Package gov.nih.mipav.model.algorithms

Class AlgorithmSkullRemoval

java.lang.Object
java.lang.Thread
gov.nih.mipav.model.algorithms.AlgorithmBase
gov.nih.mipav.model.algorithms.AlgorithmSkullRemoval
All Implemented Interfaces:
ActionListener, WindowListener, Runnable, EventListener
public class AlgorithmSkullRemoval extends AlgorithmBase
Algorithm Implementation 1. Calculate the input image histogram. 2. Calculate the image values that represent 2% and 98% of the histogram values and clamp the input image data to that range. 3. Set the cerebrospinal fluid (CSF) threshold minimum value to 30 % of the clamped image range and the CSF threshold maximum value to 70% of the clamped image range. 4. Calculate the brain center of gravity (COG) as the weighted sum of all voxels between the CSF minimum and maximum range using the voxel position scaled by intensity value. 5. Estimate the white matter threshold by segmenting the image into 5x5x5 voxel cubes and finding the cube with the highest mean intensity and lowest variance. The mean intensity of the selected cube is used to set the white matter threshold value. 6. Generate a white-matter segmentation of the brain by using a flood-fill algorithm with the white matter threshold seed point as the starting point. The flood-fill algorithm is limited by the CSF threshold values as well as a radius centered around the initial seed point. 7. Take the convex-hull of the white matter segmentation and pass this mesh into a modified version of the AlgorithmBrainExtractor. 8. The output of the AlgorithmBrainExtractor is a segmented mesh representing the surface of the brain. To err on the side of not removing too much data, the convex-hull of the brain surface is generated. 9. The final mask representing the data outside the brain is generated using all voxels outside the convex-hull of the brain surface. 10. (Optional final step). If the user chooses to segment only the face region instead of the entire skull region the final step produces the face segmentation from the convex-hull of the brain surface.

  • Field Details

    • faceOrientation

      private int faceOrientation
      Face Orientation is left:

    • min_2P

      private float min_2P
      Value representing 2% of the histogram count:

    • max_98P

      private float max_98P
      Value representing 98% of the histogram count:

    • csfThresholdMin

      private float csfThresholdMin
      Cerebrospinal Fluid (CSF) minimum threshold :

    • csfThresholdMax

      private float csfThresholdMax
      Cerebrospinal Fluid (CSF) maximum threshold :

    • wmThreshold

      private float wmThreshold
      White Matter threshold :

    • gmThresholdMin

      private float gmThresholdMin
      Gray Matter minimum threshold :

    • gmThresholdMax

      private float gmThresholdMax
      Gray Matter maximum threshold :

    • cog

      private WildMagic.LibFoundation.Mathematics.Vector3f cog
      Center of Gravity :

    • dimX

      private int dimX

    • dimY

      private int dimY

    • dimZ

      private int dimZ

    • blur

      private boolean blur
      when true, blur the output

    • remove

      private boolean remove
      when true, remove the output

    • face

      private boolean face
      when true, compute face segmentation instead of skull

    • showFaceSegmentation

      private boolean showFaceSegmentation
      when true, display the face segmentation

    • showSkullSegmentation

      private boolean showSkullSegmentation
      when true, display the skull segmentation

    • offSet

      private float offSet
      Optional offset (in mm) boundary around the segmented region

    • originalAxis

      private int[] originalAxis
      stores the original image orientation axis

    • targetAxis

      private int[] targetAxis
      the orientation the images are remapped to before processing:

    • originalAxisTargetAtlas

      private int[] originalAxisTargetAtlas
      stores the original image orientation axis (used for the target image when an atlas image is present)

    • reMappedSrc

      private boolean reMappedSrc
      When true the source image was remapped

    • reMappedTargetAtlas

      private boolean reMappedTargetAtlas
      When true the target image was remapped (used for the target image when an atlas image is present)

    • atlasBasedImage

      private ModelImage atlasBasedImage
      atlas image:

    • registeredSourceImage

      private ModelImage registeredSourceImage
      registered atlas image

    • originalSrc

      private ModelImage originalSrc
      original source image

  • Constructor Details

    • AlgorithmSkullRemoval

      public AlgorithmSkullRemoval(ModelImage srcImg)
      Automatic DeSkulling initialization.
      Parameters:
      srcImg - The image to segment.

    • AlgorithmSkullRemoval

      public AlgorithmSkullRemoval(ModelImage srcImg, ModelImage atlasImage)
      Automatic DeSkulling initialization.
      Parameters:
      srcImg - The image to segment.
      atlasImage - The atlas image.

