Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases

Guray Erus, Jimit Doshi, Yang An, Dimitris Verganelakis, Susan M. Resnick, Christos Davatzikos

Research output: Research - peer-reviewArticle

Abstract

As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.

LanguageEnglish (US)
Pages71-78
Number of pages8
JournalNeuroImage
Volume166
DOIs
StatePublished - Feb 1 2018

Fingerprint

Atlases
Anatomy
Brain
Longitudinal Studies
Baltimore
Neuroimaging
Cross-Sectional Studies
White Matter
Datasets

Keywords

  • Longitudinal
  • MRI
  • Multi-atlas segmentation
  • Protocol differences
  • ROI
  • Scanner

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases. / Erus, Guray; Doshi, Jimit; An, Yang; Verganelakis, Dimitris; Resnick, Susan M.; Davatzikos, Christos.

In: NeuroImage, Vol. 166, 01.02.2018, p. 71-78.

Research output: Research - peer-reviewArticle

Erus, Guray ; Doshi, Jimit ; An, Yang ; Verganelakis, Dimitris ; Resnick, Susan M. ; Davatzikos, Christos. / Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases. In: NeuroImage. 2018 ; Vol. 166. pp. 71-78
@article{eb3b184fa7b1439bbd0a4290f19076bb,
title = "Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases",
abstract = "As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.",
keywords = "Longitudinal, MRI, Multi-atlas segmentation, Protocol differences, ROI, Scanner",
author = "Guray Erus and Jimit Doshi and Yang An and Dimitris Verganelakis and Resnick, {Susan M.} and Christos Davatzikos",
year = "2018",
month = "2",
doi = "10.1016/j.neuroimage.2017.10.026",
volume = "166",
pages = "71--78",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Longitudinally and inter-site consistent multi-atlas based parcellation of brain anatomy using harmonized atlases

AU - Erus,Guray

AU - Doshi,Jimit

AU - An,Yang

AU - Verganelakis,Dimitris

AU - Resnick,Susan M.

AU - Davatzikos,Christos

PY - 2018/2/1

Y1 - 2018/2/1

N2 - As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.

AB - As longitudinal and multi-site studies become increasingly frequent in neuroimaging, maintaining longitudinal and inter-scanner consistency of brain parcellation has become a major challenge due to variation in scanner models and/or image acquisition protocols across scanners and sites. We present a new automated segmentation method specifically designed to achieve a consistent parcellation of anatomical brain structures in such heterogeneous datasets. Our method combines a site-specific atlas creation strategy with a state-of-the-art multi-atlas anatomical label fusion framework. Site-specific atlases are computed such that they preserve image intensity characteristics of each site's scanner and acquisition protocol, while atlas pairs share anatomical labels in a way consistent with inter-scanner acquisition variations. This harmonization of atlases improves inter-study and longitudinal consistency of segmentations in the subsequent consensus labeling step. We tested this approach on a large sample of older adults from the Baltimore Longitudinal Study of Aging (BLSA) who had longitudinal scans acquired using two scanners that vary with respect to vendor and image acquisition protocol. We compared the proposed method to standard multi-atlas segmentation for both cross-sectional and longitudinal analyses. The harmonization significantly reduced scanner-related differences in the age trends of ROI volumes, improved longitudinal consistency of segmentations, and resulted in higher across-scanner intra-class correlations, particularly in the white matter.

KW - Longitudinal

KW - MRI

KW - Multi-atlas segmentation

KW - Protocol differences

KW - ROI

KW - Scanner

UR - http://www.scopus.com/inward/record.url?scp=85032702105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032702105&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2017.10.026

DO - 10.1016/j.neuroimage.2017.10.026

M3 - Article

VL - 166

SP - 71

EP - 78

JO - NeuroImage

T2 - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -