected onto the space of valid deformations via iterative projections on each of these subspaces until convergence, i.e. all three constraints are met. A deformation field simulator uses this process to generate random samples of deformation fields that are not only realistic but also representative of the full range of anatomical variability. These simulated deformations can be used for validation of deformable registration methods. Other potential uses of this approach include representation of shape priors in statistical shape models as well as various estimation and hypothesis testing paradigms in the general fields of computational anatomy and pattern recognition.

AB - This paper proposes an approach to effectively representing the statistics of high-dimensional deformations, when relatively few training samples are available, and conventional methods, like PCA, fail due to insufficient training. Based on previous work on scale-space decomposition of deformation fields, herein we represent the space of "valid deformations" as the intersection of three subspaces: one that satisfies constraints on deformations themselves, one that satisfies constraints on Jacobian determinants of deformations, and one that represents smooth deformations via a Markov Random Field (MRF). The first two are extensions of PCA-based statistical shape models. They are based on a wavelet packet basis decomposition that allows for more accurate estimation of the covariance structure of deformation or Jacobian fields, and they are used jointly due to their complementary strengths and limitations. The third is a nested MRF regularization aiming at eliminating potential discontinuities introduced by assumptions in the statistical models. A randomly sampled deformation field is projected onto the space of valid deformations via iterative projections on each of these subspaces until convergence, i.e. all three constraints are met. A deformation field simulator uses this process to generate random samples of deformation fields that are not only realistic but also representative of the full range of anatomical variability. These simulated deformations can be used for validation of deformable registration methods. Other potential uses of this approach include representation of shape priors in statistical shape models as well as various estimation and hypothesis testing paradigms in the general fields of computational anatomy and pattern recognition.

UR - http://www.scopus.com/inward/record.url?scp=79551689792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79551689792&partnerID=8YFLogxK

M3 - Chapter

C2 - 16685997

VL - 8

SP - 500

EP - 508

BT - Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention

ER -