Automatic spinal cord localization, robust to MRI contrasts using global curve optimization

•Automatic, fast and robust method to detect the center of the spinal cord on MRI data.•Machine learning based method followed by a global curve optimization.•Brain and spine regions are automatically separated at the pontomedullary junction.•Validation on 804 images, 4 contrasts, 20 centers, large...

Full description

Saved in:
Bibliographic Details
Published inMedical image analysis Vol. 44; pp. 215 - 227
Main Authors Gros, Charley, De Leener, Benjamin, Dupont, Sara M., Martin, Allan R., Fehlings, Michael G., Bakshi, Rohit, Tummala, Subhash, Auclair, Vincent, McLaren, Donald G., Callot, Virginie, Cohen-Adad, Julien, Sdika, Michaël
Format Journal Article
LanguageEnglish
Published Netherlands Elsevier B.V 01.02.2018
Elsevier BV
Elsevier
Subjects
Online AccessGet full text
ISSN1361-8415
1361-8423
1361-8431
1361-8423
DOI10.1016/j.media.2017.12.001

Cover

Abstract •Automatic, fast and robust method to detect the center of the spinal cord on MRI data.•Machine learning based method followed by a global curve optimization.•Brain and spine regions are automatically separated at the pontomedullary junction.•Validation on 804 images, 4 contrasts, 20 centers, large amount of patients.•Better results compared to a state-of-the-art technique. During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced. The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as “OptiC”, from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2∗-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions. Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth. Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases. [Display omitted]
AbstractList •Automatic, fast and robust method to detect the center of the spinal cord on MRI data.•Machine learning based method followed by a global curve optimization.•Brain and spine regions are automatically separated at the pontomedullary junction.•Validation on 804 images, 4 contrasts, 20 centers, large amount of patients.•Better results compared to a state-of-the-art technique. During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced. The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as “OptiC”, from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2∗-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions. Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth. Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases. [Display omitted]
During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced.The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as “OptiC”, from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2*-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions.Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth.Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases.
During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced. The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as "OptiC", from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2∗-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions. Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth. Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases.During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced. The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as "OptiC", from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2∗-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions. Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth. Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases.
During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced. The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as "OptiC", from a large dataset involving 20 centers, 4 contrasts (T -weighted n = 287, T -weighted n = 120, T -weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions. Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth. Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases.
During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as quantification of the spinal cord atrophy in various diseases. However, despite the significant improvement of MR sequences adapted to the spinal cord, automatic image processing tools for spinal cord MRI data are not yet as developed as for the brain. There is nonetheless great interest in fully automatic and fast processing methods to be able to propose quantitative analysis pipelines on large datasets without user bias. The first step of most of these analysis pipelines is to detect the spinal cord, which is challenging to achieve automatically across the broad range of MRI contrasts, field of view, resolutions and pathologies. In this paper, a fully automated, robust and fast method for detecting the spinal cord centerline on MRI volumes is introduced.The algorithm uses a global optimization scheme that attempts to strike a balance between a probabilistic localization map of the spinal cord center point and the overall spatial consistency of the spinal cord centerline (i.e. the rostro-caudal continuity of the spinal cord). Additionally, a new post-processing feature, which aims to automatically split brain and spine regions is introduced, to be able to detect a consistent spinal cord centerline, independently from the field of view. We present data on the validation of the proposed algorithm, known as “OptiC”, from a large dataset involving 20 centers, 4 contrasts (T2-weighted n = 287, T1-weighted n = 120, T2∗-weighted n = 307, diffusion-weighted n = 90), 501 subjects including 173 patients with a variety of neurologic diseases. Validation involved the gold-standard centerline coverage, the mean square error between the true and predicted centerlines and the ability to accurately separate brain and spine regions.Overall, OptiC was able to cover 98.77% of the gold-standard centerline, with a mean square error of 1.02 mm. OptiC achieved superior results compared to a state-of-the-art spinal cord localization technique based on the Hough transform, especially on pathological cases with an averaged mean square error of 1.08 mm vs. 13.16 mm (Wilcoxon signed-rank test p-value < .01). Images containing brain regions were identified with a 99% precision, on which brain and spine regions were separated with a distance error of 9.37 mm compared to ground-truth.Validation results on a challenging dataset suggest that OptiC could reliably be used for subsequent quantitative analyses tasks, opening the door to more robust analysis on pathological cases.
Author McLaren, Donald G.
Cohen-Adad, Julien
Bakshi, Rohit
Tummala, Subhash
Callot, Virginie
Dupont, Sara M.
Sdika, Michaël
Auclair, Vincent
Martin, Allan R.
De Leener, Benjamin
Fehlings, Michael G.
Gros, Charley
Author_xml – sequence: 1
  givenname: Charley
  surname: Gros
  fullname: Gros, Charley
  organization: NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
– sequence: 2
  givenname: Benjamin
  surname: De Leener
  fullname: De Leener, Benjamin
  organization: NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
– sequence: 3
  givenname: Sara M.
  surname: Dupont
  fullname: Dupont, Sara M.
  organization: NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
– sequence: 4
  givenname: Allan R.
  surname: Martin
  fullname: Martin, Allan R.
  organization: Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON, Canada
– sequence: 5
  givenname: Michael G.
  surname: Fehlings
  fullname: Fehlings, Michael G.
  organization: Division of Neurosurgery, Department of Surgery, University of Toronto, Toronto, ON, Canada
– sequence: 6
  givenname: Rohit
  surname: Bakshi
  fullname: Bakshi, Rohit
  organization: Laboratory for Neuroimaging Research, Ann Romney Center for Neurologic Diseases, Department of Neurology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
– sequence: 7
  givenname: Subhash
  surname: Tummala
  fullname: Tummala, Subhash
  organization: Laboratory for Neuroimaging Research, Ann Romney Center for Neurologic Diseases, Department of Neurology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
– sequence: 8
  givenname: Vincent
  surname: Auclair
  fullname: Auclair, Vincent
  organization: Biospective Inc., Montreal, QC, Canada
– sequence: 9
  givenname: Donald G.
