radiomics

Prepare data and ROI for radiomics feature extraction

Since R2023b

expand all in page

    Description

    The radiomics object and its object functions enable you to preprocess a medical image of any modality, such as MRI, CT, and ultrasound, and compute shape features, intensity features, and texture features from a specified region of interest (ROI). You can use the same set of radiomics features for any medical imaging modality, and for applications such as studying associations between medical imaging features and patient biology or predicting clinical outcomes from medical images. The radiomics features computed using the radiomics object and its object functions comply with the standards provided by the image biomarker standardisation initiative (IBSI).

    Creation

    Syntax

    R = radiomics(data,roi)
    R = radiomics(data,roi,PropertyName=Value)

    Description

    R = radiomics(data,roi) creates a radiomics object for the medical image or volume data and the region of interest (ROI) roi. You can compute shape features, intensity features, and texture features in the ROI of the medical volume using the object. data and roi set the Data and ROILabel properties, respectively.

    example

    R = radiomics(data,roi,PropertyName=Value) sets writable properties of the object, for preprocessing the medical image or volume and region of interest, using one or more optional name-value arguments.

    Input Arguments

    expand all

    Medical image or volume to prepare for radiomics, specified as a 2-D numeric matrix or medicalImage object for a medical image, or a 3-D numeric array or medicalVolume object for a medical volume. This input argument sets the Data property of the radiomics object.

    ROI mask image or volume, specified as a 2-D numeric matrix or medicalImage object for a medical image, or a 3-D numeric array or medicalVolume object for a medical volume. The data type of roi must be the same as the data type of data. If the ROI mask image or volume has multiple ROIs, you must label each ROI with a different value to compute radiomics features separately for each ROI. This input argument sets the ROILabel property of the radiomics object.

    Properties

    expand all

    This property is read-only.

    Medical image or volume to prepare for radiomics, represented as a medicalImage object or a medicalVolume object.

    This property is read-only.

    ROI mask image or volume, represented as a medicalImage object or a medicalVolume object. The data type of ROILabel is the same as the data type of Data. The ROI mask image or volume can have multiple ROIs.

    This property is read-only after object creation.

    Medical volume and ROI mask volume resampling, specified as a numeric or logical 1 (true) or 0 (false). Specify Resample as true to resample the medical volume and ROI mask volume to an isotropic voxel spacing. When the Data and ROILabel properties of the radiomics object are 3-D arrays or medicalVolume objects, the default value of Resample is true.

    Resampling is not applicable for 2-D data. When you specify the Data and ROILabel properties as 2-D matrices or medicalImage objects, the default value is false, and you cannot change it.

    Note

    If you specify Resample as false, the radiomics object ignores the values specified for the ResampledVoxelSpacing, DataResampleMethod, and MaskResampleMethod properties.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

    This property is read-only after object creation.

    Medical image or volume resegmentation, specified as a numeric or logical 1 (true) or 0 (false). Specify Resegment as true to resegment the medical image or volume.

    Note

    If you specify Resegment as false, the radiomics object ignores the values specified for the ResegmentationRange and ExcludeOutliers properties.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

    This property is read-only after object creation.

    Medical image or volume discretization, specified as a numeric or logical 1 (true) or 0 (false). Specify Discretize as true to discretize the medical image or volume for computing intensity histogram features and texture features.

    Note

    If you specify Discretize as false, the radiomics object ignores the values specified for the DiscreteBinSizeOrBinNumber and DiscreteMethod properties.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

    This property is read-only after object creation.

    Medical image or volume discretization for IVH features, specified as a numeric or logical 1 (true) or 0 (false). Specify DiscretizeIVH as true to discretize the medical image or volume for computing intensity volume histogram (IVH) features.

    Note

    If you specify DiscretizeIVH as false, the radiomics object ignores the values specified for the DiscreteIVHBinSizeOrBinNumber and DiscreteIVHMethod properties.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

    This property is read-only after object creation.

    Resampled voxel spacing, specified a positive scalar. This value must be less than half of the minimum spatial dimension of the medical volume. When the Data and ROILabel properties of the radiomics object are 3-D arrays or medicalVolume objects, the default value of ResampledVoxelSpacing is ceil(min(data.VoxelSpacing)).

    As resampling is not applicable for 2-D data, the radiomics object ignores this value when you specify Data and ROILabel properties of the radiomics object as 2-D matrices or medicalImage objects.

    Note

    The radiomics object ignores this value if you specify Resample as false.

    Data Types: single | double

    This property is read-only after object creation.

    Medical volume resampling method, specified as "nearest", "linear", "cubic", or "spline". When the Data and ROILabel properties of the radiomics object are 3-D arrays or medicalVolume objects, the default value of DataResampleMethod is "linear".

    As resampling is not applicable for 2-D data, the radiomics object ignores this value when you specify Data and ROILabel properties of the radiomics object as 2-D matrices or medicalImage objects.

