Forskning ved Københavns Universitet - Københavns Universitet

Forside

Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. / de Bruijne, Marleen; van Ginneken, Bram; Viergever, Max A.; Niessen, Wiro J.

Information Processing in Medical Imaging: 18th International Conference, IPMI 2003. Ambleside, UK, July 20- 25, 2003. Proceedings. <Forlag uden navn>, 2003. s. 136-147 (Lecture notes in computer science, Bind 2732/2003).

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

de Bruijne, M, van Ginneken, B, Viergever, MA & Niessen, WJ 2003, Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. i Information Processing in Medical Imaging: 18th International Conference, IPMI 2003. Ambleside, UK, July 20- 25, 2003. Proceedings. <Forlag uden navn>, Lecture notes in computer science, bind 2732/2003, s. 136-147, 18th International Conference in Information Processing in Medical Imaging (IPMI), Ambleside, Storbritannien, 29/11/2010. https://doi.org/10.1007/b11820

APA

de Bruijne, M., van Ginneken, B., Viergever, M. A., & Niessen, W. J. (2003). Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. I Information Processing in Medical Imaging: 18th International Conference, IPMI 2003. Ambleside, UK, July 20- 25, 2003. Proceedings (s. 136-147). <Forlag uden navn>. Lecture notes in computer science Bind 2732/2003 https://doi.org/10.1007/b11820

Vancouver

de Bruijne M, van Ginneken B, Viergever MA, Niessen WJ. Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. I Information Processing in Medical Imaging: 18th International Conference, IPMI 2003. Ambleside, UK, July 20- 25, 2003. Proceedings. <Forlag uden navn>. 2003. s. 136-147. (Lecture notes in computer science, Bind 2732/2003). https://doi.org/10.1007/b11820

Author

de Bruijne, Marleen ; van Ginneken, Bram ; Viergever, Max A. ; Niessen, Wiro J. / Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images. Information Processing in Medical Imaging: 18th International Conference, IPMI 2003. Ambleside, UK, July 20- 25, 2003. Proceedings. <Forlag uden navn>, 2003. s. 136-147 (Lecture notes in computer science, Bind 2732/2003).

Bibtex

@inproceedings{10f690e06d1811dd8d9f000ea68e967b,
title = "Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images",
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.",
author = "{de Bruijne}, Marleen and {van Ginneken}, Bram and Viergever, {Max A.} and Niessen, {Wiro J.}",
year = "2003",
doi = "10.1007/b11820",
language = "English",
isbn = "978-3-540-40560-3",
series = "Lecture notes in computer science",
publisher = "<Forlag uden navn>",
pages = "136--147",
booktitle = "Information Processing in Medical Imaging",
note = "null ; Conference date: 29-11-2010",

}

RIS

TY - GEN

T1 - Adapting Active Shape Models for 3D Segmentation of Tubular Structures in Medical Images

AU - de Bruijne, Marleen

AU - van Ginneken, Bram

AU - Viergever, Max A.

AU - Niessen, Wiro J.

N1 - Conference code: 18

PY - 2003

Y1 - 2003

N2 - 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.

AB - 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.

U2 - 10.1007/b11820

DO - 10.1007/b11820

M3 - Article in proceedings

SN - 978-3-540-40560-3

T3 - Lecture notes in computer science

SP - 136

EP - 147

BT - Information Processing in Medical Imaging

PB - <Forlag uden navn>

Y2 - 29 November 2010

ER -

ID: 5555791