  surname: McLaren
  fullname: McLaren, Donald G.
  organization: Biospective Inc., Montreal, QC, Canada
– sequence: 10
  givenname: Virginie
  surname: Callot
  fullname: Callot, Virginie
  organization: Aix Marseille Univ, CNRS, CRMBM, Marseille, France
– sequence: 11
  givenname: Julien
  surname: Cohen-Adad
  fullname: Cohen-Adad, Julien
  organization: NeuroPoly Lab, Institute of Biomedical Engineering, Polytechnique Montreal, Montreal, QC, Canada
– sequence: 12
  givenname: Michaël
  surname: Sdika
  fullname: Sdika, Michaël
  email: michael.sdika@creatis.insa-lyon.fr
  organization: Univ. Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, CREATIS UMR 5220, U1206, F-69100, Lyon, France
BackLink https://www.ncbi.nlm.nih.gov/pubmed/29288983$$D View this record in MEDLINE/PubMed
https://hal.science/hal-01690881$$DView record in HAL
BookMark eNqNkc1rFDEYh4NU7If-BYIMeFHojvnaSebgYSnaFlYE0ZOHkMkkNUtmMuZjpf71ZjprhR7UXBJenidv8ntPwdHoRw3AcwRrBFHzZlcPureyxhCxGuEaQvQInCDSoBWnmBzdn9H6GJzGuIMQMkrhE3CMW8x5y8kJ-LrJyQ8yWVXFyY7SVcqHvnJeSWd_lrofz6vguxxTlXz14dN1AcYUZEyxytGON9WN893s5bDXlZ-SHQ7iU_DYSBf1s8N-Br68f_f54mq1_Xh5fbHZrtSa4LTqcU-71jSM0X5NiYaqo6QrSyOoDUMdlabl2ijOGDdrw7FpjGoMZQ2FHafkDNDl3jxO8vaHdE5MwQ4y3AoExZyV2Im7rMSclUBYlKyK9nrRvsk_gpdWXG22Yq4VsYWco_3MvlrYKfjvWcckBhuVdk6O2ucoUMtxCR0RVtCXD9Cdz6EkG0t3BiklHJNCvThQuStPu-__ezIFIAuggo8xaPOff2ofWMqmu2GUkVn3D_ft4uoyq73VQURl9agKGLRKovf2r_4vmqDKqQ
CitedBy_id crossref_primary_10_1007_s10143_021_01624_z
crossref_primary_10_1016_j_nicl_2021_102849
crossref_primary_10_1016_j_nicl_2021_102766
crossref_primary_10_1002_jmri_27937
crossref_primary_10_3390_ijerph191811708
crossref_primary_10_1002_ima_22859
crossref_primary_10_1002_mrm_28665
crossref_primary_10_1007_s11655_023_3639_7
crossref_primary_10_1109_ACCESS_2024_3439892
crossref_primary_10_3174_ajnr_A6020
crossref_primary_10_1080_21681163_2022_2083018
crossref_primary_10_37349_etat_2023_00138
crossref_primary_10_1038_s41591_021_01663_5
crossref_primary_10_1109_ACCESS_2020_2993867
crossref_primary_10_1162_imag_a_00218
crossref_primary_10_1002_mrm_30475
crossref_primary_10_1016_j_neuroimage_2018_09_081
crossref_primary_10_1007_s10278_022_00637_4
crossref_primary_10_1002_acm2_14123
crossref_primary_10_1093_brain_awaa249
crossref_primary_10_1109_ACCESS_2019_2909583
crossref_primary_10_1038_s41596_021_00588_0
crossref_primary_10_1093_brain_awy352
crossref_primary_10_1007_s00415_023_11727_w
crossref_primary_10_1162_imag_a_00455
crossref_primary_10_3389_fnimg_2022_1031253
Cites_doi 10.3109/17482968.2012.701308
10.1016/j.neuroimage.2013.04.124
10.1007/s10439-007-9415-6
10.2307/1932409
10.1016/j.neuroimage.2011.09.015
10.1007/s00415-008-0545-z
10.1016/j.nicl.2015.11.001
10.1016/j.neuroimage.2014.04.051
10.1016/j.neuroimage.2009.12.121
10.3174/ajnr.A5162
10.1097/BRS.0000000000000125
10.1007/s10334-006-0052-0
10.1002/mrm.26354
10.1016/j.mri.2008.01.038
10.1371/journal.pone.0118576
10.1016/j.neuroimage.2010.11.089
10.1007/s10334-015-0507-2
10.1109/TMI.2015.2437192
10.1016/j.neuroimage.2013.07.060
10.1016/j.neuroimage.2016.10.009
10.1016/j.cviu.2007.09.014
10.3174/ajnr.A5163
10.1016/j.neuroimage.2016.09.026
10.1002/jmri.25622
10.1089/neu.2017.4980
ContentType Journal Article
Copyright 2017 Elsevier B.V.
Copyright © 2017 Elsevier B.V. All rights reserved.
Copyright Elsevier BV Feb 2018
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: 2017 Elsevier B.V.
– notice: Copyright © 2017 Elsevier B.V. All rights reserved.
– notice: Copyright Elsevier BV Feb 2018
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QO
8FD
FR3
K9.
NAPCQ
P64
7X8
1XC
VOOES
ADTOC
UNPAY
DOI 10.1016/j.media.2017.12.001
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Biotechnology Research Abstracts
Technology Research Database
Engineering Research Database
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
Hyper Article en Ligne (HAL)
Hyper Article en Ligne (HAL) (Open Access)
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Premium
Engineering Research Database
Biotechnology Research Abstracts
Technology Research Database
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitleList
ProQuest Health & Medical Complete (Alumni)
MEDLINE - Academic
MEDLINE

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Engineering
EISSN 1361-8423
EndPage 227
ExternalDocumentID oai:HAL:hal-01690881v1
29288983
10_1016_j_media_2017_12_001
S136184151730186X
Genre Validation Studies
Research Support, U.S. Gov't, Non-P.H.S
Research Support, Non-U.S. Gov't
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: CIHR
  grantid: FDN-143263
– fundername: NINDS NIH HHS
  grantid: R21 NS087465
– fundername: NEI NIH HHS
  grantid: R01 EY023240
– fundername: CIHR
  grantid: MOP-13034
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
29M
4.4
457
4G.
