Groupwise morphometric analysis based on morphological appearance manifold

N. X. Lian, C. Davatzikos

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

Abstract

The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearance manifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifoldconstrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearance manifold is treated via local approximations of the manifold via PCA.

Original languageEnglish (US)
Title of host publication2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Pages133-140
Number of pages8
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, United States
Duration: Jun 20 2009Jun 25 2009

Other

Other2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
CountryUnited States
CityMiami, FL
Period6/20/096/25/09

Fingerprint

Equivalence classes
Computer vision
Statistical methods
Lighting

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Lian, N. X., & Davatzikos, C. (2009). Groupwise morphometric analysis based on morphological appearance manifold. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 (pp. 133-140). [5204042] https://doi.org/10.1109/CVPR.2009.5204042

Groupwise morphometric analysis based on morphological appearance manifold. / Lian, N. X.; Davatzikos, C.

2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. p. 133-140 5204042.

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

Lian, NX & Davatzikos, C 2009, Groupwise morphometric analysis based on morphological appearance manifold. in 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009., 5204042, pp. 133-140, 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, Miami, FL, United States, 6/20/09. https://doi.org/10.1109/CVPR.2009.5204042
Lian NX, Davatzikos C. Groupwise morphometric analysis based on morphological appearance manifold. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. p. 133-140. 5204042 https://doi.org/10.1109/CVPR.2009.5204042
Lian, N. X. ; Davatzikos, C. / Groupwise morphometric analysis based on morphological appearance manifold. 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. 2009. pp. 133-140
@inproceedings{27513207477f44cd8c4dd07264653e84,
title = "Groupwise morphometric analysis based on morphological appearance manifold",
abstract = "The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearance manifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifoldconstrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearance manifold is treated via local approximations of the manifold via PCA.",
author = "Lian, {N. X.} and C. Davatzikos",
year = "2009",
doi = "10.1109/CVPR.2009.5204042",
language = "English (US)",
isbn = "9781424439911",
pages = "133--140",
booktitle = "2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009",

}

TY - GEN

T1 - Groupwise morphometric analysis based on morphological appearance manifold

AU - Lian, N. X.

AU - Davatzikos, C.

PY - 2009

Y1 - 2009

N2 - The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearance manifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifoldconstrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearance manifold is treated via local approximations of the manifold via PCA.

AB - The field of computational anatomy has developed rigorous frameworks for analyzing anatomical shape, based on diffeomorphic transformations of a template. However, differences in algorithms used for template warping, in regularization parameters, and in the template itself, lead to different representations of the same anatomy. Variations of these parameters are considered as confounding factors as they give rise to non-unique representation. Recently, extensions of the conventional computational anatomy framework to account for such confounding variations have shown that learning the equivalence class derived from the multitude of representations can lead to improved and more stable morphological descriptors. Herein, we follow that approach, estimating the morphological appearance manifold obtained by varying parameters of the template warping procedure. Our approach parallels work in the computer vision field, in which variations lighting, pose and other parameters leads to image appearance manifolds representing the exact same figure in different ways. The proposed framework is then used for groupwise registration and statistical analysis of biomedical images, by employing a minimum variance criterion on selected complete morphological descriptor to perform manifoldconstrained optimization, i.e. to traverse each individual's morphological appearance manifold until group variance is minimal. Effectively, this process removes the aforementioned confounding effects and potentially leads to morphological representations reflecting purely biological variations, instead of variations introduced by modeling assumptions and parameter settings. The nonlinearity of a morphological appearance manifold is treated via local approximations of the manifold via PCA.

UR - http://www.scopus.com/inward/record.url?scp=70449562424&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449562424&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2009.5204042

DO - 10.1109/CVPR.2009.5204042

M3 - Conference contribution

SN - 9781424439911

SP - 133

EP - 140

BT - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

ER -