An evaluation of four automatic methods of segmenting the subcortical structures in the brain

Kolawole Oluwole Babalola, Brian Patenaude, Paul Aljabar, Julia Schnabel, David Kennedy, William Crum, Stephen Smith, Tim Cootes, Mark Jenkinson, Daniel Rueckert

Research output: Contribution to journalArticle

138 Citations (Scopus)

Abstract

The automation of segmentation of subcortical structures in the brain is an active research area. We have comprehensively evaluated four novel methods of fully automated segmentation of subcortical structures using volumetric, spatial overlap and distance-based measures. Two methods are atlas-based - classifier fusion and labelling (CFL) and expectation-maximisation segmentation using a brain atlas (EMS), and two incorporate statistical models of shape and appearance - profile active appearance models (PAM) and Bayesian appearance models (BAM). Each method was applied to the segmentation of 18 subcortical structures in 270 subjects from a diverse pool varying in age, disease, sex and image acquisition parameters. Our results showed that all four methods perform on par with recently published methods. CFL performed better than the others according to all three classes of metrics. In summary over all structures, the ranking by the Dice coefficient was CFL, BAM, joint EMS and PAM. The Hausdorff distance ranked the methods as CFL, joint PAM and BAM, EMS, whilst percentage absolute volumetric difference ranked them as joint CFL and PAM, joint BAM and EMS. Furthermore, as we had four methods of performing segmentation, we investigated whether the results obtained by each method were more similar to each other than to the manual segmentations using Williams' Index. Reassuringly, the Williams' Index was close to 1 for most subjects (mean = 1.02, sd = 0.05), indicating better agreement of each method with the gold standard than with the other methods. However, 2% of cases (mainly amygdala and nucleus accumbens) had values outside 3 standard deviations of the mean.

LanguageEnglish
Pages1435-1447
Number of pages13
JournalNeuroImage
Volume47
Issue number4
DOIs
Publication statusPublished - 1 Oct 2009
Externally publishedYes

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Babalola, K. O., Patenaude, B., Aljabar, P., Schnabel, J., Kennedy, D., Crum, W., ... Rueckert, D. (2009). An evaluation of four automatic methods of segmenting the subcortical structures in the brain. NeuroImage, 47(4), 1435-1447. https://doi.org/10.1016/j.neuroimage.2009.05.029
Babalola, Kolawole Oluwole ; Patenaude, Brian ; Aljabar, Paul ; Schnabel, Julia ; Kennedy, David ; Crum, William ; Smith, Stephen ; Cootes, Tim ; Jenkinson, Mark ; Rueckert, Daniel. / An evaluation of four automatic methods of segmenting the subcortical structures in the brain. In: NeuroImage. 2009 ; Vol. 47, No. 4. pp. 1435-1447.
@article{f949cda9ae7945f1b94422eb6a36a530,
title = "An evaluation of four automatic methods of segmenting the subcortical structures in the brain",
abstract = "The automation of segmentation of subcortical structures in the brain is an active research area. We have comprehensively evaluated four novel methods of fully automated segmentation of subcortical structures using volumetric, spatial overlap and distance-based measures. Two methods are atlas-based - classifier fusion and labelling (CFL) and expectation-maximisation segmentation using a brain atlas (EMS), and two incorporate statistical models of shape and appearance - profile active appearance models (PAM) and Bayesian appearance models (BAM). Each method was applied to the segmentation of 18 subcortical structures in 270 subjects from a diverse pool varying in age, disease, sex and image acquisition parameters. Our results showed that all four methods perform on par with recently published methods. CFL performed better than the others according to all three classes of metrics. In summary over all structures, the ranking by the Dice coefficient was CFL, BAM, joint EMS and PAM. The Hausdorff distance ranked the methods as CFL, joint PAM and BAM, EMS, whilst percentage absolute volumetric difference ranked them as joint CFL and PAM, joint BAM and EMS. Furthermore, as we had four methods of performing segmentation, we investigated whether the results obtained by each method were more similar to each other than to the manual segmentations using Williams' Index. Reassuringly, the Williams' Index was close to 1 for most subjects (mean = 1.02, sd = 0.05), indicating better agreement of each method with the gold standard than with the other methods. However, 2{\%} of cases (mainly amygdala and nucleus accumbens) had values outside 3 standard deviations of the mean.",
author = "Babalola, {Kolawole Oluwole} and Brian Patenaude and Paul Aljabar and Julia Schnabel and David Kennedy and William Crum and Stephen Smith and Tim Cootes and Mark Jenkinson and Daniel Rueckert",
year = "2009",
month = "10",
day = "1",
doi = "10.1016/j.neuroimage.2009.05.029",
language = "English",
volume = "47",
pages = "1435--1447",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