53G
5GY
5VS
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABBQC
ABJNI
ABLVK
ABMAC
ABMZM
ABXDB
ABYKQ
ACDAQ
ACGFS
ACIUM
ACIWK
ACNNM
ACPRK
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFRAH
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AJRQY
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ANZVX
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
BNPGV
C45
CAG
COF
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HVGLF
HX~
HZ~
IHE
J1W
JJJVA
KOM
LCYCR
M41
MO0
N9A
O-L
O9-
OAUVE
OVD
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SDP
SEL
SES
SEW
SPC
SPCBC
SSH
SST
SSV
SSZ
T5K
TEORI
UHS
~G-
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACIEU
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
CGR
CUY
CVF
ECM
EIF
NPM
7QO
8FD
FR3
K9.
NAPCQ
P64
7X8
1XC
VOOES
ADTOC
UNPAY
ID FETCH-LOGICAL-c532t-d2d4b9f6774d543e0cb43bbbbe10ef71b4af98efc8778f5f82f6fc6f47640b843
IEDL.DBID .~1
ISSN 1361-8415
1361-8423
1361-8431
IngestDate Sun Oct 26 03:49:18 EDT 2025
Tue Oct 14 20:38:34 EDT 2025
Sun Sep 28 09:25:16 EDT 2025
Tue Oct 07 06:48:46 EDT 2025
Thu Apr 03 07:09:25 EDT 2025
Thu Apr 24 23:05:13 EDT 2025
Wed Oct 29 21:17:55 EDT 2025
Fri Feb 23 02:28:19 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords HOG
Spinal cord
Segmentation
MRI
MS
ALS
SVM
PMJ
FOV
SYR
DCM
SC
NMO
Global optimization
(S-I) axis
Machine learning
SCI
HC
Detection
MSE
Spinal Cord
Language English
License Copyright © 2017 Elsevier B.V. All rights reserved.
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
other-oa
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c532t-d2d4b9f6774d543e0cb43bbbbe10ef71b4af98efc8778f5f82f6fc6f47640b843
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Undefined-3
ORCID 0000-0003-3662-9532
0000-0003-0850-1742
0000-0002-3129-6874
OpenAccessLink https://proxy.k.utb.cz/login?url=https://hal.science/hal-01690881
PMID 29288983
PQID 2070443823
PQPubID 2045428
PageCount 13
ParticipantIDs unpaywall_primary_10_1016_j_media_2017_12_001
hal_primary_oai_HAL_hal_01690881v1
proquest_miscellaneous_1982842137
proquest_journals_2070443823
pubmed_primary_29288983
crossref_primary_10_1016_j_media_2017_12_001
crossref_citationtrail_10_1016_j_media_2017_12_001
elsevier_sciencedirect_doi_10_1016_j_media_2017_12_001
PublicationCentury 2000
PublicationDate February 2018
2018-02-00
20180201
2018-02
PublicationDateYYYYMMDD 2018-02-01
PublicationDate_xml – month: 02
  year: 2018
  text: February 2018
PublicationDecade 2010
PublicationPlace Netherlands
PublicationPlace_xml – name: Netherlands
– name: Amsterdam
PublicationTitle Medical image analysis
PublicationTitleAlternate Med Image Anal
PublicationYear 2018
Publisher Elsevier B.V
Elsevier BV
Elsevier
Publisher_xml – name: Elsevier B.V
– name: Elsevier BV
– name: Elsevier
References Dupont, Leener, Taso, Troter, Nadeau, Stikov, Callot, Cohen-Adad (bib0015) 2017; 150
De Leener, Kadoury, Cohen-Adad (bib0010) 2014; 98
Martin, De Leener, Cohen-Adad, Cadotte, Kalsi-Ryan, Lange, Tetreault, Nouri, Crawley, Mikulis, Ginsberg (bib0025) 2017
Vannesjo, Shi, Tracey, Miller, Clare (bib0036) 2017
Cawley, Tur, Prados, Plantone, Kearney, Abdel-Aziz, Ourselin, Wheeler-Kingshott, Miller, Thompson, Ciccarelli (bib0004) 2017
De Leener, Taso, Cohen-Adad, Callot (bib0013) 2016; 29
Cohen-Adad, El Mendili, Lehéricy, Pradat, Blancho, Rossignol, Benali (bib0006) 2011; 55
Koh, Kim, Chaudhary, Dhillon (bib0022) 2010; 2010
Martin, De Leener, Cohen-Adad, Cadotte, Kalsi-Ryan, Lange, Tetreault, Nouri, Crawley, Mikulis (bib0024) 2017
Pezold, Fundana, Amann, Andelova, Pfister, Sprenger, Cattin (bib0029) 2015; 20
Nakamura, Miyazawa, Fujihara, Nakashima, Misu, Watanabe, Takahashi, Itoyama (bib0027) 2008; 255
Topfer, Starewicz, Lo, Metzemaekers, Jette, Hetherington, Stikov, Cohen-Adad (bib0035) 2016; 76
Bradski, Kaehler (bib0002) 2008
Meijster, Roerdink, Hesselink (bib0026) 2002; 18
Long, Shelhamer, Darrell (bib0023) 2015
De Leener, Cohen-Adad, Kadoury (bib0009) 2015; 34
Horsfield, Sala, Neema, Absinta, Bakshi, Sormani, Rocca, Bakshi, Filippi (bib0020) 2010; 50
Prados, Jorge Cardoso, Yiannakas, Hoy, Tebaldi, Kearney, Liechti (bib0031) 2016; 6
De Leener, Lévy, Dupont, Fonov, Stikov, Collins, Callot, Cohen-Adad (bib0011) 2017; 145
Jenkinson, Beckmann, Behrens, Woolrich, Smith (bib0021) 2012; 62
Chen, Carass, Oh, Nair, Pham, Reich, Prince (bib0005) 2013; 83
De Leener, Mangeat, Dupont, Martin, Callot, Stikov, Fehlings, Cohen-Adad (bib0012) 2017
Felzenszwalb, Huttenlocher (bib0017) 2004
Cohen-Adad, El Mendili, Morizot-Koutlidis, Lehéricy, Meininger, Blancho, Rossignol, Benali, Pradat (bib0007) 2013; 14
Bay, Ess, Tuytelaars, Gool (bib0001) 2008; 110
Ronneberger, Fischer, Brox (bib0032) 2015
Prados, Ashburner, Blaiotta, Brosch, Carballido-Gamio, Cardoso, Conrad (bib0030) 2017; 152
Fradet, Arnoux, Ranjeva, Petit, Callot (bib0018) 2014; 39
Grabher, Mohammadi, David, Freund (bib0019) 2017
Papinutto, Schlaeger, Panara, Zhu, Caverzasi, Stern, Hauser, Henry (bib0028) 2015; 10