    Note

    The radiomics object ignores this value if you specify Resample as false.

    Data Types: char | string

    This property is read-only after object creation.

    ROI mask volume resampling method, specified as "nearest", "linear", "cubic", or "spline". When the Data and ROILabel properties of the radiomics object are 3-D arrays or medicalVolume objects, the default value of MaskResampleMethod is "linear".

    As resampling is not applicable for 2-D data, the radiomics object ignores this value when you specify Data and ROILabel properties of the radiomics object as 2-D matrices or medicalImage objects.

    Note

    The radiomics object ignores this value if you specify Resample as false.

    Data Types: char | string

    This property is read-only after object creation.

    Resegmentation range, specified as a two-element numeric vector. The object removes pixels or voxels with intensities outside the specified range. By default, the resegmentation range value is empty, and the object does not perform resegmentation.

    Note

    The radiomics object ignores this value if you specify Resegment as false.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    This property is read-only after object creation.

    Outlier exclusion, specified as a numeric or logical 1 (true) or 0 (false). Specify ExcludeOutliers as true to compute the inlier range of the medical image or volume and remove pixels or voxels with intensities outside the inlier range.

    Note

    The radiomics object ignores this value if you specify Resegment as false.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64 | logical

    This property is read-only after object creation.

    Bin size or bin number for discretization, specified as a positive scalar. The functionality of this property differs based on the specified value of the DiscreteMethod property.

    • "FixedBinSize" — The value of DiscreteBinSizeOrNumber specifies the bin size, and must be less than or equal to the maximum intensity value of the medical image or volume.

    • "FixedBinNumber" — The value of DiscreteBinSizeOrNumber specifies the bin number, and must be greater than 1.

    By default, the object scales the range of the medical data scaled by a factor of 0.1 and rounds it, then performs discretization using the rounded range value as the bin size or bin number.

    Note

    The radiomics object ignores this value if you specify Discretize as false.

    Data Types: single | double

    This property is read-only after object creation.

    Discretization method, specified as "FixedBinSize" or "FixedBinNumber".

    Note

    The radiomics object ignores this value if you specify Discretize as false.

    Data Types: char | string

    This property is read-only after object creation.

    Bin size or bin number for discretization for IVH features, specified as a positive scalar. The functionality of this property differs based on the specified value of the DiscreteIVHMethod property.

    • "FixedBinSize" — The value of DiscreteIVHBinSizeOrNumber specifies the bin size, and must be less than or equal to the maximum intensity value of the medical image or volume.

    • "FixedBinNumber" — The value of DiscreteIVHBinSizeOrNumber specifies the bin number, and must be greater than 1.

    By default, the object scales the range of the medical data scaled by a factor of 0.1 and rounds it, then performs discretization using the rounded range value as the bin size or bin number.

    Note

    The radiomics object ignores this value if you specify DiscretizeIVH as false.

    Data Types: single | double | int8 | int16 | int32 | int64 | uint8 | uint16 | uint32 | uint64

    This property is read-only after object creation.

    Discretization method for IVH features, specified as "FixedBinSize" or "FixedBinNumber".

    Note

    The radiomics object ignores this value if you specify DiscretizeIVH as false.

    Data Types: char | string

    Object Functions

    shapeFeaturesRadiomics shape features
    intensityFeaturesRadiomics intensity features
    textureFeaturesRadiomics texture features
    selectFeaturesSelected radiomics features

    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: [1×1 medicalVolume]
                         ROILabel: [1×1 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, intensity, and texture features of the ROI in the CT image volume.

    S = shapeFeatures(R)
    S=1×24 table
    LabelID    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
    _______    ____________    __________________    _________________    ____________________    _______________    _______________    ________________________    ____________    _____________    ___________________    ___________________    _________________    _________________    _________________    ____________    __________    ____________________    __________________    ___________________    _________________    _________________________    _______________________    _____________________

