Skip to main content
Advertisement

Main menu

  • Home
  • Content
    • Current Issue
    • Accepted Manuscripts
    • Article Preview
    • Past Issue Archive
    • Video Articles
    • AJNR Case Collection
    • Case of the Week Archive
    • Case of the Month Archive
    • Classic Case Archive
  • Special Collections
    • AJNR Awards
    • Low-Field MRI
    • Alzheimer Disease
    • ASNR Foundation Special Collection
    • Photon-Counting CT
    • View All
  • Multimedia
    • AJNR Podcasts
    • AJNR SCANtastic
    • Trainee Corner
    • MRI Safety Corner
    • Imaging Protocols
  • For Authors
    • Submit a Manuscript
    • Submit a Video Article
    • Submit an eLetter to the Editor/Response
    • Manuscript Submission Guidelines
    • Statistical Tips
    • Fast Publishing of Accepted Manuscripts
    • Graphical Abstract Preparation
    • Imaging Protocol Submission
    • Author Policies
  • About Us
    • About AJNR
    • Editorial Board
    • Editorial Board Alumni
  • More
    • Become a Reviewer/Academy of Reviewers
    • Subscribers
    • Permissions
    • Alerts
    • Feedback
    • Advertisers
    • ASNR Home

User menu

  • Alerts
  • Log in

Search

  • Advanced search
American Journal of Neuroradiology
American Journal of Neuroradiology

American Journal of Neuroradiology

ASHNR American Society of Functional Neuroradiology ASHNR American Society of Pediatric Neuroradiology ASSR
  • Alerts
  • Log in

Advanced Search

  • Home
  • Content
    • Current Issue
    • Accepted Manuscripts
    • Article Preview
    • Past Issue Archive
    • Video Articles
    • AJNR Case Collection
    • Case of the Week Archive
    • Case of the Month Archive
    • Classic Case Archive
  • Special Collections
    • AJNR Awards
    • Low-Field MRI
    • Alzheimer Disease
    • ASNR Foundation Special Collection
    • Photon-Counting CT
    • View All
  • Multimedia
    • AJNR Podcasts
    • AJNR SCANtastic
    • Trainee Corner
    • MRI Safety Corner
    • Imaging Protocols
  • For Authors
    • Submit a Manuscript
    • Submit a Video Article
    • Submit an eLetter to the Editor/Response
    • Manuscript Submission Guidelines
    • Statistical Tips
    • Fast Publishing of Accepted Manuscripts
    • Graphical Abstract Preparation
    • Imaging Protocol Submission
    • Author Policies
  • About Us
    • About AJNR
    • Editorial Board
    • Editorial Board Alumni
  • More
    • Become a Reviewer/Academy of Reviewers
    • Subscribers
    • Permissions
    • Alerts
    • Feedback
    • Advertisers
    • ASNR Home
  • Follow AJNR on Twitter
  • Visit AJNR on Facebook
  • Follow AJNR on Instagram
  • Join AJNR on LinkedIn
  • RSS Feeds

AJNR Awards, New Junior Editors, and more. Read the latest AJNR updates

Research ArticleBrain
Open Access

Evaluating the Effects of White Matter Multiple Sclerosis Lesions on the Volume Estimation of 6 Brain Tissue Segmentation Methods

