Optimum template selection for atlas-based segmentation

Minjie Wu, Caterina Rosano, Pilar Lopez-Garcia, Cameron S Carter, Howard J. Aizenstein

Research output: Contribution to journalArticle

97 Citations (Scopus)

Abstract

Atlas-based segmentation of MR brain images typically uses a single atlas (e.g., MNI Colin27) for region identification. Normal individual variations in human brain structures present a significant challenge for atlas selection. Previous researches mainly focused on how to create a specific template for different requirements (e.g., for a certain population). We address atlas selection with a different approach: instead of choosing a fixed brain atlas, we use a family of brain templates for atlas-based segmentation. For each subject and each region, the template selection method automatically chooses the 'best' template with the highest local registration accuracy, based on normalized mutual information. The region classification performances of the template selection method and the single template method were quantified by the overlap ratios (ORs) and intraclass correlation coefficients (ICCs) between the manual tracings and the respective automated labeled results. Two groups of brain images and multiple regions of interest (ROIs), including the right anterior cingulate cortex (ACC) and several subcortical structures, were tested for both methods. We found that the template selection method produced significantly higher ORs than did the single template method across all of the 13 analyzed ROIs (two-tailed paired t-test, right ACC at t(8) = 4.353, p = 0.0024; right amygdala, matched paired t test t(8) > 3.175, p < 0.013; for the remaining ROIs, t(8) = 4.36, p < 0.002). The template selection method also provided more reliable volume estimates than the single template method with increased ICCs. Moreover, the improved accuracy of atlas-based segmentation using optimum templates approaches the accuracy of manual tracing, and thus is valid for automated brain imaging analyses.

Original languageEnglish (US)
Pages (from-to)1612-1618
Number of pages7
JournalNeuroImage
Volume34
Issue number4
DOIs
StatePublished - Feb 15 2007

Fingerprint

Atlases
Brain
Gyrus Cinguli
Amygdala
Neuroimaging
Research

Keywords

  • Atlas-based segmentation
  • Template selection

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Wu, M., Rosano, C., Lopez-Garcia, P., Carter, C. S., & Aizenstein, H. J. (2007). Optimum template selection for atlas-based segmentation. NeuroImage, 34(4), 1612-1618. https://doi.org/10.1016/j.neuroimage.2006.07.050

Optimum template selection for atlas-based segmentation. / Wu, Minjie; Rosano, Caterina; Lopez-Garcia, Pilar; Carter, Cameron S; Aizenstein, Howard J.

In: NeuroImage, Vol. 34, No. 4, 15.02.2007, p. 1612-1618.

Research output: Contribution to journalArticle

Wu, M, Rosano, C, Lopez-Garcia, P, Carter, CS & Aizenstein, HJ 2007, 'Optimum template selection for atlas-based segmentation', NeuroImage, vol. 34, no. 4, pp. 1612-1618. https://doi.org/10.1016/j.neuroimage.2006.07.050
Wu, Minjie ; Rosano, Caterina ; Lopez-Garcia, Pilar ; Carter, Cameron S ; Aizenstein, Howard J. / Optimum template selection for atlas-based segmentation. In: NeuroImage. 2007 ; Vol. 34, No. 4. pp. 1612-1618.
@article{73130ac183f4480ba9d5a477c4cd36e2,
title = "Optimum template selection for atlas-based segmentation",
abstract = "Atlas-based segmentation of MR brain images typically uses a single atlas (e.g., MNI Colin27) for region identification. Normal individual variations in human brain structures present a significant challenge for atlas selection. Previous researches mainly focused on how to create a specific template for different requirements (e.g., for a certain population). We address atlas selection with a different approach: instead of choosing a fixed brain atlas, we use a family of brain templates for atlas-based segmentation. For each subject and each region, the template selection method automatically chooses the 'best' template with the highest local registration accuracy, based on normalized mutual information. The region classification performances of the template selection method and the single template method were quantified by the overlap ratios (ORs) and intraclass correlation coefficients (ICCs) between the manual tracings and the respective automated labeled results. Two groups of brain images and multiple regions of interest (ROIs), including the right anterior cingulate cortex (ACC) and several subcortical structures, were tested for both methods. We found that the template selection method produced significantly higher ORs than did the single template method across all of the 13 analyzed ROIs (two-tailed paired t-test, right ACC at t(8) = 4.353, p = 0.0024; right amygdala, matched paired t test t(8) > 3.175, p < 0.013; for the remaining ROIs, t(8) = 4.36, p < 0.002). The template selection method also provided more reliable volume estimates than the single template method with increased ICCs. Moreover, the improved accuracy of atlas-based segmentation using optimum templates approaches the accuracy of manual tracing, and thus is valid for automated brain imaging analyses.",
keywords = "Atlas-based segmentation, Template selection",
author = "Minjie Wu and Caterina Rosano and Pilar Lopez-Garcia and Carter, {Cameron S} and Aizenstein, {Howard J.}",
year = "2007",
month = "2",
day = "15",
doi = "10.1016/j.neuroimage.2006.07.050",
language = "English (US)",
volume = "34",
pages = "1612--1618",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "4",