  • Method Details

    • finalize

      public void finalize()
      Clean up memory used by the algorithm.
      Overrides:
      finalize in class AlgorithmBase

    • runAlgorithm

      public void runAlgorithm()
      Run the de-facing algorithm.
      Specified by:
      runAlgorithm in class AlgorithmBase

    • setOffSet

      public void setOffSet(float offSet)
      Set the boundary offset parameter in mm.
      Parameters:
      offSet -

    • setOutputOption

      public void setOutputOption(boolean blur, boolean remove, boolean face, boolean showFaceSegmentation, boolean showSkullSegmentation)
      Set the output options
      Parameters:
      blur - when true blur the segmented region
      remove - when true remove the segmented region
      face - when true segment the face
      showFaceSegmentation - when true show the face segmentation
      showSkullSegmentation - when true show the skull segmentation

    • addBlur

      private void addBlur(ModelImage blurImage, ModelImage destImage)
      Combines the randomized-voxel blurred image with the output image. Only the areas that are in the segmented region are modified by the blur.
      Parameters:
      blurImage -
      destImage -

    • computeSurfaceMask

      private BitSet computeSurfaceMask(WildMagic.LibGraphics.SceneGraph.TriMesh mesh)
      Computes a volume mask of the triangle mesh surface. The BitSet mask volume has the same volume dimensions as the current image. The mask is used to show the surface-plane intersections in the slice views.
      Parameters:
      mesh - triangle mesh to convert to a volume mask representation.
      Returns:
      BitSet mask, which is set to true wherever the triangle mesh intersects the volume voxel.

    • convexHull

      private WildMagic.LibGraphics.SceneGraph.TriMesh convexHull(WildMagic.LibGraphics.SceneGraph.TriMesh mesh)
      Compute the convex hull of the input mesh, return the convex hull.
      Parameters:
      mesh -
      Returns:

    • createMask

      private BitSet createMask(WildMagic.LibFoundation.Mathematics.Plane3f clipPlane, WildMagic.LibFoundation.Mathematics.Vector3f cog)

    • createMask

      private BitSet createMask(WildMagic.LibGraphics.SceneGraph.TriMesh mesh, boolean show, String postScript)

    • createMesh

      private WildMagic.LibGraphics.SceneGraph.TriMesh createMesh(BitSet mask)

    • createMesh

      private WildMagic.LibGraphics.SceneGraph.TriMesh createMesh(ModelImage image)

    • distance

      private float distance(WildMagic.LibFoundation.Mathematics.Vector3f cog, int x, int y, int z)

    • estimateParameters

      private void estimateParameters()
      1. Calculate the input image histogram. 2. Calculate the image values that represent 2% and 98% of the histogram values and clamp the input image data to that range. 3. Set the cerebrospinal fluid (CSF) threshold minimum value to 30 % of the clamped image range and the CSF threshold maximum value to 70% of the clamped image range. 4. Calculate the brain center of gravity (COG) as the weighted sum of all voxels between the CSF minimum and maximum range using the voxel position scaled by intensity value. Steps 1-4: The preprocessed steps generate the center of gravity (COG) and cerebrospinal fluid (CSF) thresholds, which are used to find the initial white-matter seed point. Potential white-matter seed points are limited to a radius around the COG. The minimum variance is selected from potential seed points with a maximum mean-intensity greater than the CSF threshold. These steps prevent the algorithm from finding a seed point in the background, where the variance may be zero but where the intensity is lower than the CSF threshold.

    • estimateWhiteMatter

      private VOI estimateWhiteMatter(ModelImage image)
      5. Estimate the white matter threshold by segmenting the image into 5x5x5 voxel cubes and finding the cube with the highest mean intensity and lowest variance. The mean intensity of the selected cube is used to set the white matter threshold value.
      Parameters:
      image - image remapped to the robust image range.
      Returns:
      initial white-matter seed point(s).

    • fill

      private void fill(ModelImage image, WildMagic.LibFoundation.Mathematics.Vector3f centerBound, Vector<WildMagic.LibFoundation.Mathematics.Vector3f> seedList, BitSet visited, BitSet whiteMatter)

    • fill

      private void fill(Vector<WildMagic.LibFoundation.Mathematics.Vector3f> seedList, BitSet visited, BitSet mask)

    • fillWhiteMatter

      private void fillWhiteMatter(ModelImage image, VOI seedPoints)
      Once the white-matter seed point is found it is used to initialize a flood-fill algorithm that segments the white-matter of the brain. The seed point is typically found in one hemisphere of the brain. The first step in initializing the flood-fill algorithm is to generate a mirror-image seed-point located in the opposite hemisphere. This enables the flood-fill algorithm to work equally well on both hemispheres. The flood-fill algorithm is limited to an ellipsoid shape around the COG, where the long axis of the ellipsoid is anterior-to-posterior and the short axes of the ellipsoid are superior-to-inferior and left-to-right.
      Parameters:
      image -
      seedPoints -

    • floodFill

      private void floodFill(BitSet mask, WildMagic.LibFoundation.Mathematics.Vector3f cog)