S. Valverde, A. Oliver, Y. Díez, M. Cabezas, J.C. Vilanova, L. Ramió-Torrentà, À. Rovira and X. Lladó
American Journal of Neuroradiology June 2015, 36 (6) 1109-1115; DOI: https://doi.org/10.3174/ajnr.A4262
S. Valverde
aFrom the Computer Vision and Robotics Group (S.V., A.O., Y.D., X.L.), University of Girona, Campus Montilivi, Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
A. Oliver
aFrom the Computer Vision and Robotics Group (S.V., A.O., Y.D., X.L.), University of Girona, Campus Montilivi, Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for A. Oliver
Y. Díez
aFrom the Computer Vision and Robotics Group (S.V., A.O., Y.D., X.L.), University of Girona, Campus Montilivi, Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
M. Cabezas
dMagnetic Resonance Unit (M.C., A.R.), Department of Radiology, Vall d'Hebron University Hospital, Barcelona, Spain.
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
J.C. Vilanova
bGirona Magnetic Resonance Center (J.C.V.), Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
L. Ramió-Torrentà
cMultiple Sclerosis and Neuroimmunology Unit (L.R.-T.), Dr. Josep Trueta University Hospital, Institut d'Investigació Biomèdica de Girona, Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
À. Rovira
dMagnetic Resonance Unit (M.C., A.R.), Department of Radiology, Vall d'Hebron University Hospital, Barcelona, Spain.
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
X. Lladó
aFrom the Computer Vision and Robotics Group (S.V., A.O., Y.D., X.L.), University of Girona, Campus Montilivi, Girona, Spain
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • Article
  • Figures & Data
  • Info & Metrics
  • Responses
  • References
  • PDF
Loading

Article Figures & Data

Figures

  • Tables
  • Fig 1.
    • Download figure
    • Open in new tab
    • Download powerpoint
    Fig 1.

    T1-weighted images from the 3 hospitals and scanners involved in the study: 1.5T Magnetom Symphony Quantum (Siemens) from H1 (first row), 1.5T Intera (R12) (Philips) from H2 (middle row), and 1.5T Signa HDxt (GE Healthcare) from H3 (last row).

  • Fig 2.
    • Download figure
    • Open in new tab
    • Download powerpoint
    Fig 2.

    Our pipeline approach. From the 30 T1-weighted scans of patients with MS, nonbrain parts are stripped and brain voxels are corrected for intensity inhomogeneities. From the same corrected set (original), a new set is generated by removing WML masks from scans before segmentation (masked). The scans of both sets are segmented into 1 of the 3 tissue classes (GM, WM, and CSF). Lesion voxels are added as WM after segmentation on masked images.

  • Fig 3.
    • Download figure
    • Open in new tab
    • Download powerpoint
    Fig 3.

    Percentage of voxels in WML regions having been classified as GM (top) and WM (bottom) for each segmentation method and hospital, H1 (♢), H2 (□) or H3 (○). Reported values are means and SDs.

  • Fig 4.
    • Download figure
    • Open in new tab
    • Download powerpoint
    Fig 4.

    Classification output returned by each segmentation method on the same image. A, T1-weighted scan. B, Zoomed part of the scan with lesions outlined in red. Brain tissue segmentation outputs also with lesions outlined for ANN (C), FCM (D), FANTASM (E), FAST (F), SPM5 (G), and SPM8 (H). C–H, Segmented GM tissue is represented in gray; WM, in white; and CSF, in black.

Tables

  • Figures
    • View popup
    Table 1:

    Average percentage of change in total tissue volume estimation between original and masked imagesa

    MethodH1H2H3
    GMWMCSFGMWMCSFGMWMCSF
    ANN0.33 ± 0.42−0.23 ± 0.280.11 ± 0.111.59 ± 1.37−0.56 ± 0.460.78 ± 0.760.25 ± 0.31−0.16 ± 0.28−0.09 ± 0.09
    FCM0.28 ± 0.37−0.22 ± 0.290.09 ± 0.112.28 ± 2.26−0.90 ± 0.830.94 ± 0.900.28 ± 0.23−0.25 ± 0.200.08 ± 0.09
    FANTASM0.23 ± 0.26−0.18 ± 0.210.08 ± 0.081.34 ± 1.13−0.49 ± 0.370.80 ± 0.730.26 ± 0.22−0.24 ± 0.190.07 ± 0.08
    FAST0.29 ± 0.36−0.29 ± 0.360.12 ± 0.131.92 ± 1.59−1.28 ± 1.030.47 ± 0.390.34 ± 0.28−0.37 ± 0.310.12 ± 0.17
    SPM50.20 ± 0.30−0.21 ± 0.20−0.14 ± 0.540.10 ± 2.68−1.04 ± 3.010.53 ± 0.510.04 ± 0.17−0.18 ± 0.360.15 ± 0.23
    SPM80.08 ± 0.09−0.08 ± 0.08−0.04 ± 0.180.55 ± 0.34−0.93 ± 0.550.54 ± 0.420.09 ± 0.15−0.23 ± 0.250.17 ± 0.23
    • ↵a The results are divided by tissue and hospital. Reported values are the means ± SD. Positive values indicate a tissue overestimation on original images compared with masked.