      "1"         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      


    I = intensityFeatures(R)
    I=1×50 table
    LabelID    LocalIntensityPeak3D    GlobalIntensityPeak3D    MeanIntensity3D    IntensityVariance3D    IntensitySkewness3D    IntensityKurtosis3D    MedianIntensity3D    MinimumIntensity3D    TenthIntensityPercentile3D    NinetiethIntensityPercentile3D    MaximumIntensity3D    IntensityInterquartileRange3D    IntensityRange3D    MeanAbsoluteDeviation3D    RobustMeanAbsoluteDeviation3D    MedianAbsoluteDeviation3D    CoefficientOfVariation3D    QuartileCoefficientOfDispersion3D    IntensityEnergy3D    RootMeanSquare3D    MeanDiscretisedIntensity3D    DiscretisedIntensityVariance3D    DiscretisedIntensitySkewness3D    DiscretisedIntensityKurtosis3D    MedianDiscretisedIntensity3D    MinimumDiscretisedIntensity3D    TenthDiscretisedIntensityPercentile3D    NinetiethDiscretisedIntensityPercentile3D    MaximumDiscretisedIntensity3D    IntensityHistogramMode3D    DiscretisedIntensityInterquartileRange3D    DiscretisedIntensityRange3D    IntensityHistogramMeanAbsoluteDeviation3D    IntensityHistogramRobustMeanAbsoluteDeviation3D    IntensityHistogramMedianAbsoluteDeviation3D    IntensityHistogramCoeffcientOfVariation3D    IntensityHistogramQuartileCoeffcientOfDispersion3D    DiscretisedIntensityEntropy3D    DiscretisedIntensityUniformity3D    MaximumHistogramGradient3D    MaximumHistogramGradientIntensity3D    MinimumHistogramGradient3D    MinimumHistogramGradientIntensity3D    TenPercentVolumeFraction3D    NinetyPercentVolumeFraction3D    TenPercentIntensityFraction3D    NinetyPercentIntensityFraction3D    VolumeFractionDifference3D    IntensityFractionDifference3D
    _______    ____________________    _____________________    _______________    ___________________    ___________________    ___________________    _________________    __________________    __________________________    ______________________________    __________________    _____________________________    ________________    _______________________    _____________________________    _________________________    ________________________    _________________________________    _________________    ________________    __________________________    ______________________________    ______________________________    ______________________________    ____________________________    _____________________________    _____________________________________    _________________________________________    _____________________________    ________________________    ________________________________________    ___________________________    _________________________________________    _______________________________________________    ___________________________________________    _________________________________________    __________________________________________________    _____________________________    ________________________________    __________________________    ___________________________________    __________________________    ___________________________________    __________________________    _____________________________    _____________________________    ________________________________    __________________________    _____________________________

      "1"             76.235                  77.672                58.706               855.73                -0.11994               -0.04034                 59                   -31                        21                              96                         148                         39                        179                   23.302                        16.403                         23.294                       0.4983                          0.32773                    2.2674e+08             65.588                   9.5216                          8.6378                           -0.11707                         -0.057331                            10                               1                                    6                                         13                                     18                             10                                  4                                    17                                  2.3549                                          1.7176                                           2.3425                                        0.30867                                            0.2                                       3.5962                            0.096231                           1444                                7                              -1517.5                              13                              0.99048                        0.0056728                           711                               292                             0.9848                           419             


    T = textureFeatures(R)
    T=1×137 table
    LabelID    JointMaximumAveraged3D    JointAverageAveraged3D    JointVarianceAveraged3D    JointEntropyAveraged3D    DifferenceAverageAveraged3D    DifferenceVarianceAveraged3D    DifferenceEntropyAveraged3D    SumAverageAveraged3D    SumVarianceAveraged3D    SumEntropyAveraged3D    AngularSecondMomentAveraged3D    ContrastAveraged3D    DissimilarityAveraged3D    InverseDifferenceAveraged3D    NormalisedInverseDifferenceAveraged3D    InverseDifferenceMomentAveraged3D    NormalisedInverseDifferenceMomentAveraged3D    InverseVarianceAveraged3D    CorrelationAveraged3D    AutoCorrelationAveraged3D    ClusterTendencyAveraged3D    ClusterShadeAveraged3D    ClusterProminenceAveraged3D    InformationCorrelation1Averaged3D    InformationCorrelation2Averaged3D    JointMaximumMerged3D    JointAverageMerged3D    JointVarianceMerged3D    JointEntropyMerged3D    DifferenceAverageMerged3D    DifferenceVarianceMerged3D    DifferenceEntropyMerged3D    SumAverageMerged3D    SumVarianceMerged3D    SumEntropyMerged3D    AngularSecondMomentMerged3D    ContrastMerged3D    DissimilarityMerged3D    InverseDifferenceMerged3D    NormalisedInverseDifferenceMerged3D    InverseDifferenceMomentMerged3D    NormalisedInverseDifferenceMomentMerged3D    InverseVarianceMerged3D    CorrelationMerged3D    AutoCorrelationMerged3D    ClusterTendencyMerged3D    ClusterShadeMerged3D    ClusterProminenceMerged3D    InformationCorrelation1Merged3D    InformationCorrelation2Merged3D    ShortRunsEmphasisAveraged3D    LongRunsEmphasisAveraged3D    LowGrayLevelRunEmphasisAveraged3D    HighGrayLevelRunEmphasisAveraged3D    ShortRunLowGrayLevelEmphasisAveraged3D    ShortRunHighGrayLevelEmphasisAveraged3D    LongRunLowGrayLevelEmphasisAveraged3D    LongRunHighGrayLevelEmphasisAveraged3D    GrayLevelNonUniformityAveraged3D    NormalisedGrayLevelNonUniformityAveraged3D    RunLengthNonUniformityAveraged3D    NormalisedRunLengthNonUniformityAveraged3D    RunPercentageAveraged3D    GrayLevelVarianceAveraged3D    RunLengthVarianceAveraged3D    RunEntropyAveraged3D    ShortRunsEmphasisMerged3D    LongRunsEmphasisMerged3D    LowGrayLevelRunEmphasisMerged3D    HighGrayLevelRunEmphasisMerged3D    ShortRunLowGrayLevelEmphasisMerged3D    ShortRunHighGrayLevelEmphasisMerged3D    LongRunLowGrayLevelEmphasisMerged3D    LongRunHighGrayLevelEmphasisMerged3D    GrayLevelNonUniformityMerged3D    NormalisedGrayLevelNonUniformityMerged3D    RunLengthNonUniformityMerged3D    NormalisedRunLengthNonUniformityMerged3D    RunPercentageMerged3D    GrayLevelVarianceMerged3D    RunLengthVarianceMerged3D    RunEntropyMerged3D    SmallZoneEmphasis3D    LargeZoneEmphasis3D    LowGrayLevelZoneEmphasis3D    HighGrayLevelZoneEmphasis3D    SmallZoneLowGrayLevelEmphasis3D    SmallZoneHighGrayLevelEmphasis3D    LargeZoneLowGrayLevelEmphasis3D    LargeZoneHighGrayLevelEmphasis3D    GrayLevelNonUniformity3D    NormalisedGrayLevelNonUniformity3D    ZoneSizeNonUniformity3D    NormalisedZoneSizeNonUniformity3D    ZonePercentage3D    GrayLevelVariance3D    ZoneSizeVariance3D    ZoneSizeEntropy3D    SmallDistanceEmphasis3D    LargeDistanceEmphasis3D    LowGrayLevelZoneDistanceEmphasis3D    HighGrayLevelZoneDistanceEmphasis3D    SmallDistanceLowGrayLevelEmphasis3D    SmallDistanceHighGrayLevelEmphasis3D    LargeDistanceLowGrayLevelEmphasis3D    LargeDistanceHighGrayLevelEmphasis3D    GrayLevelDistanceNonUniformity3D    NormalisedGrayLevelDistanceNonUniformity3D    ZoneDistanceNonUniformity3D    NormalisedZoneDistanceNonUniformity3D    ZoneDistancePercentage3D    GrayLevelDistanceVariance3D    ZoneDistanceVariance3D    ZoneDistanceEntropy3D    Coarseness3D    Contrast3D    Busyness3D    Complexity3D    Strength3D    LowDependenceEmphasis3D    HighDependenceEmphasis3D    LowGrayLevelCountEmphasis3D    HighGrayLevelCountEmphasis3D    LowDependenceLowGrayLevelEmphasis3D    LowDependenceHighGrayLevelEmphasis3D    HighDependenceLowGrayLevelEmphasis3D    HighDependenceHighGrayLevelEmphasi3D    GrayLevelDependenceNonUniformity3D    NormalisedGrayLevelDependenceNonUniformity3D    DependenceCountNonUniformity3D    NormalisedDependenceCountNonUniformity3D    DependenceCountPercentage3D    GrayLevelDependenceVariance3D    DependenceCountVariance3D    DependenceCountEntropy3D    DependenceCountEnergy3D
    _______    ______________________    ______________________    _______________________    ______________________    ___________________________    ____________________________    ___________________________    ____________________    _____________________    ____________________    _____________________________    __________________    _______________________    ___________________________    _____________________________________    _________________________________    ___________________________________________    _________________________    _____________________    _________________________    _________________________    ______________________    ___________________________    _________________________________    _________________________________    ____________________    ____________________    _____________________    ____________________    _________________________    __________________________    _________________________    __________________    ___________________    __________________    ___________________________    ________________    _____________________    _________________________    ___________________________________    _______________________________    _________________________________________    _______________________    ___________________    _______________________    _______________________    ____________________    _________________________    _______________________________    _______________________________    ___________________________    __________________________    _________________________________    __________________________________    ______________________________________    _______________________________________    _____________________________________    ______________________________________    ________________________________    __________________________________________    ________________________________    __________________________________________    _______________________    ___________________________    ___________________________    ____________________    _________________________    ________________________    _______________________________    ________________________________    ____________________________________    _____________________________________    ___________________________________    ____________________________________    ______________________________    ________________________________________    ______________________________    ________________________________________    _____________________    _________________________    _________________________    __________________    ___________________    ___________________    __________________________    ___________________________    _______________________________    ________________________________    _______________________________    ________________________________    ________________________    __________________________________    _______________________    _________________________________    ________________    ___________________    __________________    _________________    _______________________    _______________________    __________________________________    ___________________________________    ___________________________________    ____________________________________    ___________________________________    ____________________________________    ________________________________    __________________________________________    ___________________________    _____________________________________    ________________________    ___________________________    ______________________    _____________________    ____________    __________    __________    ____________    __________    _______________________    ________________________    ___________________________    ____________________________    ___________________________________    ____________________________________    ____________________________________    ____________________________________    __________________________________    ____________________________________________    ______________________________    ________________________________________    ___________________________    _____________________________    _________________________    ________________________    _______________________

