Spinal cord grey matter segmentation challenge

Ferran Prados, John Ashburner, Claudia Blaiotta, Tom Brosch, Julio Carballido-Gamio, Manuel Jorge Cardoso, Benjamin N. Conrad, Esha Datta, Gergely Dávid, Benjamin De Leener, Sara M. Dupont, Patrick Freund, Claudia A.M.Gandini Wheeler-Kingshott, Francesco Grussu, Roland Henry, Bennett A. Landman, Emil Ljungberg, Bailey Lyttle, Sebastien Ourselin, Nico Papinutto & 8 others Salvatore Saporito, Regina Schlaeger, Seth A. Smith, Paul Summers, Roger Tam, Marios C. Yiannakas, Alyssa Zhu, Julien Cohen-Adad

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

An important image processing step in spinal cord magnetic resonance imaging is the ability to reliably and accurately segment grey and white matter for tissue specific analysis. There are several semi- or fully-automated segmentation methods for cervical cord cross-sectional area measurement with an excellent performance close or equal to the manual segmentation. However, grey matter segmentation is still challenging due to small cross-sectional size and shape, and active research is being conducted by several groups around the world in this field. Therefore a grey matter spinal cord segmentation challenge was organised to test different capabilities of various methods using the same multi-centre and multi-vendor dataset acquired with distinct 3D gradient-echo sequences. This challenge aimed to characterize the state-of-the-art in the field as well as identifying new opportunities for future improvements. Six different spinal cord grey matter segmentation methods developed independently by various research groups across the world and their performance were compared to manual segmentation outcomes, the present gold-standard. All algorithms provided good overall results for detecting the grey matter butterfly, albeit with variable performance in certain quality-of-segmentation metrics. The data have been made publicly available and the challenge web site remains open to new submissions. No modifications were introduced to any of the presented methods as a result of this challenge for the purposes of this publication.

Original languageEnglish
Pages (from-to)312-329
Number of pages18
JournalNeuroImage
Volume152
DOIs
Publication statusPublished - May 15 2017

Fingerprint

Spinal Cord
Butterflies
Research
Gold
Magnetic Resonance Imaging
Gray Matter

Keywords

  • Challenge
  • Evaluation metrics
  • Grey matter
  • MRI
  • Segmentation
  • Spinal cord

ASJC Scopus subject areas

  • Neurology
  • Cognitive Neuroscience

Cite this

Prados, F., Ashburner, J., Blaiotta, C., Brosch, T., Carballido-Gamio, J., Cardoso, M. J., ... Cohen-Adad, J. (2017). Spinal cord grey matter segmentation challenge. NeuroImage, 152, 312-329. https://doi.org/10.1016/j.neuroimage.2017.03.010

Spinal cord grey matter segmentation challenge. / Prados, Ferran; Ashburner, John; Blaiotta, Claudia; Brosch, Tom; Carballido-Gamio, Julio; Cardoso, Manuel Jorge; Conrad, Benjamin N.; Datta, Esha; Dávid, Gergely; Leener, Benjamin De; Dupont, Sara M.; Freund, Patrick; Wheeler-Kingshott, Claudia A.M.Gandini; Grussu, Francesco; Henry, Roland; Landman, Bennett A.; Ljungberg, Emil; Lyttle, Bailey; Ourselin, Sebastien; Papinutto, Nico; Saporito, Salvatore; Schlaeger, Regina; Smith, Seth A.; Summers, Paul; Tam, Roger; Yiannakas, Marios C.; Zhu, Alyssa; Cohen-Adad, Julien.

In: NeuroImage, Vol. 152, 15.05.2017, p. 312-329.

