A new MRI-based pediatric subcortical segmentation technique (PSST)

Wai Yen Loh, Alan Connelly, Jeanie L Y Cheong, Alicia J. Spittle, Jian Chen, Christopher Adamson, Zohra M. Ahmadzai, Lillian Gabra Fam, Sandra Rees, Katherine J. Lee, Lex W. Doyle, Peter J. Anderson, Deanne K. Thompson

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Volumetric and morphometric neuroimaging studies of the basal ganglia and thalamus in pediatric populations have utilized existing automated segmentation tools including FIRST (Functional Magnetic Resonance Imaging of the Brain’s Integrated Registration and Segmentation Tool) and FreeSurfer. These segmentation packages, however, are mostly based on adult training data. Given that there are marked differences between the pediatric and adult brain, it is likely an age-specific segmentation technique will produce more accurate segmentation results. In this study, we describe a new automated segmentation technique for analysis of 7-year-old basal ganglia and thalamus, called Pediatric Subcortical Segmentation Technique (PSST). PSST consists of a probabilistic 7-year-old subcortical gray matter atlas (accumbens, caudate, pallidum, putamen and thalamus) combined with a customized segmentation pipeline using existing tools: ANTs (Advanced Normalization Tools) and SPM (Statistical Parametric Mapping). The segmentation accuracy of PSST in 7-year-old data was compared against FIRST and FreeSurfer, relative to manual segmentation as the ground truth, utilizing spatial overlap (Dice’s coefficient), volume correlation (intraclass correlation coefficient, ICC) and limits of agreement (Bland-Altman plots). PSST achieved spatial overlap scores ≥90 % and ICC scores ≥0.77 when compared with manual segmentation, for all structures except the accumbens. Compared with FIRST and FreeSurfer, PSST showed higher spatial overlap (pFDR < 0.05) and ICC scores, with less volumetric bias according to Bland-Altman plots. PSST is a customized segmentation pipeline with an age-specific atlas that accurately segments typical and atypical basal ganglia and thalami at age 7 years, and has the potential to be applied to other pediatric datasets.

Original languageEnglish
Pages (from-to)69-81
Number of pages13
JournalNeuroinformatics
Volume14
Issue number1
DOIs
Publication statusPublished - Jan 2016

Keywords

  • Basal ganglia
  • Magnetic resonance imaging
  • Pediatric
  • Segmentation
  • Subcortical
  • Thalamus