      "1"             0.023811                   9.6016                    8.3563                     6.8904                      2.3407                          3.5474                         2.7164                      19.203                  24.082                   4.3302                     0.011903                     9.3434                  2.3407                       0.42572                             0.89254                                0.34697                                   0.97367                               0.34478                    0.44066                    95.876                       24.082                     -14.219                      1766.6                           -0.071978                             0.51232                       0.02387                  9.6014                   8.357                   6.9797                    2.3355                        3.8557                        2.796                    19.203                24.118                 4.3401                   0.011132                   9.3101                2.3355                     0.42635                           0.89275                              0.34775                                 0.97376                             0.34535                  0.44298                  95.889                     24.118                   -14.595                    1772.3                         -0.047062                           0.53447                          0.8948                         1.6184                          0.022051                               99.343                                 0.020252                                   88.924                                   0.032272                                   160.51                                 4252.9                                  0.093867                                  34781                                   0.76314                              0.85952                      8.9998                         0.24022                     4.2908                    0.89739                      1.5847                        0.022046                             99.351                               0.020307                                 89.195                                 0.031637                                 157.17                               55285                                 0.093871                              4.5075e+05                              0.76535                            0.85952                    8.9979                       0.23116                   4.2962                0.54053                 21751                    0.044971                       101.61                          0.026927                             55.289                             237.38                            2.1404e+06                        398.92                          0.065861                         1677.4                          0.27694                     0.11492               18.452                 21676                6.6843                  0.37615                    38.684                          0.044971                               101.61                                0.023829                                 29.867                                 1.1708                                  4444.5                                398.92                                  0.065861                               901.04                              0.14876                           0.11492                       18.452                       16.962                   7.3218             0.00015653      0.088117       36.374         194.83        0.015559             0.12867                     26.96                       0.021291                         99.298                            0.0046226                                12.944                                  0.422                                   2663.2                                 5072.2                                    0.096231                                  6725.7                                 0.1276                                  1                            8.6377                         5.3148                       6.6704                    0.012506

    Compute selected radiomics features for a 2-D slice of the CT image volume.

    dataSlice = data.Voxels(:,:,20);
roiSlice = roi.Voxels(:,:,20);
R2D = radiomics(dataSlice,roiSlice)
    R2D = 
  radiomics with properties:

                             Data: [1×1 medicalImage]
                         ROILabel: [1×1 medicalImage]
                         Resample: 0
                        Resegment: 1
                       Discretize: 1
                    DiscretizeIVH: 1
            ResampledVoxelSpacing: []
               DataResampleMethod: []
               MaskResampleMethod: []
              ResegmentationRange: []
                  ExcludeOutliers: 1
       DiscreteBinSizeOrBinNumber: []
                   DiscreteMethod: 'FixedBinNumber'
    DiscreteIVHBinSizeOrBinNumber: []
                DiscreteIVHMethod: 'FixedBinNumber'


    F = selectFeatures(R2D,["AreaDensityConvexHull2D","MaximumHistogramGradient2D","Complexity2D"])
    F=1×4 table
    LabelID    AreaDensityConvexHull2D    MaximumHistogramGradient2D    Complexity2D
    _______    _______________________    __________________________    ____________

      "1"              0.97913                        15                   882.61

    [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.

    Open Live Script

    Import a magnetic resonance (MR) image volume from the IBSI validation data set [1][2][3] as a medicalVolume object.

    unzip("MRImageMaskDICOM.zip")
data = medicalVolume("MR_image");

    Read the corresponding DICOM metadata from the DICOM-RT structure set file. Extract the ROI data from the structure set and ROI contour modules of the DICOM metadata.

    info = dicominfo("MR_mask/RS.dcm");
contours = dicomContours(info);
contourIndex = 1;

    Get the spatial details of the DICOM volume. Create an ROI mask volume as a medicalVolume object from the spatial details and ROI contour.

    [~,spatial] = dicomreadVolume("MR_image");
roi = createMask(contours,contourIndex,spatial);
roi = permute(roi,[2 1 3]);
roi = medicalVolume(uint8(roi),data.VolumeGeometry);

    Visualize a slice of the MR 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 MR image volume and ROI mask volume, with default preprocessing options.

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

                             Data: [1×1 medicalVolume]
                         ROILabel: [1×1 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, intensity, and texture features of the ROI in the MR image volume.