Stroman, Wheeler-Kingshott, Bacon, Schwab, Bosma, Brooks, Cadotte (bib0034) 2014; 84
Ellingson, Ulmer, Schmit (bib0016) 2008; 36
Dalal, Triggs (bib0008) 2005; 1
Carbonell-Caballero, Manjón, Martí-Bonmatí, Olalla, Casanova, Iglesia-Vayá, Coret, Robles (bib0003) 2006; 19
Dice (bib0014) 1945; 26
Stroman, Figley, Cahill (bib0033) 2008; 26
Yiannakas, Mustafa, Leener, Kearney, Tur, Altmann, Angelis (bib0037) 2016; 10
Ronneberger (10.1016/j.media.2017.12.001_bib0032) 2015
Papinutto (10.1016/j.media.2017.12.001_bib0028) 2015; 10
Carbonell-Caballero (10.1016/j.media.2017.12.001_bib0003) 2006; 19
Cawley (10.1016/j.media.2017.12.001_bib0004) 2017
Martin (10.1016/j.media.2017.12.001_bib0024) 2017
Long (10.1016/j.media.2017.12.001_bib0023) 2015
Jenkinson (10.1016/j.media.2017.12.001_bib0021) 2012; 62
Chen (10.1016/j.media.2017.12.001_bib0005) 2013; 83
Vannesjo (10.1016/j.media.2017.12.001_bib0036) 2017
De Leener (10.1016/j.media.2017.12.001_bib0013) 2016; 29
Dupont (10.1016/j.media.2017.12.001_bib0015) 2017; 150
Prados (10.1016/j.media.2017.12.001_bib0030) 2017; 152
Stroman (10.1016/j.media.2017.12.001_bib0033) 2008; 26
Dalal (10.1016/j.media.2017.12.001_bib0008) 2005; 1
Ellingson (10.1016/j.media.2017.12.001_bib0016) 2008; 36
Felzenszwalb (10.1016/j.media.2017.12.001_bib0017) 2004
Martin (10.1016/j.media.2017.12.001_bib0025) 2017
Koh (10.1016/j.media.2017.12.001_bib0022) 2010; 2010
Horsfield (10.1016/j.media.2017.12.001_bib0020) 2010; 50
De Leener (10.1016/j.media.2017.12.001_bib0010) 2014; 98
Grabher (10.1016/j.media.2017.12.001_bib0019) 2017
Cohen-Adad (10.1016/j.media.2017.12.001_bib0006) 2011; 55
Yiannakas (10.1016/j.media.2017.12.001_bib0037) 2016; 10
Dice (10.1016/j.media.2017.12.001_bib0014) 1945; 26
Stroman (10.1016/j.media.2017.12.001_bib0034) 2014; 84
Nakamura (10.1016/j.media.2017.12.001_bib0027) 2008; 255
Pezold (10.1016/j.media.2017.12.001_bib0029) 2015; 20
Fradet (10.1016/j.media.2017.12.001_bib0018) 2014; 39
Bay (10.1016/j.media.2017.12.001_bib0001) 2008; 110
Cohen-Adad (10.1016/j.media.2017.12.001_bib0007) 2013; 14
De Leener (10.1016/j.media.2017.12.001_bib0012) 2017
De Leener (10.1016/j.media.2017.12.001_bib0009) 2015; 34
Prados (10.1016/j.media.2017.12.001_bib0031) 2016; 6
Topfer (10.1016/j.media.2017.12.001_bib0035) 2016; 76
De Leener (10.1016/j.media.2017.12.001_bib0011) 2017; 145
Bradski (10.1016/j.media.2017.12.001_bib0002) 2008
Meijster (10.1016/j.media.2017.12.001_bib0026) 2002; 18
References_xml – volume: 6
  year: 2016
  ident: bib0031
  article-title: Fully automated grey and white matter spinal cord segmentation
– year: 2015
  ident: bib0032
  article-title: U-Net: convolutional networks for biomedical image segmentation
  publication-title: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015
– volume: 26
  start-page: 297
  year: 1945
  end-page: 302
  ident: bib0014
  article-title: Measures of the amount of ecologic association between species
  publication-title: Ecology
– start-page: 3431
  year: 2015
  end-page: 3440
  ident: bib0023
  article-title: Fully convolutional networks for semantic segmentation
  publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
– volume: 255
  start-page: 163
  year: 2008
  end-page: 170
  ident: bib0027
  article-title: Preferential spinal central gray matter involvement in neuromyelitis optica
– volume: 55
  start-page: 1024
  year: 2011
  end-page: 1033
  ident: bib0006
  article-title: Demyelination and degeneration in the injured human spinal cord detected with diffusion and magnetization transfer MRI
  publication-title: NeuroImage
– volume: 36
  start-page: 224
  year: 2008
  end-page: 236
  ident: bib0016
  article-title: Morphology and morphometry of human chronic spinal cord injury using diffusion tensor imaging and fuzzy logic
– volume: 18
  start-page: 331
  year: 2002
  end-page: 340
  ident: bib0026
  article-title: A general algorithm for computing distance transforms in linear time
  publication-title: Mathematical Morphology and Its Applications to Image and Signal Processing
– year: 2017
  ident: bib0004
  article-title: Spinal cord atrophy as a primary outcome measure in phase II trials of progressive multiple sclerosis
  publication-title: Multiple Sclerosis
– volume: 84
  year: 2014
  ident: bib0034
  article-title: The current state-of-the-art of spinal cord imaging: methods
  publication-title: NeuroImage
– volume: 10
  year: 2015
  ident: bib0028
  article-title: Age, gender and normalization covariates for spinal cord gray matter and total cross-sectional areas at cervical and thoracic levels: a 2D phase sensitive inversion recovery imaging study
  publication-title: PloS One
– volume: 83
  start-page: 1051
  year: 2013
  end-page: 1062
  ident: bib0005
  article-title: Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view
  publication-title: NeuroImage
– volume: 98
  start-page: 528
  year: 2014
  end-page: 536
  ident: bib0010