Babalola, KO, Patenaude, B, Aljabar, P, Schnabel, J, Kennedy, D, Crum, W, Smith, S, Cootes, T, Jenkinson, M & Rueckert, D 2009, 'An evaluation of four automatic methods of segmenting the subcortical structures in the brain', NeuroImage, vol. 47, no. 4, pp. 1435-1447. https://doi.org/10.1016/j.neuroimage.2009.05.029

An evaluation of four automatic methods of segmenting the subcortical structures in the brain. / Babalola, Kolawole Oluwole; Patenaude, Brian; Aljabar, Paul; Schnabel, Julia; Kennedy, David; Crum, William; Smith, Stephen; Cootes, Tim; Jenkinson, Mark; Rueckert, Daniel.

In: NeuroImage, Vol. 47, No. 4, 01.10.2009, p. 1435-1447.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An evaluation of four automatic methods of segmenting the subcortical structures in the brain

AU - Babalola, Kolawole Oluwole

AU - Patenaude, Brian

AU - Aljabar, Paul

AU - Schnabel, Julia

AU - Kennedy, David

AU - Crum, William

AU - Smith, Stephen

AU - Cootes, Tim

AU - Jenkinson, Mark

AU - Rueckert, Daniel

PY - 2009/10/1

Y1 - 2009/10/1

N2 - The automation of segmentation of subcortical structures in the brain is an active research area. We have comprehensively evaluated four novel methods of fully automated segmentation of subcortical structures using volumetric, spatial overlap and distance-based measures. Two methods are atlas-based - classifier fusion and labelling (CFL) and expectation-maximisation segmentation using a brain atlas (EMS), and two incorporate statistical models of shape and appearance - profile active appearance models (PAM) and Bayesian appearance models (BAM). Each method was applied to the segmentation of 18 subcortical structures in 270 subjects from a diverse pool varying in age, disease, sex and image acquisition parameters. Our results showed that all four methods perform on par with recently published methods. CFL performed better than the others according to all three classes of metrics. In summary over all structures, the ranking by the Dice coefficient was CFL, BAM, joint EMS and PAM. The Hausdorff distance ranked the methods as CFL, joint PAM and BAM, EMS, whilst percentage absolute volumetric difference ranked them as joint CFL and PAM, joint BAM and EMS. Furthermore, as we had four methods of performing segmentation, we investigated whether the results obtained by each method were more similar to each other than to the manual segmentations using Williams' Index. Reassuringly, the Williams' Index was close to 1 for most subjects (mean = 1.02, sd = 0.05), indicating better agreement of each method with the gold standard than with the other methods. However, 2% of cases (mainly amygdala and nucleus accumbens) had values outside 3 standard deviations of the mean.

AB - The automation of segmentation of subcortical structures in the brain is an active research area. We have comprehensively evaluated four novel methods of fully automated segmentation of subcortical structures using volumetric, spatial overlap and distance-based measures. Two methods are atlas-based - classifier fusion and labelling (CFL) and expectation-maximisation segmentation using a brain atlas (EMS), and two incorporate statistical models of shape and appearance - profile active appearance models (PAM) and Bayesian appearance models (BAM). Each method was applied to the segmentation of 18 subcortical structures in 270 subjects from a diverse pool varying in age, disease, sex and image acquisition parameters. Our results showed that all four methods perform on par with recently published methods. CFL performed better than the others according to all three classes of metrics. In summary over all structures, the ranking by the Dice coefficient was CFL, BAM, joint EMS and PAM. The Hausdorff distance ranked the methods as CFL, joint PAM and BAM, EMS, whilst percentage absolute volumetric difference ranked them as joint CFL and PAM, joint BAM and EMS. Furthermore, as we had four methods of performing segmentation, we investigated whether the results obtained by each method were more similar to each other than to the manual segmentations using Williams' Index. Reassuringly, the Williams' Index was close to 1 for most subjects (mean = 1.02, sd = 0.05), indicating better agreement of each method with the gold standard than with the other methods. However, 2% of cases (mainly amygdala and nucleus accumbens) had values outside 3 standard deviations of the mean.

UR - http://www.scopus.com/inward/record.url?scp=67651051867&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2009.05.029

DO - 10.1016/j.neuroimage.2009.05.029

M3 - Article

VL - 47

SP - 1435

EP - 1447

JO - NeuroImage

T2 - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -

Babalola KO, Patenaude B, Aljabar P, Schnabel J, Kennedy D, Crum W et al. An evaluation of four automatic methods of segmenting the subcortical structures in the brain. NeuroImage. 2009 Oct 1;47(4):1435-1447. https://doi.org/10.1016/j.neuroimage.2009.05.029