    S = shapeFeatures(R)
    S=1×24 table
    LabelID    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
    _______    ____________    __________________    _________________    ____________________    _______________    _______________    ________________________    ____________    _____________    ___________________    ___________________    _________________    _________________    _________________    ____________    __________    ____________________    __________________    ___________________    _________________    _________________________    _______________________    _____________________

      "1"         52977              53029                 8267                 0.15605              0.039764            0.5618                  1.2119               0.82514          0.21192             0.58271                57.044                50.077               44.011               33.814            0.87885        0.67523             0.5173                0.62186                1.3577                1.3919                   0.91396                      1.092                  1.9964e+07      


    I = intensityFeatures(R)
    I=1×50 table
    LabelID    LocalIntensityPeak3D    GlobalIntensityPeak3D    MeanIntensity3D    IntensityVariance3D    IntensitySkewness3D    IntensityKurtosis3D    MedianIntensity3D    MinimumIntensity3D    TenthIntensityPercentile3D    NinetiethIntensityPercentile3D    MaximumIntensity3D    IntensityInterquartileRange3D    IntensityRange3D    MeanAbsoluteDeviation3D    RobustMeanAbsoluteDeviation3D    MedianAbsoluteDeviation3D    CoefficientOfVariation3D    QuartileCoefficientOfDispersion3D    IntensityEnergy3D    RootMeanSquare3D    MeanDiscretisedIntensity3D    DiscretisedIntensityVariance3D    DiscretisedIntensitySkewness3D    DiscretisedIntensityKurtosis3D    MedianDiscretisedIntensity3D    MinimumDiscretisedIntensity3D    TenthDiscretisedIntensityPercentile3D    NinetiethDiscretisedIntensityPercentile3D    MaximumDiscretisedIntensity3D    IntensityHistogramMode3D    DiscretisedIntensityInterquartileRange3D    DiscretisedIntensityRange3D    IntensityHistogramMeanAbsoluteDeviation3D    IntensityHistogramRobustMeanAbsoluteDeviation3D    IntensityHistogramMedianAbsoluteDeviation3D    IntensityHistogramCoeffcientOfVariation3D    IntensityHistogramQuartileCoeffcientOfDispersion3D    DiscretisedIntensityEntropy3D    DiscretisedIntensityUniformity3D    MaximumHistogramGradient3D    MaximumHistogramGradientIntensity3D    MinimumHistogramGradient3D    MinimumHistogramGradientIntensity3D    TenPercentVolumeFraction3D    NinetyPercentVolumeFraction3D    TenPercentIntensityFraction3D    NinetyPercentIntensityFraction3D    VolumeFractionDifference3D    IntensityFractionDifference3D
    _______    ____________________    _____________________    _______________    ___________________    ___________________    ___________________    _________________    __________________    __________________________    ______________________________    __________________    _____________________________    ________________    _______________________    _____________________________    _________________________    ________________________    _________________________________    _________________    ________________    __________________________    ______________________________    ______________________________    ______________________________    ____________________________    _____________________________    _____________________________________    _________________________________________    _____________________________    ________________________    ________________________________________    ___________________________    _________________________________________    _______________________________________________    ___________________________________________    _________________________________________    __________________________________________________    _____________________________    ________________________________    __________________________    ___________________________________    __________________________    ___________________________________    __________________________    _____________________________    _____________________________    ________________________________    __________________________    _____________________________

      "1"             716.07                  716.07                376.84               5820.4                 1.6378                 2.2078                  351                  265                       311                             495                         662                         72                        397                   56.834                        34.043                          51.62                      0.20245                         0.099448                    7.6772e+09             384.49                   11.766                          59.148                            1.6361                            2.1973                             9                                1                                    5                                         24                                     40                             7                                   7                                    39                                  5.7308                                          3.5845                                           5.1877                                        0.65364                                          0.33333                                     4.4234                            0.064718                          2057.5                               4                               -966.5                              10                              0.95596                         0.01398                            581                               117                            0.94198                           464             