Cite this

Loh, W. Y., Connelly, A., Cheong, J. L. Y., Spittle, A. J., Chen, J., Adamson, C., ... Thompson, D. K. (2016). A new MRI-based pediatric subcortical segmentation technique (PSST). Neuroinformatics, 14(1), 69-81. https://doi.org/10.1007/s12021-015-9279-0
Loh, Wai Yen ; Connelly, Alan ; Cheong, Jeanie L Y ; Spittle, Alicia J. ; Chen, Jian ; Adamson, Christopher ; Ahmadzai, Zohra M. ; Fam, Lillian Gabra ; Rees, Sandra ; Lee, Katherine J. ; Doyle, Lex W. ; Anderson, Peter J. ; Thompson, Deanne K. / A new MRI-based pediatric subcortical segmentation technique (PSST). In: Neuroinformatics. 2016 ; Vol. 14, No. 1. pp. 69-81.
@article{10ba5d756a0b4fc3ba14a40450e87ed9,
title = "A new MRI-based pediatric subcortical segmentation technique (PSST)",
abstract = "Volumetric and morphometric neuroimaging studies of the basal ganglia and thalamus in pediatric populations have utilized existing automated segmentation tools including FIRST (Functional Magnetic Resonance Imaging of the Brain’s Integrated Registration and Segmentation Tool) and FreeSurfer. These segmentation packages, however, are mostly based on adult training data. Given that there are marked differences between the pediatric and adult brain, it is likely an age-specific segmentation technique will produce more accurate segmentation results. In this study, we describe a new automated segmentation technique for analysis of 7-year-old basal ganglia and thalamus, called Pediatric Subcortical Segmentation Technique (PSST). PSST consists of a probabilistic 7-year-old subcortical gray matter atlas (accumbens, caudate, pallidum, putamen and thalamus) combined with a customized segmentation pipeline using existing tools: ANTs (Advanced Normalization Tools) and SPM (Statistical Parametric Mapping). The segmentation accuracy of PSST in 7-year-old data was compared against FIRST and FreeSurfer, relative to manual segmentation as the ground truth, utilizing spatial overlap (Dice’s coefficient), volume correlation (intraclass correlation coefficient, ICC) and limits of agreement (Bland-Altman plots). PSST achieved spatial overlap scores ≥90 {\%} and ICC scores ≥0.77 when compared with manual segmentation, for all structures except the accumbens. Compared with FIRST and FreeSurfer, PSST showed higher spatial overlap (pFDR < 0.05) and ICC scores, with less volumetric bias according to Bland-Altman plots. PSST is a customized segmentation pipeline with an age-specific atlas that accurately segments typical and atypical basal ganglia and thalami at age 7 years, and has the potential to be applied to other pediatric datasets.",
keywords = "Basal ganglia, Magnetic resonance imaging, Pediatric, Segmentation, Subcortical, Thalamus",
author = "Loh, {Wai Yen} and Alan Connelly and Cheong, {Jeanie L Y} and Spittle, {Alicia J.} and Jian Chen and Christopher Adamson and Ahmadzai, {Zohra M.} and Fam, {Lillian Gabra} and Sandra Rees and Lee, {Katherine J.} and Doyle, {Lex W.} and Anderson, {Peter J.} and Thompson, {Deanne K.}",
year = "2016",
month = "1",
doi = "10.1007/s12021-015-9279-0",
language = "English",
volume = "14",
pages = "69--81",
journal = "Neuroinformatics",
issn = "1539-2791",
publisher = "Springer-Verlag London Ltd.",
number = "1",

}

Loh, WY, Connelly, A, Cheong, JLY, Spittle, AJ, Chen, J, Adamson, C, Ahmadzai, ZM, Fam, LG, Rees, S, Lee, KJ, Doyle, LW, Anderson, PJ & Thompson, DK 2016, 'A new MRI-based pediatric subcortical segmentation technique (PSST)' Neuroinformatics, vol. 14, no. 1, pp. 69-81. https://doi.org/10.1007/s12021-015-9279-0

A new MRI-based pediatric subcortical segmentation technique (PSST). / Loh, Wai Yen; Connelly, Alan; Cheong, Jeanie L Y; Spittle, Alicia J.; Chen, Jian; Adamson, Christopher; Ahmadzai, Zohra M.; Fam, Lillian Gabra; Rees, Sandra; Lee, Katherine J.; Doyle, Lex W.; Anderson, Peter J.; Thompson, Deanne K.

In: Neuroinformatics, Vol. 14, No. 1, 01.2016, p. 69-81.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A new MRI-based pediatric subcortical segmentation technique (PSST)

AU - Loh, Wai Yen

AU - Connelly, Alan

AU - Cheong, Jeanie L Y

AU - Spittle, Alicia J.

AU - Chen, Jian

AU - Adamson, Christopher

AU - Ahmadzai, Zohra M.

AU - Fam, Lillian Gabra

AU - Rees, Sandra

AU - Lee, Katherine J.

AU - Doyle, Lex W.

AU - Anderson, Peter J.

AU - Thompson, Deanne K.