    • View popup
    Table 2:

    Pearson correlation coefficients between method differences in total volume estimation and WML sizea

    MethodGMWMCSF
    H1
        ANN0.94−0.900.89
        FCM0.93−0.890.83
        FANTASM0.87−0.800.78
        FAST0.97−0.970.96
        SPM50.58b−0.89−0.21b
        SPM80.92−0.63−0.69
    H2
        ANN0.91−0.880.93
        FCM0.92−0.940.92
        FANTASM0.89−0.870.84
        FAST0.95−0.960.82
        SPM5−0.35b−0.06b0.72
        SPM80.76−0.790.57b
    H3
        ANN0.56b−0.55b0.88
        FCM0.77−0.840.88
        FANTASM0.74−0.820.85
        FAST0.88−0.940.92
        SPM5−0.06b−0.03b0.21b
        SPM80.56b−0.48b0.09b
    • ↵a Correlation was computed for each method and hospital separately. All values were found to be significant (P value < .05) unless otherwise noted.

    • ↵b Not significant.

    • View popup
    Table 3:

    Average percentage change in the volume estimation of tissue outside the lesion regions between original and masked scansa

    MethodH1H2H3
    GMWMCSFGMWMCSFGMWMCSF
    ANN0.15 ± 0.26−0.10 ± 0.180.07 ± 0.080.70 ± 0.61−0.31 ± 0.240.67 ± 0.69−0.01 ± 0.280.04 ± 0.24−0.12 ± 0.08
    FCM0.09 ± 0.16−0.07 ± 0.130.05 ± 0.081.27 ± 1.69−0.56 ± 0.620.82 ± 0.810.01 ± 0.03−0.03 ± 0.050.05 ± 0.07
    FANTASM0.06 ± 0.05−0.05 ± 0.050.03 ± 0.050.48 ± 0.48−0.25 ± 0.180.68 ± 0.630.00 ± 0.04−0.02 ± 0.050.04 ± 0.07
    FAST0.08 ± 0.14−0.09 ± 0.140.07 ± 0.080.56 ± 0.87−0.45 ± 0.640.22 ± 0.330.02 ± 0.07−0.06 ± 0.130.08 ± 0.16
    SPM50.06 ± 0.250.02 ± 0.13−0.19 ± 0.54−0.29 ± 2.61−0.47 ± 2.910.21 ± 0.32−0.20 ± 0.240.23 ± 0.340.06 ± 0.15
    SPM8−0.03 ± 0.060.09 ± 0.15−0.10 ± 0.230.13 ± 0.30−0.29 ± 0.330.25 ± 0.26−0.15 ± 0.120.14 ± 0.150.10 ± 0.20
    • ↵a The results are divided by hospital and tissue. Reported values are the means ± SD. Positive values indicate a tissue overestimation on original images compared with masked.

    • View popup
    Table 4:

    Pearson correlation coefficients among method differences in volume estimation of tissue outside the lesion regions and WML sizea

    MethodGMWMCSF
    H1
        ANN0.77−0.740.83
        FCM0.82−0.800.71
        FANTASM0.80−0.730.66
        FAST0.86−0.930.97
        SPM50.110.51b−0.30b
        SPM8−0.57b0.95−0.77
    H2
        ANN0.85−0.920.93
        FCM0.71−0.840.94
        FANTASM0.66−0.820.87
        FAST0.33b−0.46b0.62b
        SPM5−0.43b0.18b0.65b
        SPM80.16b−0.37b0.30b
    H3
        ANN0.07−0.16b0.79
        FCM0.50−0.770.89
        FANTASM0.17−0.57b0.87
        FAST0.45−0.730.89
        SPM5−0.78b0.720.14b
        SPM8−0.64b0.72−0.01b
    • ↵a Correlation was computed for each method and hospital separately. All values were found to be significant (P value <.05) unless otherwise noted.

