Main Content

shapeFeatures

Radiomics shape features

Since R2023b

collapse all in page

    Syntax

    S = shapeFeatures(R)
    S = shapeFeatures(R,Name=Value)

    Description

    S = shapeFeatures(R) computes the radiomics shape features S for the radiomics object R.

    example

    S = shapeFeatures(R,Name=Value) specifies additional options using one or more optional name-value arguments.

    Examples

    collapse all

    Open Live Script

    Import a computed tomography (CT) image volume and the corresponding ROI mask volume from the IBSI validation data set [1][2][3] as medicalVolume objects.

    unzip("CTImageMaskNIfTI.zip")
data = medicalVolume("CT_image.nii.gz");
roi = medicalVolume("CT_mask.nii.gz");

    Visualize a slice of the CT image volume and the corresponding ROI.

    figure
imshowpair(data.Voxels(:,:,20),roi.Voxels(:,:,20),"montage")

    Figure contains an axes object. The hidden axes object contains an object of type image.

    Create a radiomics object, using the CT image volume and ROI mask volume, with default preprocessing options.

    R = radiomics(data,roi)
    R = 
  radiomics with properties:

                             Data: [1x1 medicalVolume]
                         ROILabel: [1x1 medicalVolume]
                         Resample: 1
                        Resegment: 1
                       Discretize: 1
                    DiscretizeIVH: 1
            ResampledVoxelSpacing: 1
               DataResampleMethod: 'linear'
               MaskResampleMethod: 'linear'
              ResegmentationRange: []
                  ExcludeOutliers: 1
       DiscreteBinSizeOrBinNumber: []
                   DiscreteMethod: 'FixedBinNumber'
    DiscreteIVHBinSizeOrBinNumber: []
                DiscreteIVHMethod: 'FixedBinNumber'

    Compute the shape features of the ROI in both the 2D-resampled and 3D-resampled CT image volumes.

    S = shapeFeatures(R,Type="all",SubType="all")
    S=1×51 table
    LabelID    VolumeMesh2D    VolumeVoxelCount2D    SurfaceAreaMesh2D    SurfaceVolumeRatio2D    Compactness1_2D    Compactness2_2D    SphericalDisproportion2D    Sphericity2D    Asphericity2D    CentreOfMassShift2D    Maximum3dDiameter2D    MajorAxisLength2D    MinorAxisLength2D    LeastAxisLength2D    Elongation2D    Flatness2D    VolumeDensityAABB_2D    AreaDensityAABB_2D    VolumeDensityAEE_2D    AreaDensityAEE_2D    VolumeDensityConvexHull2D    AreaDensityConvexHull2D    IntegratedIntensity2D    MoransIIndex2D    GearysCMeasure2D    VolumeMesh3D    VolumeVoxelCount3D    SurfaceAreaMesh3D    SurfaceVolumeRatio3D    Compactness1_3D    Compactness2_3D    SphericalDisproportion3D    Sphericity3D    Asphericity3D    CentreOfMassShift3D    Maximum3dDiameter3D    MajorAxisLength3D    MinorAxisLength3D    LeastAxisLength3D    Elongation3D    Flatness3D    VolumeDensityAABB_3D    AreaDensityAABB_3D    VolumeDensityAEE_3D    AreaDensityAEE_3D    VolumeDensityConvexHull3D    AreaDensityConvexHull3D    IntegratedIntensity3D    MoransIIndex3D    GearysCMeasure3D
    _______    ____________    __________________    _________________    ____________________    _______________    _______________    ________________________    ____________    _____________    ___________________    ___________________    _________________    _________________    _________________    ____________    __________    ____________________    __________________    ___________________    _________________    _________________________    _______________________    _____________________    ______________    ________________    ____________    __________________    _________________    ____________________    _______________    _______________    ________________________    ____________    _____________    ___________________    ___________________    _________________    _________________    _________________    ____________    __________    ____________________    __________________    ___________________    _________________    _________________________    _______________________    _____________________    ______________    ________________

      "1"         52504              52637                8411.4                 0.1602              0.038399            0.52389                 1.2405               0.80615          0.24047             0.91477                56.989                50.304                 44                 33.402            0.87467         0.664             0.47158                0.59688                1.3563                1.4179                   0.90243                     1.1059                  3.1173e+06             0.013525           0.97867            52923              52975                 8425                 0.15919              0.038611            0.5297                  1.2359               0.80911          0.23592             0.8888                 57.359                50.405                44.1                33.518             0.8749        0.66497            0.46924                0.59248                1.3566                1.4135                   0.89714                     1.0994                  3.1069e+06             0.016362           0.96493

    [1] Vallières, Martin, Carolyn R. Freeman, Sonia R. Skamene, and Issam El Naqa. “A Radiomics Model from Joint FDG-PET and MRI Texture Features for the Prediction of Lung Metastases in Soft-Tissue Sarcomas of the Extremities.” The Cancer Imaging Archive, 2015. https://doi.org/10.7937/K9/TCIA.2015.7GO2GSKS.

    [2] Vallières, M, C R Freeman, S R Skamene, and I El Naqa. “A Radiomics Model from Joint FDG-PET and MRI Texture Features for the Prediction of Lung Metastases in Soft-Tissue Sarcomas of the Extremities.” Physics in Medicine and Biology 60, no. 14 (July 7, 2015): 5471–96. https://doi.org/10.1088/0031-9155/60/14/5471.

    [3] Clark, Kenneth, Bruce Vendt, Kirk Smith, John Freymann, Justin Kirby, Paul Koppel, Stephen Moore, et al. “The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository.” Journal of Digital Imaging 26, no. 6 (December 2013): 1045–57. https://doi.org/10.1007/s10278-013-9622-7.

    Input Arguments

    collapse all

    Data and ROI for feature computation, specified as a radiomics object. The radiomics object R contains details of the preprocessed data and region of interest (ROI) from which to compute the features.

    Name-Value Arguments

    Specify optional pairs of arguments as Name1=Value1,...,NameN=ValueN, where Name is the argument name and Value is the corresponding value. Name-value arguments must appear after other arguments, but the order of the pairs does not matter.

    Example: shapeFeatures(R,SubType="2D") computes the shape features on 2D resampled data.

    Category of shape features to compute, specified as one of these options.

    • "basic"

    • "all"

    If you specify "all", the function computes advanced features in addition to basic features. For more information on which specific shape features each category includes, see IBSI Standard and Radiomics Function Feature Correspondences.

    Data Types: char | string

    Resampling from which to compute shape features, specified as one of these options.

    • "2D" — Computes features from the 2D resampled volume.

    • "3D" — Computes features from the 3D resampled volume.

    • "all" — Computes features for both options.

    When you 2D-resample the volume, the function makes the voxel spacing along the x- and y-dimensions isotropic, but the voxel spacing along the z-dimension is the same as in the input volume. When you 3D-resample the volume, the function makes the voxel spacing along all three spatial dimensions isotropic.

    Data Types: char | string

    Output Arguments

    collapse all

    Shape features, returned as a table. The first column in S is LabelID. The subsequent columns are the shape features. For more details on which shape features are computed in each Type and SubType, see IBSI Standard and Radiomics Function Feature Correspondences.

    Version History

    Introduced in R2023b

    expand all

    See Also

    | |

    Topics

    External Websites