Neonatal brain tissue classification with morphological adaptation and unified segmentation

Richard J. Beare, Jian Chen, Claire E. Kelly, Dimitrios Alexopoulos, Christopher D. Smyser, Cynthia E. Rogers, Wai Y. Loh, Lillian G. Matthews, Jeanie L Y Cheong, Alicia J. Spittle, Peter J. Anderson, Lex W. Doyle, Terrie E. Inder, Marc L. Seal, Deanne K. Thompson

Research output: Contribution to journalArticleOtherpeer-review

Abstract

Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal T2-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (n = 5), coronal T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5) and axial T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of T2-weighted images of preterm infants (born <30 weeks' gestation) acquired shortly after birth (n = 12), preterm infants acquired at term-equivalent age (n = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (n = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from http://developmentalimagingmcri.github.io/mantis

Original languageEnglish
Article number12
Number of pages17
JournalFrontiers in Neuroinformatics
Volume10
DOIs
Publication statusPublished - 29 Mar 2016

Keywords

  • Magnetic resonance imaging
  • Neonate
  • Preterm birth
  • Statistical parametric mapping
  • Tissue classification

Cite this

Beare, R. J., Chen, J., Kelly, C. E., Alexopoulos, D., Smyser, C. D., Rogers, C. E., ... Thompson, D. K. (2016). Neonatal brain tissue classification with morphological adaptation and unified segmentation. Frontiers in Neuroinformatics, 10, [12]. https://doi.org/10.3389/fninf.2016.00012
Beare, Richard J. ; Chen, Jian ; Kelly, Claire E. ; Alexopoulos, Dimitrios ; Smyser, Christopher D. ; Rogers, Cynthia E. ; Loh, Wai Y. ; Matthews, Lillian G. ; Cheong, Jeanie L Y ; Spittle, Alicia J. ; Anderson, Peter J. ; Doyle, Lex W. ; Inder, Terrie E. ; Seal, Marc L. ; Thompson, Deanne K. / Neonatal brain tissue classification with morphological adaptation and unified segmentation. In: Frontiers in Neuroinformatics. 2016 ; Vol. 10.
@article{55361381a4ea4454bdf16a330b9c5c44,
title = "Neonatal brain tissue classification with morphological adaptation and unified segmentation",
abstract = "Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal T2-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (n = 5), coronal T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5) and axial T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of T2-weighted images of preterm infants (born <30 weeks' gestation) acquired shortly after birth (n = 12), preterm infants acquired at term-equivalent age (n = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (n = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from http://developmentalimagingmcri.github.io/mantis",
keywords = "Magnetic resonance imaging, Neonate, Preterm birth, Statistical parametric mapping, Tissue classification",
author = "Beare, {Richard J.} and Jian Chen and Kelly, {Claire E.} and Dimitrios Alexopoulos and Smyser, {Christopher D.} and Rogers, {Cynthia E.} and Loh, {Wai Y.} and Matthews, {Lillian G.} and Cheong, {Jeanie L Y} and Spittle, {Alicia J.} and Anderson, {Peter J.} and Doyle, {Lex W.} and Inder, {Terrie E.} and Seal, {Marc L.} and Thompson, {Deanne K.}",
year = "2016",
month = "3",
day = "29",
doi = "10.3389/fninf.2016.00012",
language = "English",
volume = "10",
journal = "Frontiers in Neuroinformatics",
issn = "1662-5196",
publisher = "Frontiers Media",

}

Beare, RJ, Chen, J, Kelly, CE, Alexopoulos, D, Smyser, CD, Rogers, CE, Loh, WY, Matthews, LG, Cheong, JLY, Spittle, AJ, Anderson, PJ, Doyle, LW, Inder, TE, Seal, ML & Thompson, DK 2016, 'Neonatal brain tissue classification with morphological adaptation and unified segmentation' Frontiers in Neuroinformatics, vol. 10, 12. https://doi.org/10.3389/fninf.2016.00012

Neonatal brain tissue classification with morphological adaptation and unified segmentation. / Beare, Richard J.; Chen, Jian; Kelly, Claire E.; Alexopoulos, Dimitrios; Smyser, Christopher D.; Rogers, Cynthia E.; Loh, Wai Y.; Matthews, Lillian G.; Cheong, Jeanie L Y; Spittle, Alicia J.; Anderson, Peter J.; Doyle, Lex W.; Inder, Terrie E.; Seal, Marc L.; Thompson, Deanne K.

