TubeTK/Documentation/EnhanceTubesUsingDiscriminantAnalysis

From KitwarePublic
Jump to navigationJump to search
  Description: Given an image and foreground and background masks,
  computes multiscale Jet (0, 1, and 2 order) features at each pixel,
  performs a multivariate LDA or PCA for separating the classes, and
  generates the LDA/PCA instances of the images.

USAGE:

  ./EnhanceTubesUsingDiscriminantAnalysis  [--returnparameterfile
                                       <std::string>]
                                       [--processinformationaddress
                                       <std::string>] [--xml] [--echo]
                                       [--saveFeatureImages <std::string>]
                                       [--seedTolerance <double>]
                                       [--loadDiscriminantInfo
                                       <std::string>] [-i] [--tubeScales
                                       <std::vector<double>>]
                                       [--outputSeedScaleImage
                                       <std::string>]
                                       [--saveDiscriminantInfo
                                       <std::string>] [--unknownId <int>]
                                       [--backgroundId <int>] [--tubeId
                                       <int>] [--labelmap <std::string>]
                                       [--] [--version] [-h] <std::string>
                                       <std::string>


Where:

  --returnparameterfile <std::string>
    Filename in which to write simple return parameters (int, float,
    int-vector, etc.) as opposed to bulk return parameters (image,
    geometry, transform, measurement, table).
  --processinformationaddress <std::string>
    Address of a structure to store process information (progress, abort,
    etc.). (default: 0)
  --xml
    Produce xml description of command line arguments (default: 0)
  --echo
    Echo the command line arguments (default: 0)
  --saveFeatureImages <std::string>
    Base filename for saving feature images.
  --seedTolerance <double>
    Tradeoff between sensitivity and specificity (higher value = more
    seeds) (default: 1)
  --loadDiscriminantInfo <std::string>
    Load learned enhancement parameters from a file.
  -i,  --useIntensityOnly
    Use intensity information at each scale only (default: 0)
  --tubeScales <std::vector<double>>
    Scales at which tube features are computed. (default: 1,2,4)
  --outputSeedScaleImage <std::string>
    Image that contains the chosen seed scale at each voxel.
  --saveDiscriminantInfo <std::string>
    Save learned enhancement parameters to a file.
  --unknownId <int>
    Value for unlabeled points in the label map. (default: 0)
  --backgroundId <int>
    Value for background points in the label map. (default: 127)
  --tubeId <int>
    Value for tube points in the label map. (default: 255)
  --labelmap <std::string>
    Label map for object of interest and 'other.'
  --,  --ignore_rest
    Ignores the rest of the labeled arguments following this flag.
  --version
    Displays version information and exits.
  -h,  --help
    Displays usage information and exits.
  <std::string>
    (required)  Input volume list.
  <std::string>
    (required)  Output image having enhanced tubes
  Author(s): Stephen R. Aylward (Kitware)
  Acknowledgements: This work is part of the TubeTK project at Kitware.