PY - 2016/1

Y1 - 2016/1

N2 - Volumetric and morphometric neuroimaging studies of the basal ganglia and thalamus in pediatric populations have utilized existing automated segmentation tools including FIRST (Functional Magnetic Resonance Imaging of the Brain’s Integrated Registration and Segmentation Tool) and FreeSurfer. These segmentation packages, however, are mostly based on adult training data. Given that there are marked differences between the pediatric and adult brain, it is likely an age-specific segmentation technique will produce more accurate segmentation results. In this study, we describe a new automated segmentation technique for analysis of 7-year-old basal ganglia and thalamus, called Pediatric Subcortical Segmentation Technique (PSST). PSST consists of a probabilistic 7-year-old subcortical gray matter atlas (accumbens, caudate, pallidum, putamen and thalamus) combined with a customized segmentation pipeline using existing tools: ANTs (Advanced Normalization Tools) and SPM (Statistical Parametric Mapping). The segmentation accuracy of PSST in 7-year-old data was compared against FIRST and FreeSurfer, relative to manual segmentation as the ground truth, utilizing spatial overlap (Dice’s coefficient), volume correlation (intraclass correlation coefficient, ICC) and limits of agreement (Bland-Altman plots). PSST achieved spatial overlap scores ≥90 % and ICC scores ≥0.77 when compared with manual segmentation, for all structures except the accumbens. Compared with FIRST and FreeSurfer, PSST showed higher spatial overlap (pFDR < 0.05) and ICC scores, with less volumetric bias according to Bland-Altman plots. PSST is a customized segmentation pipeline with an age-specific atlas that accurately segments typical and atypical basal ganglia and thalami at age 7 years, and has the potential to be applied to other pediatric datasets.

AB - Volumetric and morphometric neuroimaging studies of the basal ganglia and thalamus in pediatric populations have utilized existing automated segmentation tools including FIRST (Functional Magnetic Resonance Imaging of the Brain’s Integrated Registration and Segmentation Tool) and FreeSurfer. These segmentation packages, however, are mostly based on adult training data. Given that there are marked differences between the pediatric and adult brain, it is likely an age-specific segmentation technique will produce more accurate segmentation results. In this study, we describe a new automated segmentation technique for analysis of 7-year-old basal ganglia and thalamus, called Pediatric Subcortical Segmentation Technique (PSST). PSST consists of a probabilistic 7-year-old subcortical gray matter atlas (accumbens, caudate, pallidum, putamen and thalamus) combined with a customized segmentation pipeline using existing tools: ANTs (Advanced Normalization Tools) and SPM (Statistical Parametric Mapping). The segmentation accuracy of PSST in 7-year-old data was compared against FIRST and FreeSurfer, relative to manual segmentation as the ground truth, utilizing spatial overlap (Dice’s coefficient), volume correlation (intraclass correlation coefficient, ICC) and limits of agreement (Bland-Altman plots). PSST achieved spatial overlap scores ≥90 % and ICC scores ≥0.77 when compared with manual segmentation, for all structures except the accumbens. Compared with FIRST and FreeSurfer, PSST showed higher spatial overlap (pFDR < 0.05) and ICC scores, with less volumetric bias according to Bland-Altman plots. PSST is a customized segmentation pipeline with an age-specific atlas that accurately segments typical and atypical basal ganglia and thalami at age 7 years, and has the potential to be applied to other pediatric datasets.

KW - Basal ganglia

KW - Magnetic resonance imaging

KW - Pediatric

KW - Segmentation

KW - Subcortical

KW - Thalamus

UR - http://www.scopus.com/inward/record.url?scp=84953835083&partnerID=8YFLogxK

U2 - 10.1007/s12021-015-9279-0

DO - 10.1007/s12021-015-9279-0

M3 - Article

VL - 14

SP - 69

EP - 81

JO - Neuroinformatics

JF - Neuroinformatics

SN - 1539-2791

IS - 1

ER -

Loh WY, Connelly A, Cheong JLY, Spittle AJ, Chen J, Adamson C et al. A new MRI-based pediatric subcortical segmentation technique (PSST). Neuroinformatics. 2016 Jan;14(1):69-81. https://doi.org/10.1007/s12021-015-9279-0