Class AlgorithmEvaluateSegmentation

  • All Implemented Interfaces:
    java.awt.event.ActionListener, java.awt.event.WindowListener, java.lang.Runnable, java.util.EventListener

    public class AlgorithmEvaluateSegmentation
    extends AlgorithmBase
    Compares segmentation results of a test image to segmentation results of an ideal gold standard true image. Comparisons are made for contour or polyline vois having the same ids in the 2 images. For each id number, the false negative volume fraction, the false positive volume fraction, and the positive volume fraction are output to the global data text.
    • Field Detail

      • absoluteTrue

        private double absoluteTrue
        total number of id voxels in true image.
      • falseNegative

        private double falseNegative
        where trueImage has id but test image does not.
      • falsePositive

        private double falsePositive
        where trueImage does not have id but test image does.
      • fnvf

        private double fnvf
        false negative volume fraction.
      • fpvf

        private double fpvf
        false positive volume fraction.
      • length

        private int length
        DOCUMENT ME!
      • nTestVOIs

        private int nTestVOIs
        DOCUMENT ME!
      • nTrueVOIs

        private int nTrueVOIs
        DOCUMENT ME!
      • testID

        private int testID
        DOCUMENT ME!
      • testImage

        private ModelImage testImage
        DOCUMENT ME!
      • testLength

        private int testLength
        DOCUMENT ME!
      • tpvf

        private double tpvf
        positive volume fraction.
      • trueFound

        private double trueFound
        number of the absoluteTrue found in the test image.
      • trueID

        private int trueID
        DOCUMENT ME!
    • Constructor Detail

      • AlgorithmEvaluateSegmentation

        public AlgorithmEvaluateSegmentation​(ModelImage trueImage,
                                             ModelImage testImage)
        Creates a new AlgorithmEvaluateSegmentation object.
        Parameters:
        trueImage - image model used as a ideal gold standard
        testImage - image model tested against the trueImage
    • Method Detail

      • finalize

        public void finalize()
        Prepares this class for destruction.
        Overrides:
        finalize in class AlgorithmBase