Shape Particle Filtering for Image Segmentation

Marleen de Bruijne; Mads Nielsen

doi:10.1007/b100265

Shape Particle Filtering for Image Segmentation

39 Citations (Scopus)

Abstract

Deformable template models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but can not cope with localized appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required.

We propose a maximum likelihood shape inference that is based on pixel classification, so that local and non-linear intensity variations are dealt with naturally, while a global shape model ensures a consistent segmentation. Optimization by stochastic sampling removes the need for accurate initialization.

The method is demonstrated on three different medical image segmentation problems: vertebra segmentation in spine radiographs, lung field segmentation in thorax X rays, and delineation of the myocardium of the left ventricle in MRI slices. Accurate results were obtained in all tasks.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention – MICCAI : 7th International Conference, Saint-Malo, France, September 26-29, 2004. Proceedings, Part I
Publisher	<Forlag uden navn>
Publication date	2004
Pages	168-175
ISBN (Print)	978-3-540-22976-6
DOIs	https://doi.org/10.1007/b100265
Publication status	Published - 2004
Externally published	Yes
Event	International Conference in Medical Image Computing and Computer-Assisted Intervention (MICCAI) - Saint-Malo, France Duration: 29 Nov 2010 → … Conference number: 7

Conference

Conference	International Conference in Medical Image Computing and Computer-Assisted Intervention (MICCAI)
Number	7
Country/Territory	France
City	Saint-Malo
Period	29/11/2010 → …

Series	Lecture notes in computer science
Volume	3216/2004
ISSN	0302-9743

Access to Document

10.1007/b100265

http://www.springerlink.de/content/hflf5jq3wy97p70a/fulltext.pdf

Cite this

de Bruijne, M., & Nielsen, M. (2004). Shape Particle Filtering for Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI: 7th International Conference, Saint-Malo, France, September 26-29, 2004. Proceedings, Part I (pp. 168-175). <Forlag uden navn>. Lecture notes in computer science Vol. 3216/2004 https://doi.org/10.1007/b100265

Shape Particle Filtering for Image Segmentation. / de Bruijne, Marleen; Nielsen, Mads.

Medical Image Computing and Computer-Assisted Intervention – MICCAI: 7th International Conference, Saint-Malo, France, September 26-29, 2004. Proceedings, Part I. <Forlag uden navn>, 2004. p. 168-175 (Lecture notes in computer science, Vol. 3216/2004).

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

de Bruijne, M & Nielsen, M 2004, Shape Particle Filtering for Image Segmentation. in Medical Image Computing and Computer-Assisted Intervention – MICCAI: 7th International Conference, Saint-Malo, France, September 26-29, 2004. Proceedings, Part I. <Forlag uden navn>, Lecture notes in computer science, vol. 3216/2004, pp. 168-175, International Conference in Medical Image Computing and Computer-Assisted Intervention (MICCAI), Saint-Malo, France, 29/11/2010. https://doi.org/10.1007/b100265

@inproceedings{85331700532b11dd8d9f000ea68e967b,

title = "Shape Particle Filtering for Image Segmentation",

abstract = "Deformable template models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but can not cope with localized appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required. We propose a maximum likelihood shape inference that is based on pixel classification, so that local and non-linear intensity variations are dealt with naturally, while a global shape model ensures a consistent segmentation. Optimization by stochastic sampling removes the need for accurate initialization. The method is demonstrated on three different medical image segmentation problems: vertebra segmentation in spine radiographs, lung field segmentation in thorax X rays, and delineation of the myocardium of the left ventricle in MRI slices. Accurate results were obtained in all tasks. ",

author = "{de Bruijne}, Marleen and Mads Nielsen",

year = "2004",

doi = "10.1007/b100265",

language = "English",

isbn = "978-3-540-22976-6",

series = "Lecture notes in computer science",

publisher = "<Forlag uden navn>",

pages = "168--175",

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

note = "International Conference in Medical Image Computing and Computer-Assisted Intervention (MICCAI) ; Conference date: 29-11-2010",

}

TY - GEN

T1 - Shape Particle Filtering for Image Segmentation

AU - de Bruijne, Marleen

AU - Nielsen, Mads

N1 - Conference code: 7

PY - 2004

Y1 - 2004

N2 - Deformable template models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but can not cope with localized appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required. We propose a maximum likelihood shape inference that is based on pixel classification, so that local and non-linear intensity variations are dealt with naturally, while a global shape model ensures a consistent segmentation. Optimization by stochastic sampling removes the need for accurate initialization. The method is demonstrated on three different medical image segmentation problems: vertebra segmentation in spine radiographs, lung field segmentation in thorax X rays, and delineation of the myocardium of the left ventricle in MRI slices. Accurate results were obtained in all tasks.

AB - Deformable template models are valuable tools in medical image segmentation. Current methods elegantly incorporate global shape and appearance, but can not cope with localized appearance variations and rely on an assumption of Gaussian gray value distribution. Furthermore, initialization near the optimal solution is required. We propose a maximum likelihood shape inference that is based on pixel classification, so that local and non-linear intensity variations are dealt with naturally, while a global shape model ensures a consistent segmentation. Optimization by stochastic sampling removes the need for accurate initialization. The method is demonstrated on three different medical image segmentation problems: vertebra segmentation in spine radiographs, lung field segmentation in thorax X rays, and delineation of the myocardium of the left ventricle in MRI slices. Accurate results were obtained in all tasks.

U2 - 10.1007/b100265

DO - 10.1007/b100265

M3 - Article in proceedings

C2 - 20209048

SN - 978-3-540-22976-6

T3 - Lecture notes in computer science

SP - 168

EP - 175

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

PB - <Forlag uden navn>

T2 - International Conference in Medical Image Computing and Computer-Assisted Intervention (MICCAI)

Y2 - 29 November 2010

ER -

Shape Particle Filtering for Image Segmentation

Abstract

Conference

Access to Document

Fingerprint

Cite this