TY - JOUR
T1 - Hierarchical active shape models, using the wavelet transform
AU - Davatzikos, Christos
AU - Tao, Xiaodong
AU - Shen, Dinggang
N1 - Funding Information:
Manuscript received October 15,2001; revised September 10, 2002. This work was supported in part by the National Institutes of Health (NIH) under Grant R01 AG14971–03. Asterisk indicates corresponding author. *C. Davatzikos is with the Section for Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104 USA (e-mail: hristos@rad.jhu.edu).
Copyright:
Copyright 2008 Elsevier B.V., All rights reserved.
PY - 2003/3
Y1 - 2003/3
N2 - Active shape models (ASMs) are often limited by the inability of relatively few eigenvectors to capture the full range of biological shape variability. This paper presents a method that overcomes this limitation, by using a hierarchical formulation of active shape models, using the wavelet transform. The statistical properties of the wavelet transform of a deformable contour are analyzed via principal component analysis, and used as priors in the contour's deformation. Some of these priors reflect relatively global shape characteristics of the object boundaries, whereas, some of them capture local and high-frequency shape characteristics and, thus, serve as local smoothness constraints. This formulation achieves two objectives. First, it is robust when only a limited number of training samples is available. Second, by using local statistics as smoothness constraints, it eliminates the need for adopting ad hoc physical models, such as elasticity or other smoothness models, which do not necessarily reflect true biological variability. Examples on magnetic resonance images of the corpus callosum and hand contours demonstrate that good and fully automated segmentations can be achieved, even with as few as five training samples.
AB - Active shape models (ASMs) are often limited by the inability of relatively few eigenvectors to capture the full range of biological shape variability. This paper presents a method that overcomes this limitation, by using a hierarchical formulation of active shape models, using the wavelet transform. The statistical properties of the wavelet transform of a deformable contour are analyzed via principal component analysis, and used as priors in the contour's deformation. Some of these priors reflect relatively global shape characteristics of the object boundaries, whereas, some of them capture local and high-frequency shape characteristics and, thus, serve as local smoothness constraints. This formulation achieves two objectives. First, it is robust when only a limited number of training samples is available. Second, by using local statistics as smoothness constraints, it eliminates the need for adopting ad hoc physical models, such as elasticity or other smoothness models, which do not necessarily reflect true biological variability. Examples on magnetic resonance images of the corpus callosum and hand contours demonstrate that good and fully automated segmentations can be achieved, even with as few as five training samples.
KW - Active shape model
KW - Deformable contours
KW - The wavelet transform
UR - http://www.scopus.com/inward/record.url?scp=0038321577&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0038321577&partnerID=8YFLogxK
U2 - 10.1109/TMI.2003.809688
DO - 10.1109/TMI.2003.809688
M3 - Article
C2 - 12760558
AN - SCOPUS:0038321577
SN - 0278-0062
VL - 22
SP - 414
EP - 423
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 3
ER -