  article-title: Robust, accurate and fast automatic segmentation of the spinal cord
  publication-title: NeuroImage
– volume: 20
  start-page: 107
  year: 2015
  end-page: 118
  ident: bib0029
  article-title: Automatic segmentation of the spinal cord using continuous max flow with cross-sectional similarity prior and tubularity features
  publication-title: Recent Advances in Computational Methods and Clinical Applications for Spine Imaging
– year: 2017
  ident: bib0012
  article-title: Topologically preserving straightening of spinal cord MRI
– volume: 10
  start-page: 71
  year: 2016
  end-page: 77
  ident: bib0037
  article-title: Fully automated segmentation of the cervical cord from T1-weighted MRI using propseg: application to multiple sclerosis
– year: 2017
  ident: bib0019
  article-title: Neurodegeneration in the spinal ventral horn prior to motor impairment in cervical spondylotic myelopathy
  publication-title: . May
– volume: 1
  start-page: 886
  year: 2005
  end-page: 893
  ident: bib0008
  article-title: Histograms of oriented gradients for human detection
  publication-title: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05)
– volume: 19
  start-page: 237
  year: 2006
  end-page: 246
  ident: bib0003
  article-title: Accurate quantification methods to evaluate cervical cord atrophy in multiple sclerosis patients
  publication-title: Magma
– volume: 152
  year: 2017
  ident: bib0030
  article-title: Spinal cord grey matter segmentation challenge
  publication-title: NeuroImage
– volume: 62
  start-page: 782
  year: 2012
  end-page: 790
  ident: bib0021
  article-title: FSL
  publication-title: NeuroImage
– year: 2004
  ident: bib0017
  article-title: Distance Transforms of Sampled Functions
– volume: 34
  start-page: 1705
  year: 2015
  end-page: 1718
  ident: bib0009
  article-title: Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling
– volume: 2010
  start-page: 3117
  year: 2010
  end-page: 3120
  ident: bib0022
  article-title: Automatic segmentation of the spinal cord and the dural sac in lumbar MR images using gradient vector flow field
  publication-title: Conference Proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
– year: 2017
  ident: bib0025
  article-title: A novel MRI biomarker of spinal cord white matter injury: T2*-weighted white matter to gray matter signal intensity ratio
  publication-title: .
– volume: 76
  year: 2016
  ident: bib0035
  article-title: A 24-channel shim array for the human spinal cord: design, evaluation, and application
– volume: 14
  start-page: 30
  year: 2013
  end-page: 38
  ident: bib0007
  article-title: Involvement of spinal sensory pathway in ALS and specificity of cord atrophy to lower motor neuron degeneration
– year: 2017
  ident: bib0036
  article-title: Slice-wise rst-order shimming of the human spinal cord at 7T
  publication-title: Proceedings of the 25th Annual Meeting of ISMRM
– volume: 39
  start-page: E262
  year: 2014
  end-page: E269
  ident: bib0018
  article-title: Morphometrics of the entire human spinal cord and spinal canal measured from in vivo high-resolution anatomical magnetic resonance imaging
  publication-title: Spine
– volume: 50
  start-page: 446
  year: 2010
  end-page: 455
  ident: bib0020
  article-title: Rapid semi-automatic segmentation of the spinal cord from magnetic resonance images: application in multiple sclerosis
  publication-title: NeuroImage
– year: 2008
  ident: bib0002
  article-title: Learning OpenCV: Computer Vision With the OpenCV Library
– volume: 145
  start-page: 24
  year: 2017
  end-page: 43
  ident: bib0011
  article-title: SCT: spinal cord toolbox, an open-source software for processing spinal cord MRI data
  publication-title: NeuroImage
– volume: 29
  start-page: 125
  year: 2016
  end-page: 153
  ident: bib0013
  article-title: Segmentation of the human spinal cord
  publication-title: Magma
– volume: 110
  start-page: 346
  year: 2008
  end-page: 359
  ident: bib0001
  article-title: Speeded-up robust features (SURF)
– year: 2017
  ident: bib0024
  article-title: Clinically feasible microstructural mri to quantify cervical spinal cord tissue injury using DTI, MT, and T2*-weighted imaging: assessment of normative data and reliability
– volume: 150
  start-page: 358
  year: 2017
  end-page: 372
  ident: bib0015
  article-title: Fully-Integrated framework for the segmentation and registration of the spinal cord white and gray matter
  publication-title: NeuroImage
– volume: 26
  year: 2008
  ident: bib0033
  article-title: Spatial normalization, bulk motion correction and coregistration for functional magnetic resonance imaging of the human cervical spinal cord and brainstem
– volume: 14
  start-page: 30
  issue: 1
  year: 2013
  ident: 10.1016/j.media.2017.12.001_bib0007
  article-title: Involvement of spinal sensory pathway in ALS and specificity of cord atrophy to lower motor neuron degeneration
  publication-title: Amyotrophic Lateral Sclerosis Frontotemporal Degener.