In: Frontiers in Neuroinformatics, Vol. 10, 12, 29.03.2016.

Research output: Contribution to journalArticleOtherpeer-review

TY - JOUR

T1 - Neonatal brain tissue classification with morphological adaptation and unified segmentation

AU - Beare, Richard J.

AU - Chen, Jian

AU - Kelly, Claire E.

AU - Alexopoulos, Dimitrios

AU - Smyser, Christopher D.

AU - Rogers, Cynthia E.

AU - Loh, Wai Y.

AU - Matthews, Lillian G.

AU - Cheong, Jeanie L Y

AU - Spittle, Alicia J.

AU - Anderson, Peter J.

AU - Doyle, Lex W.

AU - Inder, Terrie E.

AU - Seal, Marc L.

AU - Thompson, Deanne K.

PY - 2016/3/29

Y1 - 2016/3/29

N2 - Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal T2-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (n = 5), coronal T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5) and axial T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of T2-weighted images of preterm infants (born <30 weeks' gestation) acquired shortly after birth (n = 12), preterm infants acquired at term-equivalent age (n = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (n = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from http://developmentalimagingmcri.github.io/mantis

AB - Measuring the distribution of brain tissue types (tissue classification) in neonates is necessary for studying typical and atypical brain development, such as that associated with preterm birth, and may provide biomarkers for neurodevelopmental outcomes. Compared with magnetic resonance images of adults, neonatal images present specific challenges that require the development of specialized, population-specific methods. This paper introduces MANTiS (Morphologically Adaptive Neonatal Tissue Segmentation), which extends the unified segmentation approach to tissue classification implemented in Statistical Parametric Mapping (SPM) software to neonates. MANTiS utilizes a combination of unified segmentation, template adaptation via morphological segmentation tools and topological filtering, to segment the neonatal brain into eight tissue classes: cortical gray matter, white matter, deep nuclear gray matter, cerebellum, brainstem, cerebrospinal fluid (CSF), hippocampus and amygdala. We evaluated the performance of MANTiS using two independent datasets. The first dataset, provided by the NeoBrainS12 challenge, consisted of coronal T2-weighted images of preterm infants (born ≤30 weeks' gestation) acquired at 30 weeks' corrected gestational age (n = 5), coronal T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5) and axial T2-weighted images of preterm infants acquired at 40 weeks' corrected gestational age (n = 5). The second dataset, provided by the Washington University NeuroDevelopmental Research (WUNDeR) group, consisted of T2-weighted images of preterm infants (born <30 weeks' gestation) acquired shortly after birth (n = 12), preterm infants acquired at term-equivalent age (n = 12), and healthy term-born infants (born ≥38 weeks' gestation) acquired within the first 9 days of life (n = 12). For the NeoBrainS12 dataset, mean Dice scores comparing MANTiS with manual segmentations were all above 0.7, except for the cortical gray matter for coronal images acquired at 30 weeks. This demonstrates that MANTiS' performance is competitive with existing techniques. For the WUNDeR dataset, mean Dice scores comparing MANTiS with manually edited segmentations demonstrated good agreement, where all scores were above 0.75, except for the hippocampus and amygdala. The results show that MANTiS is able to segment neonatal brain tissues well, even in images that have brain abnormalities common in preterm infants. MANTiS is available for download as an SPM toolbox from http://developmentalimagingmcri.github.io/mantis

KW - Magnetic resonance imaging

KW - Neonate

KW - Preterm birth

KW - Statistical parametric mapping

KW - Tissue classification

UR - http://www.scopus.com/inward/record.url?scp=84961905770&partnerID=8YFLogxK

U2 - 10.3389/fninf.2016.00012

DO - 10.3389/fninf.2016.00012

M3 - Article

VL - 10

JO - Frontiers in Neuroinformatics

JF - Frontiers in Neuroinformatics

SN - 1662-5196

M1 - 12

ER -