    • ↵b Not significant.

PreviousNext
Back to top

In this issue

American Journal of Neuroradiology: 36 (6)
American Journal of Neuroradiology
Vol. 36, Issue 6
1 Jun 2015
  • Table of Contents
  • Index by author
  • Complete Issue (PDF)
Advertisement
Print
Download PDF
Email Article

Thank you for your interest in spreading the word on American Journal of Neuroradiology.

NOTE: We only request your email address so that the person you are recommending the page to knows that you wanted them to see it, and that it is not junk mail. We do not capture any email address.

Enter multiple addresses on separate lines or separate them with commas.
Evaluating the Effects of White Matter Multiple Sclerosis Lesions on the Volume Estimation of 6 Brain Tissue Segmentation Methods
(Your Name) has sent you a message from American Journal of Neuroradiology
(Your Name) thought you would like to see the American Journal of Neuroradiology web site.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Cite this article
S. Valverde, A. Oliver, Y. Díez, M. Cabezas, J.C. Vilanova, L. Ramió-Torrentà, À. Rovira, X. Lladó
Evaluating the Effects of White Matter Multiple Sclerosis Lesions on the Volume Estimation of 6 Brain Tissue Segmentation Methods
American Journal of Neuroradiology Jun 2015, 36 (6) 1109-1115; DOI: 10.3174/ajnr.A4262

Citation Manager Formats

  • BibTeX
  • Bookends
  • EasyBib
  • EndNote (tagged)
  • EndNote 8 (xml)
  • Medlars
  • Mendeley
  • Papers
  • RefWorks Tagged
  • Ref Manager
  • RIS
  • Zotero
0 Responses
Respond to this article
Share
Bookmark this article
Evaluating the Effects of White Matter Multiple Sclerosis Lesions on the Volume Estimation of 6 Brain Tissue Segmentation Methods
S. Valverde, A. Oliver, Y. Díez, M. Cabezas, J.C. Vilanova, L. Ramió-Torrentà, À. Rovira, X. Lladó
American Journal of Neuroradiology Jun 2015, 36 (6) 1109-1115; DOI: 10.3174/ajnr.A4262
del.icio.us logo Twitter logo Facebook logo Mendeley logo
  • Tweet Widget
  • Facebook Like
  • Google Plus One
Purchase

Jump to section

  • Article
    • Abstract
    • ABBREVIATIONS:
    • Materials and Methods
    • Results
    • Discussion
    • Conclusions
    • Footnotes
    • References
  • Figures & Data
  • Info & Metrics
  • Responses
  • References
  • PDF

Related Articles

  • No related articles found.
  • PubMed
  • Google Scholar

Cited By...

  • No citing articles found.
  • Crossref (11)
  • Google Scholar

This article has been cited by the following articles in journals that are participating in Crossref Cited-by Linking.