  doi: 10.3109/17482968.2012.701308
– volume: 84
  year: 2014
  ident: 10.1016/j.media.2017.12.001_bib0034
  article-title: The current state-of-the-art of spinal cord imaging: methods
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2013.04.124
– volume: 152
  issue: May
  year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0030
  article-title: Spinal cord grey matter segmentation challenge
  publication-title: NeuroImage
– volume: 2010
  start-page: 3117
  year: 2010
  ident: 10.1016/j.media.2017.12.001_bib0022
  article-title: Automatic segmentation of the spinal cord and the dural sac in lumbar MR images using gradient vector flow field
– volume: 36
  start-page: 224
  issue: 2
  year: 2008
  ident: 10.1016/j.media.2017.12.001_bib0016
  article-title: Morphology and morphometry of human chronic spinal cord injury using diffusion tensor imaging and fuzzy logic
  publication-title: Ann. Biomed. Eng.
  doi: 10.1007/s10439-007-9415-6
– volume: 26
  start-page: 297
  issue: 3
  year: 1945
  ident: 10.1016/j.media.2017.12.001_bib0014
  article-title: Measures of the amount of ecologic association between species
  publication-title: Ecology
  doi: 10.2307/1932409
– year: 2015
  ident: 10.1016/j.media.2017.12.001_bib0032
  article-title: U-Net: convolutional networks for biomedical image segmentation
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0036
  article-title: Slice-wise rst-order shimming of the human spinal cord at 7T
– start-page: 3431
  year: 2015
  ident: 10.1016/j.media.2017.12.001_bib0023
  article-title: Fully convolutional networks for semantic segmentation
– volume: 62
  start-page: 782
  issue: 2
  year: 2012
  ident: 10.1016/j.media.2017.12.001_bib0021
  article-title: FSL
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2011.09.015
– volume: 255
  start-page: 163
  issue: 2
  year: 2008
  ident: 10.1016/j.media.2017.12.001_bib0027
  article-title: Preferential spinal central gray matter involvement in neuromyelitis optica
  publication-title: J. Neurol.
  doi: 10.1007/s00415-008-0545-z
– volume: 10
  start-page: 71
  year: 2016
  ident: 10.1016/j.media.2017.12.001_bib0037
  article-title: Fully automated segmentation of the cervical cord from T1-weighted MRI using propseg: application to multiple sclerosis
  publication-title: NeuroImage. Clin.
  doi: 10.1016/j.nicl.2015.11.001
– volume: 98
  start-page: 528
  issue: September
  year: 2014
  ident: 10.1016/j.media.2017.12.001_bib0010
  article-title: Robust, accurate and fast automatic segmentation of the spinal cord
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2014.04.051
– year: 2004
  ident: 10.1016/j.media.2017.12.001_bib0017
– volume: 50
  start-page: 446
  issue: 2
  year: 2010
  ident: 10.1016/j.media.2017.12.001_bib0020
  article-title: Rapid semi-automatic segmentation of the spinal cord from magnetic resonance images: application in multiple sclerosis
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2009.12.121
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0025
  article-title: A novel MRI biomarker of spinal cord white matter injury: T2*-weighted white matter to gray matter signal intensity ratio
  publication-title: AJNR. Am. J. Neuroradiol.
  doi: 10.3174/ajnr.A5162
– volume: 39
  start-page: E262
  issue: 4
  year: 2014
  ident: 10.1016/j.media.2017.12.001_bib0018
  article-title: Morphometrics of the entire human spinal cord and spinal canal measured from in vivo high-resolution anatomical magnetic resonance imaging
  publication-title: Spine
  doi: 10.1097/BRS.0000000000000125
– volume: 6
  issue: October
  year: 2016
  ident: 10.1016/j.media.2017.12.001_bib0031
  article-title: Fully automated grey and white matter spinal cord segmentation
  publication-title: Sci. Rep.
– volume: 1
  start-page: 886
  year: 2005
  ident: 10.1016/j.media.2017.12.001_bib0008
  article-title: Histograms of oriented gradients for human detection
– volume: 19
  start-page: 237
  issue: 5
  year: 2006
  ident: 10.1016/j.media.2017.12.001_bib0003
  article-title: Accurate quantification methods to evaluate cervical cord atrophy in multiple sclerosis patients
  publication-title: Magma
  doi: 10.1007/s10334-006-0052-0
– volume: 76
  issue: 5
  year: 2016
  ident: 10.1016/j.media.2017.12.001_bib0035
  article-title: A 24-channel shim array for the human spinal cord: design, evaluation, and application
  publication-title: Magn. Reson. Med.
