Multi-object segmentation using shape particles

Marleen de Bruijne; Mads Nielsen

doi:10.1007/b137723

Multi-object segmentation using shape particles

7 Citations (Scopus)

Abstract

Deformable template models, in which a shape model and its corresponding appearance model are deformed to optimally fit an object in the image, have proven successful in many medical image segmentation tasks. In some applications, the number of objects in an image is not known a priori. In that case not only the most clearly visible object must be extracted, but the full collection of objects present in the image.
We propose a stochastic optimization algorithm that optimizes a distribution of shape particles so that the overall distribution explains as much of the image as possible. Possible spatial interrelationships between objects are modelled and used to steer the evolution of the particle set by generating new shape hypotheses that are consistent with the shapes currently observed.
The method is evaluated on rib segmentation in chest X-rays.

Original language	English
Title of host publication	Information Processing in Medical Imaging
Publisher	<Forlag uden navn>
Publication date	2005
Pages	762-773
ISBN (Print)	978-3-540-26545-0
DOIs	https://doi.org/10.1007/b137723
Publication status	Published - 2005
Externally published	Yes
Event	Information Processing in Medical Imaging (IPMI) - Glenwood Springs, CO, United States Duration: 29 Nov 2010 → … Conference number: 19

Conference

Conference	Information Processing in Medical Imaging (IPMI)
Number	19
Country/Territory	United States
City	Glenwood Springs, CO
Period	29/11/2010 → …

Series	Lecture notes in computer science
Volume	3565/2005
ISSN	0302-9743

Access to Document

10.1007/b137723

http://www.springerlink.de/content/958qg2hljm9wxrwb/fulltext.pdf

Cite this

@inproceedings{cb0c40504c0811dd8d9f000ea68e967b,

title = "Multi-object segmentation using shape particles",

abstract = "Deformable template models, in which a shape model and its corresponding appearance model are deformed to optimally fit an object in the image, have proven successful in many medical image segmentation tasks. In some applications, the number of objects in an image is not known a priori. In that case not only the most clearly visible object must be extracted, but the full collection of objects present in the image.We propose a stochastic optimization algorithm that optimizes a distribution of shape particles so that the overall distribution explains as much of the image as possible. Possible spatial interrelationships between objects are modelled and used to steer the evolution of the particle set by generating new shape hypotheses that are consistent with the shapes currently observed.The method is evaluated on rib segmentation in chest X-rays.",

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

year = "2005",

doi = "10.1007/b137723",

language = "English",

isbn = "978-3-540-26545-0",

series = "Lecture notes in computer science",

publisher = "<Forlag uden navn>",

pages = "762--773",

booktitle = "Information Processing in Medical Imaging",

note = "Information Processing in Medical Imaging (IPMI) ; Conference date: 29-11-2010",

}

TY - GEN

T1 - Multi-object segmentation using shape particles

AU - de Bruijne, Marleen

AU - Nielsen, Mads

N1 - Conference code: 19

PY - 2005

Y1 - 2005

N2 - Deformable template models, in which a shape model and its corresponding appearance model are deformed to optimally fit an object in the image, have proven successful in many medical image segmentation tasks. In some applications, the number of objects in an image is not known a priori. In that case not only the most clearly visible object must be extracted, but the full collection of objects present in the image.We propose a stochastic optimization algorithm that optimizes a distribution of shape particles so that the overall distribution explains as much of the image as possible. Possible spatial interrelationships between objects are modelled and used to steer the evolution of the particle set by generating new shape hypotheses that are consistent with the shapes currently observed.The method is evaluated on rib segmentation in chest X-rays.

AB - Deformable template models, in which a shape model and its corresponding appearance model are deformed to optimally fit an object in the image, have proven successful in many medical image segmentation tasks. In some applications, the number of objects in an image is not known a priori. In that case not only the most clearly visible object must be extracted, but the full collection of objects present in the image.We propose a stochastic optimization algorithm that optimizes a distribution of shape particles so that the overall distribution explains as much of the image as possible. Possible spatial interrelationships between objects are modelled and used to steer the evolution of the particle set by generating new shape hypotheses that are consistent with the shapes currently observed.The method is evaluated on rib segmentation in chest X-rays.

U2 - 10.1007/b137723

DO - 10.1007/b137723

M3 - Article in proceedings

SN - 978-3-540-26545-0

T3 - Lecture notes in computer science

SP - 762

EP - 773

BT - Information Processing in Medical Imaging

PB - <Forlag uden navn>

T2 - Information Processing in Medical Imaging (IPMI)

Y2 - 29 November 2010

ER -

Multi-object segmentation using shape particles

Abstract

Conference

Access to Document

Fingerprint

Cite this