Homeomorphic brain image segmentation with topological and statistical atlases

Pierre Louis Bazin, Dzung L. Pham

Research output: Contribution to journalArticle

Abstract

Atlas-based segmentation techniques are often employed to encode anatomical information for the delineation of multiple structures in magnetic resonance images of the brain. One of the primary challenges of these approaches is to efficiently model qualitative and quantitative anatomical knowledge without introducing a strong bias toward certain anatomical preferences when segmenting new images. This paper explores the use of topological information as a prior and proposes a segmentation framework based on both topological and statistical atlases of brain anatomy. Topology can be used to describe continuity of structures, as well as the relationships between structures, and is often a critical component in cortical surface reconstruction and deformation-based morphometry. Our method guarantees strict topological equivalence between the segmented image and the atlas, and relies only weakly on a statistical atlas of shape. Tissue classification and fast marching methods are used to provide a powerful and flexible framework to handle multiple image contrasts, high levels of noise, gain field inhomogeneities, and variable anatomies. The segmentation algorithm has been validated on simulated and real brain image data and made freely available to researchers. Our experiments demonstrate the accuracy and robustness of the method and the limited influence of the statistical atlas.

Original languageEnglish (US)
Pages (from-to)616-625
Number of pages10
JournalMedical Image Analysis
Volume12
Issue number5
DOIs
StatePublished - Oct 2008

Fingerprint

Atlases
Image segmentation
Brain
Surface reconstruction
Magnetic resonance
Anatomy
Topology
Tissue
Noise
Magnetic Resonance Spectroscopy
Research Personnel
Experiments

Keywords

  • Brain segmentation
  • Digital homeomorphism
  • Fast marching segmentation
  • Topological atlas

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Medicine (miscellaneous)
  • Computer Science (miscellaneous)

Cite this

Homeomorphic brain image segmentation with topological and statistical atlases. / Bazin, Pierre Louis; Pham, Dzung L.

In: Medical Image Analysis, Vol. 12, No. 5, 10.2008, p. 616-625.

Research output: Contribution to journalArticle

Bazin, Pierre Louis ; Pham, Dzung L. / Homeomorphic brain image segmentation with topological and statistical atlases. In: Medical Image Analysis. 2008 ; Vol. 12, No. 5. pp. 616-625.
@article{e975ed67ba32411aa166605ca1864671,
title = "Homeomorphic brain image segmentation with topological and statistical atlases",
abstract = "Atlas-based segmentation techniques are often employed to encode anatomical information for the delineation of multiple structures in magnetic resonance images of the brain. One of the primary challenges of these approaches is to efficiently model qualitative and quantitative anatomical knowledge without introducing a strong bias toward certain anatomical preferences when segmenting new images. This paper explores the use of topological information as a prior and proposes a segmentation framework based on both topological and statistical atlases of brain anatomy. Topology can be used to describe continuity of structures, as well as the relationships between structures, and is often a critical component in cortical surface reconstruction and deformation-based morphometry. Our method guarantees strict topological equivalence between the segmented image and the atlas, and relies only weakly on a statistical atlas of shape. Tissue classification and fast marching methods are used to provide a powerful and flexible framework to handle multiple image contrasts, high levels of noise, gain field inhomogeneities, and variable anatomies. The segmentation algorithm has been validated on simulated and real brain image data and made freely available to researchers. Our experiments demonstrate the accuracy and robustness of the method and the limited influence of the statistical atlas.",
keywords = "Brain segmentation, Digital homeomorphism, Fast marching segmentation, Topological atlas",
author = "Bazin, {Pierre Louis} and Pham, {Dzung L.}",
year = "2008",
month = "10",
doi = "10.1016/j.media.2008.06.008",
language = "English (US)",
volume = "12",
pages = "616--625",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "5",

}

TY - JOUR

T1 - Homeomorphic brain image segmentation with topological and statistical atlases

AU - Bazin, Pierre Louis

AU - Pham, Dzung L.

PY - 2008/10

Y1 - 2008/10

N2 - Atlas-based segmentation techniques are often employed to encode anatomical information for the delineation of multiple structures in magnetic resonance images of the brain. One of the primary challenges of these approaches is to efficiently model qualitative and quantitative anatomical knowledge without introducing a strong bias toward certain anatomical preferences when segmenting new images. This paper explores the use of topological information as a prior and proposes a segmentation framework based on both topological and statistical atlases of brain anatomy. Topology can be used to describe continuity of structures, as well as the relationships between structures, and is often a critical component in cortical surface reconstruction and deformation-based morphometry. Our method guarantees strict topological equivalence between the segmented image and the atlas, and relies only weakly on a statistical atlas of shape. Tissue classification and fast marching methods are used to provide a powerful and flexible framework to handle multiple image contrasts, high levels of noise, gain field inhomogeneities, and variable anatomies. The segmentation algorithm has been validated on simulated and real brain image data and made freely available to researchers. Our experiments demonstrate the accuracy and robustness of the method and the limited influence of the statistical atlas.

AB - Atlas-based segmentation techniques are often employed to encode anatomical information for the delineation of multiple structures in magnetic resonance images of the brain. One of the primary challenges of these approaches is to efficiently model qualitative and quantitative anatomical knowledge without introducing a strong bias toward certain anatomical preferences when segmenting new images. This paper explores the use of topological information as a prior and proposes a segmentation framework based on both topological and statistical atlases of brain anatomy. Topology can be used to describe continuity of structures, as well as the relationships between structures, and is often a critical component in cortical surface reconstruction and deformation-based morphometry. Our method guarantees strict topological equivalence between the segmented image and the atlas, and relies only weakly on a statistical atlas of shape. Tissue classification and fast marching methods are used to provide a powerful and flexible framework to handle multiple image contrasts, high levels of noise, gain field inhomogeneities, and variable anatomies. The segmentation algorithm has been validated on simulated and real brain image data and made freely available to researchers. Our experiments demonstrate the accuracy and robustness of the method and the limited influence of the statistical atlas.

KW - Brain segmentation

KW - Digital homeomorphism

KW - Fast marching segmentation

KW - Topological atlas

UR - http://www.scopus.com/inward/record.url?scp=48749119801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48749119801&partnerID=8YFLogxK

U2 - 10.1016/j.media.2008.06.008

DO - 10.1016/j.media.2008.06.008

M3 - Article

VL - 12

SP - 616

EP - 625

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 5

ER -