  • Automated tissue segmentation of MR brain images in the presence of white matter lesions
    Sergi Valverde, Arnau Oliver, Eloy Roura, Sandra González-Villà, Deborah Pareto, Joan C. Vilanova, Lluís Ramió-Torrentà, Àlex Rovira, Xavier Lladó
    Medical Image Analysis 2017 35
  • Automatic brain tissue segmentation in MR images using Random Forests and Conditional Random Fields
    Sérgio Pereira, Adriano Pinto, Jorge Oliveira, Adriënne M. Mendrik, José H. Correia, Carlos A. Silva
    Journal of Neuroscience Methods 2016 270
  • Quantifying brain tissue volume in multiple sclerosis with automated lesion segmentation and filling
    Sergi Valverde, Arnau Oliver, Eloy Roura, Deborah Pareto, Joan C. Vilanova, Lluís Ramió-Torrentà, Jaume Sastre-Garriga, Xavier Montalban, Àlex Rovira, Xavier Lladó
    NeuroImage: Clinical 2015 9
  • Evaluating the effect of multiple sclerosis lesions on automatic brain structure segmentation
    Sandra González-Villà, Sergi Valverde, Mariano Cabezas, Deborah Pareto, Joan C. Vilanova, Lluís Ramió-Torrentà, Àlex Rovira, Arnau Oliver, Xavier Lladó
    NeuroImage: Clinical 2017 15
  • Automated multiclass tissue segmentation of clinical brain MRIs with lesions
    David A. Weiss, Rachit Saluja, Long Xie, James C. Gee, Leo P Sugrue, Abhijeet Pradhan, R. Nick Bryan, Andreas M. Rauschecker, Jeffrey D. Rudie
    NeuroImage: Clinical 2021 31
  • Automated Robust Image Segmentation: Level Set Method Using Nonnegative Matrix Factorization with Application to Brain MRI
    Dimah Dera, Nidhal Bouaynaya, Hassan M. Fathallah-Shaykh
    Bulletin of Mathematical Biology 2016 78 7
  • FLAIR-only joint volumetric analysis of brain lesions and atrophy in clinically isolated syndrome (CIS) suggestive of multiple sclerosis
    O. Goodkin, F. Prados, S.B. Vos, H. Pemberton, S. Collorone, M.H.J. Hagens, M.J. Cardoso, T.A. Yousry, J.S. Thornton, C.H. Sudre, F. Barkhof
    NeuroImage: Clinical 2021 29
  • Multimodal Image Analysis for Assessing Multiple Sclerosis and Future Prospects Powered by Artificial Intelligence
    Minjeong Kim, Valerie Jewells
    Seminars in Ultrasound, CT and MRI 2020 41 3
  • The Impact of MRI T1 Hypointense Brain Lesions on Cerebral Deep Gray Matter Volume Measures in Multiple Sclerosis
    Korhan Buyukturkoglu, Enricomaria Mormina, Philip L. De Jager, Claire S. Riley, Victoria M. Leavitt
    Journal of Neuroimaging 2019 29 4
  • Multiple sclerosis lesion enhancement and white matter region estimation using hyperintensities in FLAIR images
    Paulo G.L. Freire, Ricardo J. Ferrari
    Biomedical Signal Processing and Control 2019 49

More in this TOC Section

  • Usefulness of Quantitative Susceptibility Mapping for the Diagnosis of Parkinson Disease
  • White Matter Alterations in the Brains of Patients with Active, Remitted, and Cured Cushing Syndrome: A DTI Study
  • Qualitative and Quantitative Analysis of MR Imaging Findings in Patients with Middle Cerebral Artery Stroke Implanted with Mesenchymal Stem Cells
Show more BRAIN

Similar Articles

Advertisement

Indexed Content

  • Current Issue
  • Accepted Manuscripts
  • Article Preview
  • Past Issues
  • Editorials
  • Editor's Choice
  • Fellows' Journal Club
  • Letters to the Editor
  • Video Articles

Cases

  • Case Collection
  • Archive - Case of the Week
  • Archive - Case of the Month
  • Archive - Classic Case

More from AJNR

  • Trainee Corner
  • Imaging Protocols
  • MRI Safety Corner

Multimedia

  • AJNR Podcasts
  • AJNR Scantastics

Resources

  • Turnaround Time
  • Submit a Manuscript
  • Submit a Video Article
  • Submit an eLetter to the Editor/Response
  • Manuscript Submission Guidelines
  • Statistical Tips
  • Fast Publishing of Accepted Manuscripts
  • Graphical Abstract Preparation
  • Imaging Protocol Submission
  • Evidence-Based Medicine Level Guide
  • Publishing Checklists
  • Author Policies
  • Become a Reviewer/Academy of Reviewers
  • News and Updates

About Us

  • About AJNR
  • Editorial Board
  • Editorial Board Alumni
  • Alerts
  • Permissions
  • Not an AJNR Subscriber? Join Now
  • Advertise with Us
  • Librarian Resources
  • Feedback
  • Terms and Conditions
  • AJNR Editorial Board Alumni

American Society of Neuroradiology

  • Not an ASNR Member? Join Now

© 2025 by the American Society of Neuroradiology All rights, including for text and data mining, AI training, and similar technologies, are reserved.
Print ISSN: 0195-6108 Online ISSN: 1936-959X

Powered by HighWire