Class JDialogSK10_MRI_CED_map_pre

All Implemented Interfaces:
AlgorithmInterface, DialogDefaultsInterface, ActionListener, FocusListener, ItemListener, WindowListener, ImageObserver, MenuContainer, Serializable, EventListener, Accessible, RootPaneContainer, WindowConstants

public class JDialogSK10_MRI_CED_map_pre extends JDialogBase implements AlgorithmInterface
This class generates the knees VOI contours from the deep learning (HNN) MRI and CED energy maps.
Author:
Ruida Cheng
See Also:
  • Field Details

  • Constructor Details

    • JDialogSK10_MRI_CED_map_pre

      public JDialogSK10_MRI_CED_map_pre(Frame theParentFrame)
      Constructor.
      Parameters:
      theParentFrame -
  • Method Details

    • disposeLocal

      public void disposeLocal()
      dispose memory
    • actionPerformed

      public void actionPerformed(ActionEvent event)
      Dialog local actionPerformed handler.
      Specified by:
      actionPerformed in interface ActionListener
      Overrides:
      actionPerformed in class JDialogBase
    • sortImageTable

      private void sortImageTable()
      Sort the testing image directory in accending order.
    • pause

      public static void pause()
    • recordSaveImageDir

      private void recordSaveImageDir()
      Let user specify the saved 2D slices atlas, record the save directory.
    • readKeyImageDir

      private void readKeyImageDir()
      Parsing 3D images directory and the HNN generated probablity maps directory
    • traverse_image_folder

      private void traverse_image_folder(File dir, String hashID)
      Traverse the test image folder
    • read_image_name

      private void read_image_name(File dir)
      Grab the test image in mipav .xml file format.
      Parameters:
      dir - image sub-directory name
    • traverse_folder_map

      private void traverse_folder_map(File dir)
    • traverse_folder_map

      private void traverse_folder_map(File dir, int index)
      Traverse the HNN subdirectories.
      Parameters:
      dir - directory name
      index - map index
    • processDir_folder_map

      private void processDir_folder_map(File dir, int index)
      HNN generates multi-scaled prediction output. We use fuse layer generated output as the energy map to inference the VOI contour.
      Parameters:
      dir - sub-directory name.
      index - probablity map index
    • algorithmPerformed

      public void algorithmPerformed(AlgorithmBase algorithm)
      This method is required if the AlgorithmPerformed interface is implemented. It is called by the algorithms when it has completed or failed to to complete, so that the dialog can be display the result image and/or clean up.
      Specified by:
      algorithmPerformed in interface AlgorithmInterface
      Parameters:
      algorithm - Algorithm that caused the event.
    • callAlgorithm

      public void callAlgorithm()
      Driver function to read image and VOIs, and convert each 3D image to 2D slices.
    • generateContours

      private void generateContours()
      Generate the VOI contours from the probablity maps.
    • generateContours_MRI

      private void generateContours_MRI()
      Generate the VOI contours from MRI prediction only. As one ablation experiment in the MRM paper.
    • smoothVOI30

      public void smoothVOI30(ModelImage maskImage, ModelImage resultImage)
      Smooth generated VOI contours by 30 points.
      Parameters:
      maskImage - mask image
      resultImage - result image to hold the resulting smoothed VOI contour.
    • readFile

      public void readFile()
      Read testing images and the HNN predcited probability maps.
    • init

      public void init()
      Initial panel
    • buildKeyImagePanel

      public void buildKeyImagePanel()
      Panel contains both the 3D image dir and saved 2D slices atlas dir.