Advertisement

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

Research ArticlePediatric Neuroimaging
Open Access

MR Imaging–Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma

M. Iv, M. Zhou, K. Shpanskaya, S. Perreault, Z. Wang, E. Tranvinh, B. Lanzman, S. Vajapeyam, N.A. Vitanza, P.G. Fisher, Y.J. Cho, S. Laughlin, V. Ramaswamy, M.D. Taylor, S.H. Cheshier, G.A. Grant, T. Young Poussaint, O. Gevaert and K.W. Yeom
American Journal of Neuroradiology December 2018, DOI: https://doi.org/10.3174/ajnr.A5899

Article Figures & Data

Figures

  • Fig 1.
    Fig 1.

    Illustration of 2 strategies used to evaluate the supervised machine learning models to predict the molecular subgroups of medulloblastoma. The upper and lower figures show details of double 10-fold cross-validation and 3-dataset cross-validation schemes, respectively.

  • Fig 2.
    Fig 2.

    Receiver operating characteristic curves with a double 10-fold cross-validation scheme for support vector machine to predict the 4 main molecular subgroups of medulloblastoma with the use of computational MR imaging features.

  • Fig 3.
    Fig 3.

    Receiver operating characteristic curves with the largest mean AUC values for 4 distinct molecular subgroups of medulloblastoma with a 3-dataset cross-validation scheme.

  • Fig 4.
    Fig 4.

    MR imaging appearance of the 4 core molecular subgroups of medulloblastoma on T2-weighted and contrast-enhanced T1-weighted images.

Tables

  • Table 1:

    Patient demographics

    CharacteristicInstitutional Cohort
    StanfordBostonToronto
    No. of patients322849
    Age (mean) (yr)10.14 ± 8.498.54 ± 4.527.53 ± 3.69
    Male sex (No.) (%)23 (72)9 (32)32 (65)
    Molecular subgroup (No.)
        SHH11910
        WNT4510
        Group 37512
        Group 410917
    MRI availability (No.)
        3T501
        1.5T272848
        T1-weighted322648
        2D T1-weighted28257
        3D T1-weighted4141
        T2-weighted302729
        T1- and T2-weighted302527
  • Table 2:

    Predictive performance of 2 machine learning models for the identification of medulloblastoma molecular subgroups

    MRI Dataset/Targeted SubgroupAUC with Double 10-Fold Cross-ValidationAUC with 3-Dataset Cross-Validation
    T1
        SHH0.670.73
        WNT0.560.47
        Group 30.400.54
        Group 40.790.76
    T2
        SHH0.700.66
        WNT0.630.72
        Group 30.510.57
        Group 40.540.59
    T1 + T2
        SHH0.790.70
        WNT0.450.45
        Group 30.700.39
        Group 40.830.80
Back to top
Advertisement
Print
Download PDF
Email Article
Cite this article
0 Responses
Respond to this article
Bookmark this article
MR Imaging–Based Radiomic Signatures of Distinct Molecular Subgroups of Medulloblastoma
M. Iv, M. Zhou, K. Shpanskaya, S. Perreault, Z. Wang, E. Tranvinh, B. Lanzman, S. Vajapeyam, N.A. Vitanza, P.G. Fisher, Y.J. Cho, S. Laughlin, V. Ramaswamy, M.D. Taylor, S.H. Cheshier, G.A. Grant, T. Young Poussaint, O. Gevaert, K.W. Yeom
American Journal of Neuroradiology Dec 2018, DOI: 10.3174/ajnr.A5899
del.icio.us logo Twitter logo Facebook logo Mendeley logo
Purchase

Jump to section

Advertisement