Active Shape Models (ASM) have proven to be an effective approach
for image segmentation. In some applications, however, the linear
model of gray level appearance around a contour that is used in ASM
is not sufficient for accurate boundary localization. Furthermore,
the statistical shape model may be too restricted if the training
set is limited. This paper describes modifications to both the shape
and the appearance model of the original ASM formulation. Shape model
flexibility is increased, for tubular objects, by modeling the axis
deformation independent of the cross-sectional deformation, and by
adding supplementary cylindrical deformation modes. Furthermore,
a novel appearance modeling scheme that effectively deals with a
highly varying background is developed. In contrast with the conventional
ASM approach, the new appearance model is trained on both boundary
and non-boundary points, and the probability that a given point belongs
to the boundary is estimated non-parametrically. The methods are
evaluated on the complex task of segmenting thrombus in abdominal
aortic aneurysms (AAA). Shape approximation errors were successfully
reduced using the two shape model extensions. Segmentation using
the new appearance model significantly outperformed the original
ASM scheme; average volume errors are 5.1\% and 45\% respectively.
%0 Journal Article
%1 Bruijne2003
%A de Bruijne, Marleen
%A van Ginneken, Bram
%A Viergever, Max A
%A Niessen, Wiro J
%D 2003
%J Inf Process Med Imaging
%K Abdominal, Algorithms; Anatomy, Aneurysm, Aorta, Aortic Automated; Biological; Computer Computer-Assisted, Cross-Sectional, Dynamics; Enhancement, Humans; Image Imaging, Interpretation, Models, Nonlinear Pattern Radiographic Recognition, Reproducibility Results; Sensitivity Simulation; Specificity; Statistical; Subtraction Technique Three-Dimensional, and methods; of radiography;
%P 136--147
%T Adapting Active Shape Models for 3D segmentation of tubular structures
in medical images.
%V 18
%X Active Shape Models (ASM) have proven to be an effective approach
for image segmentation. In some applications, however, the linear
model of gray level appearance around a contour that is used in ASM
is not sufficient for accurate boundary localization. Furthermore,
the statistical shape model may be too restricted if the training
set is limited. This paper describes modifications to both the shape
and the appearance model of the original ASM formulation. Shape model
flexibility is increased, for tubular objects, by modeling the axis
deformation independent of the cross-sectional deformation, and by
adding supplementary cylindrical deformation modes. Furthermore,
a novel appearance modeling scheme that effectively deals with a
highly varying background is developed. In contrast with the conventional
ASM approach, the new appearance model is trained on both boundary
and non-boundary points, and the probability that a given point belongs
to the boundary is estimated non-parametrically. The methods are
evaluated on the complex task of segmenting thrombus in abdominal
aortic aneurysms (AAA). Shape approximation errors were successfully
reduced using the two shape model extensions. Segmentation using
the new appearance model significantly outperformed the original
ASM scheme; average volume errors are 5.1\% and 45\% respectively.
@article{Bruijne2003,
abstract = {Active Shape Models (ASM) have proven to be an effective approach
for image segmentation. In some applications, however, the linear
model of gray level appearance around a contour that is used in ASM
is not sufficient for accurate boundary localization. Furthermore,
the statistical shape model may be too restricted if the training
set is limited. This paper describes modifications to both the shape
and the appearance model of the original ASM formulation. Shape model
flexibility is increased, for tubular objects, by modeling the axis
deformation independent of the cross-sectional deformation, and by
adding supplementary cylindrical deformation modes. Furthermore,
a novel appearance modeling scheme that effectively deals with a
highly varying background is developed. In contrast with the conventional
ASM approach, the new appearance model is trained on both boundary
and non-boundary points, and the probability that a given point belongs
to the boundary is estimated non-parametrically. The methods are
evaluated on the complex task of segmenting thrombus in abdominal
aortic aneurysms (AAA). Shape approximation errors were successfully
reduced using the two shape model extensions. Segmentation using
the new appearance model significantly outperformed the original
ASM scheme; average volume errors are 5.1\% and 45\% respectively.},
added-at = {2011-03-11T12:21:24.000+0100},
author = {de Bruijne, Marleen and van Ginneken, Bram and Viergever, Max A and Niessen, Wiro J},
biburl = {https://www.bibsonomy.org/bibtex/2947406e5c975e40db94c00ff22d3b095/jmaiora},
institution = {Image Sciences Institute, University Medical Center Utrecht, The
Netherlands.},
interhash = {fa0cf651f3a62ec7eb7460de364e7c32},
intrahash = {947406e5c975e40db94c00ff22d3b095},
journal = {Inf Process Med Imaging},
keywords = {Abdominal, Algorithms; Anatomy, Aneurysm, Aorta, Aortic Automated; Biological; Computer Computer-Assisted, Cross-Sectional, Dynamics; Enhancement, Humans; Image Imaging, Interpretation, Models, Nonlinear Pattern Radiographic Recognition, Reproducibility Results; Sensitivity Simulation; Specificity; Statistical; Subtraction Technique Three-Dimensional, and methods; of radiography;},
language = {eng},
medline-pst = {ppublish},
month = Jul,
owner = {Josu},
pages = {136--147},
pmid = {15344453},
timestamp = {2011-03-11T12:21:25.000+0100},
title = {Adapting Active Shape Models for 3D segmentation of tubular structures
in medical images.},
volume = 18,
year = 2003
}