    T = textureFeatures(R)
    T=1×137 table
    LabelID    JointMaximumAveraged3D    JointAverageAveraged3D    JointVarianceAveraged3D    JointEntropyAveraged3D    DifferenceAverageAveraged3D    DifferenceVarianceAveraged3D    DifferenceEntropyAveraged3D    SumAverageAveraged3D    SumVarianceAveraged3D    SumEntropyAveraged3D    AngularSecondMomentAveraged3D    ContrastAveraged3D    DissimilarityAveraged3D    InverseDifferenceAveraged3D    NormalisedInverseDifferenceAveraged3D    InverseDifferenceMomentAveraged3D    NormalisedInverseDifferenceMomentAveraged3D    InverseVarianceAveraged3D    CorrelationAveraged3D    AutoCorrelationAveraged3D    ClusterTendencyAveraged3D    ClusterShadeAveraged3D    ClusterProminenceAveraged3D    InformationCorrelation1Averaged3D    InformationCorrelation2Averaged3D    JointMaximumMerged3D    JointAverageMerged3D    JointVarianceMerged3D    JointEntropyMerged3D    DifferenceAverageMerged3D    DifferenceVarianceMerged3D    DifferenceEntropyMerged3D    SumAverageMerged3D    SumVarianceMerged3D    SumEntropyMerged3D    AngularSecondMomentMerged3D    ContrastMerged3D    DissimilarityMerged3D    InverseDifferenceMerged3D    NormalisedInverseDifferenceMerged3D    InverseDifferenceMomentMerged3D    NormalisedInverseDifferenceMomentMerged3D    InverseVarianceMerged3D    CorrelationMerged3D    AutoCorrelationMerged3D    ClusterTendencyMerged3D    ClusterShadeMerged3D    ClusterProminenceMerged3D    InformationCorrelation1Merged3D    InformationCorrelation2Merged3D    ShortRunsEmphasisAveraged3D    LongRunsEmphasisAveraged3D    LowGrayLevelRunEmphasisAveraged3D    HighGrayLevelRunEmphasisAveraged3D    ShortRunLowGrayLevelEmphasisAveraged3D    ShortRunHighGrayLevelEmphasisAveraged3D    LongRunLowGrayLevelEmphasisAveraged3D    LongRunHighGrayLevelEmphasisAveraged3D    GrayLevelNonUniformityAveraged3D    NormalisedGrayLevelNonUniformityAveraged3D    RunLengthNonUniformityAveraged3D    NormalisedRunLengthNonUniformityAveraged3D    RunPercentageAveraged3D    GrayLevelVarianceAveraged3D    RunLengthVarianceAveraged3D    RunEntropyAveraged3D    ShortRunsEmphasisMerged3D    LongRunsEmphasisMerged3D    LowGrayLevelRunEmphasisMerged3D    HighGrayLevelRunEmphasisMerged3D    ShortRunLowGrayLevelEmphasisMerged3D    ShortRunHighGrayLevelEmphasisMerged3D    LongRunLowGrayLevelEmphasisMerged3D    LongRunHighGrayLevelEmphasisMerged3D    GrayLevelNonUniformityMerged3D    NormalisedGrayLevelNonUniformityMerged3D    RunLengthNonUniformityMerged3D    NormalisedRunLengthNonUniformityMerged3D    RunPercentageMerged3D    GrayLevelVarianceMerged3D    RunLengthVarianceMerged3D    RunEntropyMerged3D    SmallZoneEmphasis3D    LargeZoneEmphasis3D    LowGrayLevelZoneEmphasis3D    HighGrayLevelZoneEmphasis3D    SmallZoneLowGrayLevelEmphasis3D    SmallZoneHighGrayLevelEmphasis3D    LargeZoneLowGrayLevelEmphasis3D    LargeZoneHighGrayLevelEmphasis3D    GrayLevelNonUniformity3D    NormalisedGrayLevelNonUniformity3D    ZoneSizeNonUniformity3D    NormalisedZoneSizeNonUniformity3D    ZonePercentage3D    GrayLevelVariance3D    ZoneSizeVariance3D    ZoneSizeEntropy3D    SmallDistanceEmphasis3D    LargeDistanceEmphasis3D    LowGrayLevelZoneDistanceEmphasis3D    HighGrayLevelZoneDistanceEmphasis3D    SmallDistanceLowGrayLevelEmphasis3D    SmallDistanceHighGrayLevelEmphasis3D    LargeDistanceLowGrayLevelEmphasis3D    LargeDistanceHighGrayLevelEmphasis3D    GrayLevelDistanceNonUniformity3D    NormalisedGrayLevelDistanceNonUniformity3D    ZoneDistanceNonUniformity3D    NormalisedZoneDistanceNonUniformity3D    ZoneDistancePercentage3D    GrayLevelDistanceVariance3D    ZoneDistanceVariance3D    ZoneDistanceEntropy3D    Coarseness3D    Contrast3D    Busyness3D    Complexity3D    Strength3D    LowDependenceEmphasis3D    HighDependenceEmphasis3D    LowGrayLevelCountEmphasis3D    HighGrayLevelCountEmphasis3D    LowDependenceLowGrayLevelEmphasis3D    LowDependenceHighGrayLevelEmphasis3D    HighDependenceLowGrayLevelEmphasis3D    HighDependenceHighGrayLevelEmphasi3D    GrayLevelDependenceNonUniformity3D    NormalisedGrayLevelDependenceNonUniformity3D    DependenceCountNonUniformity3D    NormalisedDependenceCountNonUniformity3D    DependenceCountPercentage3D    GrayLevelDependenceVariance3D    DependenceCountVariance3D    DependenceCountEntropy3D    DependenceCountEnergy3D
    _______    ______________________    ______________________    _______________________    ______________________    ___________________________    ____________________________    ___________________________    ____________________    _____________________    ____________________    _____________________________    __________________    _______________________    ___________________________    _____________________________________    _________________________________    ___________________________________________    _________________________    _____________________    _________________________    _________________________    ______________________    ___________________________    _________________________________    _________________________________    ____________________    ____________________    _____________________    ____________________    _________________________    __________________________    _________________________    __________________    ___________________    __________________    ___________________________    ________________    _____________________    _________________________    ___________________________________    _______________________________    _________________________________________    _______________________    ___________________    _______________________    _______________________    ____________________    _________________________    _______________________________    _______________________________    ___________________________    __________________________    _________________________________    __________________________________    ______________________________________    _______________________________________    _____________________________________    ______________________________________    ________________________________    __________________________________________    ________________________________    __________________________________________    _______________________    ___________________________    ___________________________    ____________________    _________________________    ________________________    _______________________________    ________________________________    ____________________________________    _____________________________________    ___________________________________    ____________________________________    ______________________________    ________________________________________    ______________________________    ________________________________________    _____________________    _________________________    _________________________    __________________    ___________________    ___________________    __________________________    ___________________________    _______________________________    ________________________________    _______________________________    ________________________________    ________________________    __________________________________    _______________________    _________________________________    ________________    ___________________    __________________    _________________    _______________________    _______________________    __________________________________    ___________________________________    ___________________________________    ____________________________________    ___________________________________    ____________________________________    ________________________________    __________________________________________    ___________________________    _____________________________________    ________________________    ___________________________    ______________________    _____________________    ____________    __________    __________    ____________    __________    _______________________    ________________________    ___________________________    ____________________________    ___________________________________    ____________________________________    ____________________________________    ____________________________________    __________________________________    ____________________________________________    ______________________________    ________________________________________    ___________________________    _____________________________    _________________________    ________________________    _______________________