Research output: Contribution to journalArticle

Prados, F, Ashburner, J, Blaiotta, C, Brosch, T, Carballido-Gamio, J, Cardoso, MJ, Conrad, BN, Datta, E, Dávid, G, Leener, BD, Dupont, SM, Freund, P, Wheeler-Kingshott, CAMG, Grussu, F, Henry, R, Landman, BA, Ljungberg, E, Lyttle, B, Ourselin, S, Papinutto, N, Saporito, S, Schlaeger, R, Smith, SA, Summers, P, Tam, R, Yiannakas, MC, Zhu, A & Cohen-Adad, J 2017, 'Spinal cord grey matter segmentation challenge', NeuroImage, vol. 152, pp. 312-329. https://doi.org/10.1016/j.neuroimage.2017.03.010
Prados F, Ashburner J, Blaiotta C, Brosch T, Carballido-Gamio J, Cardoso MJ et al. Spinal cord grey matter segmentation challenge. NeuroImage. 2017 May 15;152:312-329. https://doi.org/10.1016/j.neuroimage.2017.03.010
Prados, Ferran ; Ashburner, John ; Blaiotta, Claudia ; Brosch, Tom ; Carballido-Gamio, Julio ; Cardoso, Manuel Jorge ; Conrad, Benjamin N. ; Datta, Esha ; Dávid, Gergely ; Leener, Benjamin De ; Dupont, Sara M. ; Freund, Patrick ; Wheeler-Kingshott, Claudia A.M.Gandini ; Grussu, Francesco ; Henry, Roland ; Landman, Bennett A. ; Ljungberg, Emil ; Lyttle, Bailey ; Ourselin, Sebastien ; Papinutto, Nico ; Saporito, Salvatore ; Schlaeger, Regina ; Smith, Seth A. ; Summers, Paul ; Tam, Roger ; Yiannakas, Marios C. ; Zhu, Alyssa ; Cohen-Adad, Julien. / Spinal cord grey matter segmentation challenge. In: NeuroImage. 2017 ; Vol. 152. pp. 312-329.
@article{1a9fb18da73046bfb0244a86a235f7e2,
title = "Spinal cord grey matter segmentation challenge",
abstract = "An important image processing step in spinal cord magnetic resonance imaging is the ability to reliably and accurately segment grey and white matter for tissue specific analysis. There are several semi- or fully-automated segmentation methods for cervical cord cross-sectional area measurement with an excellent performance close or equal to the manual segmentation. However, grey matter segmentation is still challenging due to small cross-sectional size and shape, and active research is being conducted by several groups around the world in this field. Therefore a grey matter spinal cord segmentation challenge was organised to test different capabilities of various methods using the same multi-centre and multi-vendor dataset acquired with distinct 3D gradient-echo sequences. This challenge aimed to characterize the state-of-the-art in the field as well as identifying new opportunities for future improvements. Six different spinal cord grey matter segmentation methods developed independently by various research groups across the world and their performance were compared to manual segmentation outcomes, the present gold-standard. All algorithms provided good overall results for detecting the grey matter butterfly, albeit with variable performance in certain quality-of-segmentation metrics. The data have been made publicly available and the challenge web site remains open to new submissions. No modifications were introduced to any of the presented methods as a result of this challenge for the purposes of this publication.",
keywords = "Challenge, Evaluation metrics, Grey matter, MRI, Segmentation, Spinal cord",
author = "Ferran Prados and John Ashburner and Claudia Blaiotta and Tom Brosch and Julio Carballido-Gamio and Cardoso, {Manuel Jorge} and Conrad, {Benjamin N.} and Esha Datta and Gergely D{\'a}vid and Leener, {Benjamin De} and Dupont, {Sara M.} and Patrick Freund and Wheeler-Kingshott, {Claudia A.M.Gandini} and Francesco Grussu and Roland Henry and Landman, {Bennett A.} and Emil Ljungberg and Bailey Lyttle and Sebastien Ourselin and Nico Papinutto and Salvatore Saporito and Regina Schlaeger and Smith, {Seth A.} and Paul Summers and Roger Tam and Yiannakas, {Marios C.} and Alyssa Zhu and Julien Cohen-Adad",
year = "2017",
month = "5",
day = "15",
doi = "10.1016/j.neuroimage.2017.03.010",
language = "English",
volume = "152",
pages = "312--329",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Spinal cord grey matter segmentation challenge

AU - Prados, Ferran

AU - Ashburner, John

AU - Blaiotta, Claudia

AU - Brosch, Tom

AU - Carballido-Gamio, Julio

AU - Cardoso, Manuel Jorge

AU - Conrad, Benjamin N.

