Active Shape Analysis of Mandibular Growth

Klaus Baggesen Hilger; Rasmus Larsen; Sven Kreiborg; Søren Krarup; Tron Andre Darvann; Jeffrey Marsh

doi:10.1007/978-3-540-39903-2_110

Active Shape Analysis of Mandibular Growth

Klaus Baggesen Hilger, Rasmus Larsen, Sven Kreiborg, Søren Krarup, Tron Andre Darvann, Jeffrey Marsh

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

This work contains a clinical validation using biological landmarks of a Geometry Constrained Diffusion registration of mandibular surfaces. Canonical Correlations Analysis is extended to analyse 3D landmarks and the correlations are used as similarity measures for landmark clustering. A novel Active Shape Model is proposed targeting growth modelling by applying Partial Least Squares regression in decomposing the Procrustes tangent space. Shape centroid size is applied as dependent variable but the method generalizes to handle other, both uni- and multivariate, effects probing for high covariation wrt. shape variation.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention - MICCAI
Publisher	Springer
Publication date	2003
Pages	902-909
DOIs	https://doi.org/10.1007/978-3-540-39903-2_110
Publication status	Published - 2003

Series	Lecture Notes in Computer Science
Number	PART 2
Volume	2879
ISSN	0302-9743

Access to Document

10.1007/978-3-540-39903-2_110

OpenUrl availability

Full text

Cite this

@inproceedings{f11619f1086a433e9a46a6c1c9583516,

title = "Active Shape Analysis of Mandibular Growth",

abstract = "This work contains a clinical validation using biological landmarks of a Geometry Constrained Diffusion registration of mandibular surfaces. Canonical Correlations Analysis is extended to analyse 3D landmarks and the correlations are used as similarity measures for landmark clustering. A novel Active Shape Model is proposed targeting growth modelling by applying Partial Least Squares regression in decomposing the Procrustes tangent space. Shape centroid size is applied as dependent variable but the method generalizes to handle other, both uni- and multivariate, effects probing for high covariation wrt. shape variation.",

keywords = "GCD PLS CCA ASM PDM",

author = "Hilger, {Klaus Baggesen} and Rasmus Larsen and Sven Kreiborg and S{\o}ren Krarup and Darvann, {Tron Andre} and Jeffrey Marsh",

year = "2003",

doi = "10.1007/978-3-540-39903-2_110",

language = "English",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "PART 2",

pages = "902--909",

booktitle = "Medical Image Computing and Computer-Assisted Intervention - MICCAI",

}

Active Shape Analysis of Mandibular Growth. / Hilger, Klaus Baggesen; Larsen, Rasmus; Kreiborg, Sven et al.
Medical Image Computing and Computer-Assisted Intervention - MICCAI. Springer, 2003. p. 902-909 (Lecture Notes in Computer Science; No. PART 2, Vol. 2879).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Active Shape Analysis of Mandibular Growth

AU - Hilger, Klaus Baggesen

AU - Larsen, Rasmus

AU - Kreiborg, Sven

AU - Krarup, Søren

AU - Darvann, Tron Andre

AU - Marsh, Jeffrey

PY - 2003

Y1 - 2003

N2 - This work contains a clinical validation using biological landmarks of a Geometry Constrained Diffusion registration of mandibular surfaces. Canonical Correlations Analysis is extended to analyse 3D landmarks and the correlations are used as similarity measures for landmark clustering. A novel Active Shape Model is proposed targeting growth modelling by applying Partial Least Squares regression in decomposing the Procrustes tangent space. Shape centroid size is applied as dependent variable but the method generalizes to handle other, both uni- and multivariate, effects probing for high covariation wrt. shape variation.

AB - This work contains a clinical validation using biological landmarks of a Geometry Constrained Diffusion registration of mandibular surfaces. Canonical Correlations Analysis is extended to analyse 3D landmarks and the correlations are used as similarity measures for landmark clustering. A novel Active Shape Model is proposed targeting growth modelling by applying Partial Least Squares regression in decomposing the Procrustes tangent space. Shape centroid size is applied as dependent variable but the method generalizes to handle other, both uni- and multivariate, effects probing for high covariation wrt. shape variation.

KW - GCD PLS CCA ASM PDM

U2 - 10.1007/978-3-540-39903-2_110

DO - 10.1007/978-3-540-39903-2_110

M3 - Article in proceedings

T3 - Lecture Notes in Computer Science

SP - 902

EP - 909

BT - Medical Image Computing and Computer-Assisted Intervention - MICCAI

PB - Springer

ER -

Active Shape Analysis of Mandibular Growth

Abstract

Access to Document

OpenUrl availability

Fingerprint

Cite this