      "1"             0.055201                   11.152                    49.523                     7.1139                      1.7744                          6.5868                         2.5284                      22.304                  188.25                   5.279                      0.020007                     9.8416                  1.7744                       0.58486                             0.96071                                0.54425                                   0.99421                               0.37181                    0.89929                    168.99                       188.25                       4341                     1.9593e+05                         -0.35169                              0.97251                       0.054921                 11.154                  49.561                   7.1632                    1.7706                        6.6692                       2.5465                    22.307                188.44                 5.2854                   0.019688                   9.8041                1.7706                     0.58533                           0.96079                              0.54477                                 0.99423                             0.3717                   0.90109                  169.06                     188.44                    4353.5                  1.9663e+05                       -0.34081                            0.97328                          0.79186                        3.639                           0.014285                               255.46                                0.0097224                                   235.58                                   0.077719                                   443.56                                 1736.7                                  0.049595                                  20497                                   0.58478                               0.672                       70.681                         1.3817                      5.8533                    0.79358                      3.5532                        0.014342                             254.45                              0.0098114                                 234.83                                  0.07564                                 436.57                               22493                                 0.049578                              2.6594e+05                              0.58617                             0.672                     70.759                       1.3388                    5.8673                0.62345                 23996                   0.0044919                        582.9                          0.0023151                            382.95                             514.26                            1.4324e+06                        199.65                          0.032686                         2210.5                          0.36191                     0.11761               71.698                 23924                7.1635                  0.58649                    5.8012                         0.0044919                                582.9                                0.0019566                                378.98                                0.057854                                 2508.2                                199.65                                  0.032686                               2057.9                              0.33692                           0.11761                       71.698                       1.904                    6.9196             0.00051829      0.070477       5.531          610.45        0.44531              0.11335                     135.06                      0.017226                         197.59                           0.00062986                                59.623                                  3.3416                                  8548.8                                  3361                                     0.064718                                  2707.1                                0.052127                                 1                            59.146                         44.279                       8.2752                    0.0038749

    Compute selected radiomics features for a 2-D slice of the MR image volume.

    dataSlice = data.Voxels(:,:,20);
roiSlice = roi.Voxels(:,:,20);
R2D = radiomics(dataSlice,roiSlice)
    R2D = 
  radiomics with properties:

                             Data: [1×1 medicalImage]
                         ROILabel: [1×1 medicalImage]
                         Resample: 0
                        Resegment: 1
                       Discretize: 1
                    DiscretizeIVH: 1
            ResampledVoxelSpacing: []
               DataResampleMethod: []
               MaskResampleMethod: []
              ResegmentationRange: []
                  ExcludeOutliers: 1
       DiscreteBinSizeOrBinNumber: []
                   DiscreteMethod: 'FixedBinNumber'
    DiscreteIVHBinSizeOrBinNumber: []
                DiscreteIVHMethod: 'FixedBinNumber'


    F = selectFeatures(R2D,["SphericalDisproportion2D","LocalIntensityPeak2D","IntensityVariance2D","DifferenceEntropyAveraged2D"])
    F=1×5 table
    LabelID    SphericalDisproportion2D    LocalIntensityPeak2D    IntensityVariance2D    DifferenceEntropyAveraged2D
    _______    ________________________    ____________________    ___________________    ___________________________

      "1"               5.0986                    614.26                 2140.8                     2.1156

    [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.

    Version History

    Introduced in R2023b

    expand all

    See Also

    Topics

    External Websites