    • generateConvexHullMask

      private void generateConvexHullMask(ModelImage image)
      Algorithm Implementation Steps: 7. Take the convex-hull of the white matter segmentation and pass this mesh into a modified version of the AlgorithmBrainExtractor. 8. The output of the AlgorithmBrainExtractor is a segmented mesh representing the surface of the brain. To err on the side of not removing too much data, the convex-hull of the brain surface is generated. 9. The final mask representing the data outside the brain is generated using all voxels outside the convex-hull of the brain surface. 10. (Optional final step). If the user chooses to segment only the face region instead of the entire skull region the final step produces the face segmentation from the convex-hull of the brain surface. Once the white-matter has been segmented, a convex-hull of the segmentation is generated in step 7. This mesh is passed to a modified version of the AlgorithmBrainExtractor in MIPAV. The convex-hull of the white-matter often provides a good enough segmentation of the skull, but in a few cases the convex-hull of the white-matter does not include the entire surface of the brain and processing the mesh with the AlgorithmBrainExtractor corrects the mesh. Steps 8-9 were added to provide a buffer around the brain segmentation. This enables the algorithm to err on the side of removing too little data rather than removing small portions of the brain surface.

    • getBoundsDistance

      private void getBoundsDistance(WildMagic.LibFoundation.Mathematics.Vector3f min, WildMagic.LibFoundation.Mathematics.Vector3f max, WildMagic.LibFoundation.Mathematics.Vector3f centerBound, float limitX, float limit)

    • getIntersectX

      private float getIntersectX(WildMagic.LibFoundation.Mathematics.Vector3f kV0, WildMagic.LibFoundation.Mathematics.Vector3f kV1, WildMagic.LibFoundation.Mathematics.Vector3f kV2, float iY, float iZ)
      Compute the point of intersection between a line (0,iY,iZ)+t(1,0,0) and the triangle defined by the three input points. All calculations are in voxel coordinates and the x-value of the intersection point is truncated to an integer.
      Parameters:
      kV0 - a 3D vertex of the triangle
      kV1 - a 3D vertex of the triangle
      kV2 - a 3D vertex of the triangle
      iY - the y-value of the origin of the line
      iZ - the z-value of the origin of the line
      Returns:
      the x-value of the intersection

    • getIntersectY

      private float getIntersectY(WildMagic.LibFoundation.Mathematics.Vector3f kV0, WildMagic.LibFoundation.Mathematics.Vector3f kV1, WildMagic.LibFoundation.Mathematics.Vector3f kV2, float iX, float iZ)
      Compute the point of intersection between a line (iX,0,iZ)+t(0,1,0) and the triangle defined by the three input points. All calculations are in voxel coordinates and the y-value of the intersection point is truncated to an integer.
      Parameters:
      kV0 - a 3D vertex of the triangle
      kV1 - a 3D vertex of the triangle
      kV2 - a 3D vertex of the triangle
      iX - the x-value of the origin of the line
      iZ - the z-value of the origin of the line
      Returns:
      the y-value of the intersection

    • getIntersectZ

      private float getIntersectZ(WildMagic.LibFoundation.Mathematics.Vector3f kV0, WildMagic.LibFoundation.Mathematics.Vector3f kV1, WildMagic.LibFoundation.Mathematics.Vector3f kV2, float iX, float iY)
      Compute the point of intersection between a line (iX,iY,0)+t(0,0,1) and the triangle defined by the three input points. All calculations are in voxel coordinates and the z-value of the intersection point is truncated to an integer.
      Parameters:
      kV0 - a 3D vertex of the triangle
      kV1 - a 3D vertex of the triangle
      kV2 - a 3D vertex of the triangle
      iX - the x-value of the origin of the line
      iY - the y-value of the origin of the line
      Returns:
      the z-value of the intersection

    • getMedianIntensity

      private float getMedianIntensity(ModelImage image, BitSet mask)

    • inBounds

      private boolean inBounds(int x, int y, int z)

    • randomize

      private ModelImage randomize(ModelImage image, int stepSize)
      Randomizes voxel cubes with similar average intensities.
      Parameters:
      image -
      stepSize -
      Returns:

    • registerImages

      private ModelImage registerImages(ModelImage target, ModelImage src)
      Registers the atlas image to the input target image:
      Parameters:
      target -
      src -
      Returns:

    • removeUnusedVertices

      private WildMagic.LibGraphics.SceneGraph.TriMesh removeUnusedVertices(WildMagic.LibGraphics.SceneGraph.TriMesh kMesh)

    • scaleMesh

      private void scaleMesh(WildMagic.LibGraphics.SceneGraph.TriMesh mesh)
      Scales the input mesh based on the offset parameter set in the constructor. This enables the user to set a buffer around the segmentation.
      Parameters:
      mesh -

    • skullRemoval

      private void skullRemoval()
      Main algorithm implementation, skull segmentation and removal.

    • subtractMask

      private void subtractMask(ModelImage image)
      Removes portions of the image that are masked.
      Parameters:
      image -