AU - Datta, Esha

AU - Dávid, Gergely

AU - Leener, Benjamin De

AU - Dupont, Sara M.

AU - Freund, Patrick

AU - Wheeler-Kingshott, Claudia A.M.Gandini

AU - Grussu, Francesco

AU - Henry, Roland

AU - Landman, Bennett A.

AU - Ljungberg, Emil

AU - Lyttle, Bailey

AU - Ourselin, Sebastien

AU - Papinutto, Nico

AU - Saporito, Salvatore

AU - Schlaeger, Regina

AU - Smith, Seth A.

AU - Summers, Paul

AU - Tam, Roger

AU - Yiannakas, Marios C.

AU - Zhu, Alyssa

AU - Cohen-Adad, Julien

PY - 2017/5/15

Y1 - 2017/5/15

N2 - An important image processing step in spinal cord magnetic resonance imaging is the ability to reliably and accurately segment grey and white matter for tissue specific analysis. There are several semi- or fully-automated segmentation methods for cervical cord cross-sectional area measurement with an excellent performance close or equal to the manual segmentation. However, grey matter segmentation is still challenging due to small cross-sectional size and shape, and active research is being conducted by several groups around the world in this field. Therefore a grey matter spinal cord segmentation challenge was organised to test different capabilities of various methods using the same multi-centre and multi-vendor dataset acquired with distinct 3D gradient-echo sequences. This challenge aimed to characterize the state-of-the-art in the field as well as identifying new opportunities for future improvements. Six different spinal cord grey matter segmentation methods developed independently by various research groups across the world and their performance were compared to manual segmentation outcomes, the present gold-standard. All algorithms provided good overall results for detecting the grey matter butterfly, albeit with variable performance in certain quality-of-segmentation metrics. The data have been made publicly available and the challenge web site remains open to new submissions. No modifications were introduced to any of the presented methods as a result of this challenge for the purposes of this publication.

AB - An important image processing step in spinal cord magnetic resonance imaging is the ability to reliably and accurately segment grey and white matter for tissue specific analysis. There are several semi- or fully-automated segmentation methods for cervical cord cross-sectional area measurement with an excellent performance close or equal to the manual segmentation. However, grey matter segmentation is still challenging due to small cross-sectional size and shape, and active research is being conducted by several groups around the world in this field. Therefore a grey matter spinal cord segmentation challenge was organised to test different capabilities of various methods using the same multi-centre and multi-vendor dataset acquired with distinct 3D gradient-echo sequences. This challenge aimed to characterize the state-of-the-art in the field as well as identifying new opportunities for future improvements. Six different spinal cord grey matter segmentation methods developed independently by various research groups across the world and their performance were compared to manual segmentation outcomes, the present gold-standard. All algorithms provided good overall results for detecting the grey matter butterfly, albeit with variable performance in certain quality-of-segmentation metrics. The data have been made publicly available and the challenge web site remains open to new submissions. No modifications were introduced to any of the presented methods as a result of this challenge for the purposes of this publication.

KW - Challenge

KW - Evaluation metrics

KW - Grey matter

KW - MRI

KW - Segmentation

KW - Spinal cord

UR - http://www.scopus.com/inward/record.url?scp=85014917868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014917868&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2017.03.010

DO - 10.1016/j.neuroimage.2017.03.010

M3 - Article

VL - 152

SP - 312

EP - 329

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -