A Bayesian model of shape and appearance for subcortical brain segmentation

Brian Patenaude, Stephen M. Smith, David N. Kennedy, Mark Jenkinson

Research output: Contribution to journalArticle

1046 Citations (Scopus)

Abstract

Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.

LanguageEnglish
Pages907-922
Number of pages16
JournalNeuroImage
Volume56
Issue number3
DOIs
Publication statusPublished - 1 Jun 2011

Keywords

  • Bayesian
  • Classification
  • Segmentation
  • Shape model
  • Subcortical structures

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Patenaude, Brian ; Smith, Stephen M. ; Kennedy, David N. ; Jenkinson, Mark. / A Bayesian model of shape and appearance for subcortical brain segmentation. In: NeuroImage. 2011 ; Vol. 56, No. 3. pp. 907-922.
@article{c76b6ab43dda4db88d944b7508368a00,
title = "A Bayesian model of shape and appearance for subcortical brain segmentation",
abstract = "Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.",
keywords = "Bayesian, Classification, Segmentation, Shape model, Subcortical structures",
author = "Brian Patenaude and Smith, {Stephen M.} and Kennedy, {David N.} and Mark Jenkinson",
year = "2011",
month = "6",
day = "1",
doi = "10.1016/j.neuroimage.2011.02.046",
language = "English",
volume = "56",
pages = "907--922",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "3",

}

A Bayesian model of shape and appearance for subcortical brain segmentation. / Patenaude, Brian; Smith, Stephen M.; Kennedy, David N.; Jenkinson, Mark.

In: NeuroImage, Vol. 56, No. 3, 01.06.2011, p. 907-922.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Bayesian model of shape and appearance for subcortical brain segmentation

AU - Patenaude, Brian

AU - Smith, Stephen M.

AU - Kennedy, David N.

AU - Jenkinson, Mark

PY - 2011/6/1

Y1 - 2011/6/1

N2 - Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.

AB - Automatic segmentation of subcortical structures in human brain MR images is an important but difficult task due to poor and variable intensity contrast. Clear, well-defined intensity features are absent in many places along typical structure boundaries and so extra information is required to achieve successful segmentation. A method is proposed here that uses manually labelled image data to provide anatomical training information. It utilises the principles of the Active Shape and Appearance Models but places them within a Bayesian framework, allowing probabilistic relationships between shape and intensity to be fully exploited. The model is trained for 15 different subcortical structures using 336 manually-labelled T1-weighted MR images. Using the Bayesian approach, conditional probabilities can be calculated easily and efficiently, avoiding technical problems of ill-conditioned covariance matrices, even with weak priors, and eliminating the need for fitting extra empirical scaling parameters, as is required in standard Active Appearance Models. Furthermore, differences in boundary vertex locations provide a direct, purely local measure of geometric change in structure between groups that, unlike voxel-based morphometry, is not dependent on tissue classification methods or arbitrary smoothing. In this paper the fully-automated segmentation method is presented and assessed both quantitatively, using Leave-One-Out testing on the 336 training images, and qualitatively, using an independent clinical dataset involving Alzheimer's disease. Median Dice overlaps between 0.7 and 0.9 are obtained with this method, which is comparable or better than other automated methods. An implementation of this method, called FIRST, is currently distributed with the freely-available FSL package.

KW - Bayesian

KW - Classification

KW - Segmentation

KW - Shape model

KW - Subcortical structures

UR - http://www.scopus.com/inward/record.url?scp=79955484518&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2011.02.046

DO - 10.1016/j.neuroimage.2011.02.046

M3 - Article

VL - 56

SP - 907

EP - 922

JO - NeuroImage

T2 - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 3

ER -