  doi: 10.1002/mrm.26354
– volume: 20
  start-page: 107
  year: 2015
  ident: 10.1016/j.media.2017.12.001_bib0029
  article-title: Automatic segmentation of the spinal cord using continuous max flow with cross-sectional similarity prior and tubularity features
– volume: 26
  year: 2008
  ident: 10.1016/j.media.2017.12.001_bib0033
  article-title: Spatial normalization, bulk motion correction and coregistration for functional magnetic resonance imaging of the human cervical spinal cord and brainstem
  publication-title: Mag. Reson. Imaging
  doi: 10.1016/j.mri.2008.01.038
– volume: 10
  issue: 3
  year: 2015
  ident: 10.1016/j.media.2017.12.001_bib0028
  article-title: Age, gender and normalization covariates for spinal cord gray matter and total cross-sectional areas at cervical and thoracic levels: a 2D phase sensitive inversion recovery imaging study
  publication-title: PloS One
  doi: 10.1371/journal.pone.0118576
– volume: 55
  start-page: 1024
  issue: 3
  year: 2011
  ident: 10.1016/j.media.2017.12.001_bib0006
  article-title: Demyelination and degeneration in the injured human spinal cord detected with diffusion and magnetization transfer MRI
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2010.11.089
– volume: 29
  start-page: 125
  issue: 2
  year: 2016
  ident: 10.1016/j.media.2017.12.001_bib0013
  article-title: Segmentation of the human spinal cord
  publication-title: Magma
  doi: 10.1007/s10334-015-0507-2
– volume: 34
  start-page: 1705
  issue: 8
  year: 2015
  ident: 10.1016/j.media.2017.12.001_bib0009
  article-title: Automatic segmentation of the spinal cord and spinal canal coupled with vertebral labeling
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2015.2437192
– year: 2008
  ident: 10.1016/j.media.2017.12.001_bib0002
– volume: 83
  start-page: 1051
  issue: December
  year: 2013
  ident: 10.1016/j.media.2017.12.001_bib0005
  article-title: Automatic magnetic resonance spinal cord segmentation with topology constraints for variable fields of view
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2013.07.060
– volume: 145
  start-page: 24
  issue: Pt A
  year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0011
  article-title: SCT: spinal cord toolbox, an open-source software for processing spinal cord MRI data
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2016.10.009
– volume: 110
  start-page: 346
  issue: 3
  year: 2008
  ident: 10.1016/j.media.2017.12.001_bib0001
  article-title: Speeded-up robust features (SURF)
  publication-title: Comput. Vision Image Understanding
  doi: 10.1016/j.cviu.2007.09.014
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0024
  article-title: Clinically feasible microstructural mri to quantify cervical spinal cord tissue injury using DTI, MT, and T2*-weighted imaging: assessment of normative data and reliability
  publication-title: AJNR. Am. J. Neuroradiol
  doi: 10.3174/ajnr.A5163
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0004
  article-title: Spinal cord atrophy as a primary outcome measure in phase II trials of progressive multiple sclerosis
  publication-title: Multiple Sclerosis
– volume: 18
  start-page: 331
  year: 2002
  ident: 10.1016/j.media.2017.12.001_bib0026
  article-title: A general algorithm for computing distance transforms in linear time
– volume: 150
  start-page: 358
  issue: April
  year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0015
  article-title: Fully-Integrated framework for the segmentation and registration of the spinal cord white and gray matter
  publication-title: NeuroImage
  doi: 10.1016/j.neuroimage.2016.09.026
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0012
  article-title: Topologically preserving straightening of spinal cord MRI
  publication-title: J. Mag. Reson. Imaging
  doi: 10.1002/jmri.25622
– year: 2017
  ident: 10.1016/j.media.2017.12.001_bib0019
  article-title: Neurodegeneration in the spinal ventral horn prior to motor impairment in cervical spondylotic myelopathy
  publication-title: J. Neurotrauma. May
  doi: 10.1089/neu.2017.4980
SSID ssj0007440
Score 2.4133055
Snippet •Automatic, fast and robust method to detect the center of the spinal cord on MRI data.•Machine learning based method followed by a global curve...
During the last two decades, MRI has been increasingly used for providing valuable quantitative information about spinal cord morphometry, such as...
SourceID unpaywall
hal
proquest
pubmed
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 215
SubjectTerms Algorithms
Artificial intelligence
Atrophy
Automation
Bioengineering
Brain
Detection
Engineering Sciences
Errors
Field of view
Global optimization
Gold
Hough transformation
Humans
Image processing
Image Processing, Computer-Assisted - methods
Imaging
Life Sciences
Localization
Machine Learning
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Mean square values
Medical diagnosis
Medical imaging
Morphometry
MRI
Neurological diseases
NMR
Nuclear magnetic resonance
Optimization algorithms
Post-production processing
Quantitative analysis
Rank tests
Reproducibility of Results
Robustness
Segmentation