}

TY - JOUR

T1 - Optimum template selection for atlas-based segmentation

AU - Wu, Minjie

AU - Rosano, Caterina

AU - Lopez-Garcia, Pilar

AU - Carter, Cameron S

AU - Aizenstein, Howard J.

PY - 2007/2/15

Y1 - 2007/2/15

N2 - Atlas-based segmentation of MR brain images typically uses a single atlas (e.g., MNI Colin27) for region identification. Normal individual variations in human brain structures present a significant challenge for atlas selection. Previous researches mainly focused on how to create a specific template for different requirements (e.g., for a certain population). We address atlas selection with a different approach: instead of choosing a fixed brain atlas, we use a family of brain templates for atlas-based segmentation. For each subject and each region, the template selection method automatically chooses the 'best' template with the highest local registration accuracy, based on normalized mutual information. The region classification performances of the template selection method and the single template method were quantified by the overlap ratios (ORs) and intraclass correlation coefficients (ICCs) between the manual tracings and the respective automated labeled results. Two groups of brain images and multiple regions of interest (ROIs), including the right anterior cingulate cortex (ACC) and several subcortical structures, were tested for both methods. We found that the template selection method produced significantly higher ORs than did the single template method across all of the 13 analyzed ROIs (two-tailed paired t-test, right ACC at t(8) = 4.353, p = 0.0024; right amygdala, matched paired t test t(8) > 3.175, p < 0.013; for the remaining ROIs, t(8) = 4.36, p < 0.002). The template selection method also provided more reliable volume estimates than the single template method with increased ICCs. Moreover, the improved accuracy of atlas-based segmentation using optimum templates approaches the accuracy of manual tracing, and thus is valid for automated brain imaging analyses.

AB - Atlas-based segmentation of MR brain images typically uses a single atlas (e.g., MNI Colin27) for region identification. Normal individual variations in human brain structures present a significant challenge for atlas selection. Previous researches mainly focused on how to create a specific template for different requirements (e.g., for a certain population). We address atlas selection with a different approach: instead of choosing a fixed brain atlas, we use a family of brain templates for atlas-based segmentation. For each subject and each region, the template selection method automatically chooses the 'best' template with the highest local registration accuracy, based on normalized mutual information. The region classification performances of the template selection method and the single template method were quantified by the overlap ratios (ORs) and intraclass correlation coefficients (ICCs) between the manual tracings and the respective automated labeled results. Two groups of brain images and multiple regions of interest (ROIs), including the right anterior cingulate cortex (ACC) and several subcortical structures, were tested for both methods. We found that the template selection method produced significantly higher ORs than did the single template method across all of the 13 analyzed ROIs (two-tailed paired t-test, right ACC at t(8) = 4.353, p = 0.0024; right amygdala, matched paired t test t(8) > 3.175, p < 0.013; for the remaining ROIs, t(8) = 4.36, p < 0.002). The template selection method also provided more reliable volume estimates than the single template method with increased ICCs. Moreover, the improved accuracy of atlas-based segmentation using optimum templates approaches the accuracy of manual tracing, and thus is valid for automated brain imaging analyses.

KW - Atlas-based segmentation

KW - Template selection

UR - http://www.scopus.com/inward/record.url?scp=33846645990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846645990&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2006.07.050

DO - 10.1016/j.neuroimage.2006.07.050

M3 - Article

C2 - 17188896

AN - SCOPUS:33846645990

VL - 34

SP - 1612

EP - 1618

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 4

ER -