Sensitivity and Specificity
Signal and Image processing
Spinal cord
Spinal Cord - diagnostic imaging
Spinal cord injuries
Spine
SummonAdditionalLinks – databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9UwFA7zDpQ9OJ2_rkyJ4uMy-iNN08fL2LiKd4h4YeJDSNJkQ6_t5bad6F_vSZqWMeWifQpt0lBOkvOl-c53EHqTS8Yy7aQvM10QmtmcKEAhRIIr55llqaEuwHlxzuZL-u4iu9hBeIiFuQLEGdZ-VyZOLAQmAuxvdlkGaHuCdpfnH2af-3CqmHDqkxSEss_mFsppPIgMeTqXD8RwVK7c__4LSWD-4ojuXDlG5J9wcw_d66q1_PlDrlY3XNDZfk-FbLxyoWOefDvuWnWsf93Sddz2dQ_Q_YA_8awfMA_RjqkO0N4NVcIDdHcRztsfoS-zrq29qCtu1i5_FnabVewdYAjgPMKbWnVNi9saLz6-xZ77Lpu2wY5Sf4l7xRGsu821wTUsUN9Dw8doeXb66WROQjoGorM0aUmZlFQVlgFgLDOamkgrmiq4TBwZm8eKSltwYzXPc24zyxPLrGaW5oxGCgzyBE2qujLPENbUOBWhkgN4oICYuccSkYo4LZmkcoqSwTZCB61ylzJjJQZS2lfhDSqcQUWcOGreFB2Njda9VMf26mwwugg26VGEAGeyveFrsN3YhdPnns_eC3dvsOc1VDocRpAIq0IDL8kj6k9ep-jV-BjmszukkZWpu0bEBeyBaRKn-RQ97Ufe2FVSJJwXHFqTcSj-y6c-_8_6h2jSbjrzAuBWq16GGfcbFNUkIg
  priority: 102
  providerName: Unpaywall
Title Automatic spinal cord localization, robust to MRI contrasts using global curve optimization
URI https://dx.doi.org/10.1016/j.media.2017.12.001
https://www.ncbi.nlm.nih.gov/pubmed/29288983
https://www.proquest.com/docview/2070443823
https://www.proquest.com/docview/1982842137
https://hal.science/hal-01690881
UnpaywallVersion submittedVersion
Volume 44
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  customDbUrl:
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: GBLVA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection [SCCMFC]
  customDbUrl:
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: ACRLP
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: ScienceDirect (Elsevier)
  customDbUrl:
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: .~1
  dateStart: 19960301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: ScienceDirect Freedom Collection Journals
  customDbUrl:
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: AIKHN
  dateStart: 20161201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 1361-8423
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0007440
  issn: 1361-8415
  databaseCode: AKRWK
  dateStart: 19960301
  isFulltext: true
  providerName: Library Specific Holdings
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELZKkYAeEJTXQqkM4tiweTi2cwwVZQvdFQIWLeJg5WFD0ZKsNkkRF347M46zFIEqRC5WEjtOMvbMJP7mG0KeiIzzuEDqy7hIPBYb4eXghXgZmHIZGx5phgHO0xmfzNnLRbzYIodDLAzCKp3u73W61dbuyNi9zfHq9HT8NogwWQlYLBykki8wgp0JzGLw9McvmAcS4PWxV4GHtQfmIYvxstEZiO8S9p-gywzzF-t06TPCJP_0QXfI1a5aZd-_ZcvlObt0dINcdw4lTft7vkm2dLVLds7RDO6SK1O3gH6LfEy7trYsrbRZYUIsil-f1Fo0F5F5QNd13jUtbWs6fXNMLZg9a9qGIkb-E-0pRGjRrc80rUHjfHUNb5P50fN3hxPP5VfwijgKW68MS5YnhoMHWMYs0n6RsyiHTQe-NiLIWWYSqU0hhZAmNjI03BTcMMGZn0sW3SHbVV3pe4QWTCMtUCnBG2DgAkvrHPi5L1nJM5aNSDi8V1U48nHMgbFUA8rsi7LCUCgMFYSItRuRg02jVc-9cXF1PghM_TaEFFiHixs-BvFuukDC7Ul6ovAYctWAHg7OoNLeIH3lpnkDFxE-s0upI_JocxomKK66ZJWuu0YFCXzUsjCIxIjc7UfNpqswCaVMJLT2NsPoXx71_v8-6gNyDfZkDzvfI9vtutMPwatq8307bfbJ5fT41WQG5YtnJ-9TKOez1-mHn6oEIY8
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB61RaL0UEF5LS1gEMeGzcOxneOqotrCbg_QSitxsPKw26IlWW2SIi78djyOE4pAFSJHP-IkY8-M42--AXjDU8biHKkv4zzxaKy5lxkvxEuNKRexZpGiGOA8P2XTc_p-ES824KiPhUFYpdP9nU632tqVjN3XHK-ursafggiTlRiLhZNUsMUm3KFxyHEH9vbHL5wHMuB1wVeBh8176iEL8rLhGQjw4vanoEsN8xfztHmJOMk_ndAd2G7LVfr9W7pc3jBMx_dh13mUZNI99APYUOUe7NzgGdyDu3N3gv4QPk_aprI0raReYUYsgttPYk2aC8k8JOsqa-uGNBWZfzwhFs2e1k1NECR_QToOEZK362tFKqNyvrqOj-D8-N3Z0dRzCRa8PI7CxivCgmaJZsYFLGIaKT_PaJSZSwW-0jzIaKoToXQuOBc61iLUTOdMU86onwkaPYatsirVUyA5VcgLVAjjDlDjAwvrHfiZL2jBUpqOIOy_q8wd-zgmwVjKHmb2RVphSBSGDEIE243gcOi06sg3bm_OeoHJ3-aQNObh9o6vjXiHIZBxezqZSSxDshqjiINr0-igl75067w2N-E-tWepI3g1VJsViscuaamqtpZBYna1NAwiPoIn3awZhgqTUIhEmN7eMI3-5VWf_e-rvoTt6dl8Jmcnpx_24Z6pER0G_QC2mnWrnhsXq8le2CX0ExtcH-U
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9UwFA7zDpQ9OJ2_rkyJ4uMy-iNN08fL2LiKd4h4YeJDSNJkQ6_t5bad6F_vSZqWMeWifQpt0lBOkvOl-c53EHqTS8Yy7aQvM10QmtmcKEAhRIIr55llqaEuwHlxzuZL-u4iu9hBeIiFuQLEGdZ-VyZOLAQmAuxvdlkGaHuCdpfnH2af-3CqmHDqkxSEss_mFsppPIgMeTqXD8RwVK7c__4LSWD-4ojuXDlG5J9wcw_d66q1_PlDrlY3XNDZfk-FbLxyoWOefDvuWnWsf93Sddz2dQ_Q_YA_8awfMA_RjqkO0N4NVcIDdHcRztsfoS-zrq29qCtu1i5_FnabVewdYAjgPMKbWnVNi9saLz6-xZ77Lpu2wY5Sf4l7xRGsu821wTUsUN9Dw8doeXb66WROQjoGorM0aUmZlFQVlgFgLDOamkgrmiq4TBwZm8eKSltwYzXPc24zyxPLrGaW5oxGCgzyBE2qujLPENbUOBWhkgN4oICYuccSkYo4LZmkcoqSwTZCB61ylzJjJQZS2lfhDSqcQUWcOGreFB2Njda9VMf26mwwugg26VGEAGeyveFrsN3YhdPnns_eC3dvsOc1VDocRpAIq0IDL8kj6k9ep-jV-BjmszukkZWpu0bEBeyBaRKn-RQ97Ufe2FVSJJwXHFqTcSj-y6c-_8_6h2jSbjrzAuBWq16GGfcbFNUkIg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automatic+spinal+cord+localization%2C+robust+to+MRI+contrasts+using+global+curve+optimization&rft.jtitle=Medical+image+analysis&rft.au=Gros%2C+Charley&rft.au=De+Leener%2C+Benjamin&rft.au=Dupont%2C+Sara+M&rft.au=Martin%2C+Allan+R&rft.date=2018-02-01&rft.issn=1361-8423&rft.eissn=1361-8423&rft.volume=44&rft.spage=215&rft_id=info:doi/10.1016%2Fj.media.2017.12.001&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1361-8415&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1361-8415&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1361-8415&client=summon