Difference between revisions of "2010 Winter Project Week ProstateSeg"

From NAMIC Wiki
Jump to: navigation, search
Line 59: Line 59:
 
**alignTrainingShapesNonIso.bash: faster but not that accurate
 
**alignTrainingShapesNonIso.bash: faster but not that accurate
 
*Convert from binary to level set
 
*Convert from binary to level set
*ShapeBased\_reg\alignTrainingShapes\toSFLS\ => 1 executable
+
**ShapeBased\_reg\alignTrainingShapes\toSFLS\ => 1 executable
**Input: nrrd binary image
+
***Input: nrrd binary image
**Output: level set description
+
***Output: level set description
**For each binary image a level set image is generated and saved to ShapeBased\_reg\alignTrainingShapes\toSFLS
+
***For each binary image a level set image is generated and saved to ShapeBased\_reg\alignTrainingShapes\toSFLS
 
*Learning using PCA
 
*Learning using PCA
 
**ProstateSeg\ShapeBased\_reg\alignTrainingShapes\toSFLS\learn => 1 executable
 
**ProstateSeg\ShapeBased\_reg\alignTrainingShapes\toSFLS\learn => 1 executable
Line 69: Line 69:
 
**Execution time is about 1 minute, repeated for each eigen shape
 
**Execution time is about 1 minute, repeated for each eigen shape
 
*Images are flipped, but the images to be segmented (or the training shapes) could be flipped instead.
 
*Images are flipped, but the images to be segmented (or the training shapes) could be flipped instead.
 +
 
===Segmentation===
 
===Segmentation===
 
*ProstateSeg\ShapeBased\version20091203 => 1 executable (wholeseg)
 
*ProstateSeg\ShapeBased\version20091203 => 1 executable (wholeseg)
 
**Input: image to be segmented, and two points (at the left and right side of the prostate, on a center axial slice in IJK space)
 
**Input: image to be segmented, and two points (at the left and right side of the prostate, on a center axial slice in IJK space)
 
**Output: ?
 
**Output: ?

Revision as of 17:00, 6 January 2010

Home < 2010 Winter Project Week ProstateSeg


Key Investigators

  • Andras Lasso, Gabor Fichtinger (Queen's University)
  • Yi Gao, Allen Tannenbaum (Georgia Tech)
  • Andriy Fedorov (BWH)

Objective

Implement a Slicer module from the shape-based prostate segmentation algorithm developed by Yi Gao et al.

Approach, Plan

Implement as a command-line module that can be downloaded and installed as a Slicer extension. Add automatic testing.

Progress

The algorithm can be compiled using CMake on both linux and windows, test data are available.

References

  • Yi Gao, Romeil Sandhu, Gabor Fichtinger, Allen Tannenbaum, A Coupled Global Registration and Segmentation Framework with Application to the Magnetic Resonance Prostate Imagery, IEEE Trans Med Imaging (in review)


Notes

Training

  • Registration
    • alignTrainingShapes.bash (execution time is about 30min)
      • make isotropic (z direction)
      • register
        • ShapeBased\_reg\src\imageRegByPointSet\c\affine\ => 1 executable
          • pairwise image registration (there are many supporting files in ShapeBased\_reg\src; the result is one executable)
          • input: two images from ShapeBased\_reg\trainingShapes
          • output: transformed moving image in uchar nrrd image format
      • make anisotropic:
        • maybe this step could be skipped (to have an atlas with isotropic images)
      • results are copied to ShapeBased\_reg\alignTrainingShapes
    • alignTrainingShapesNonIso.bash: faster but not that accurate
  • Convert from binary to level set
    • ShapeBased\_reg\alignTrainingShapes\toSFLS\ => 1 executable
      • Input: nrrd binary image
      • Output: level set description
      • For each binary image a level set image is generated and saved to ShapeBased\_reg\alignTrainingShapes\toSFLS
  • Learning using PCA
    • ProstateSeg\ShapeBased\_reg\alignTrainingShapes\toSFLS\learn => 1 executable
    • Input: shapeList.txt list of all level set files
    • Output: mean shape and i-th eigen shape (multiplied by the eigen value),
    • Execution time is about 1 minute, repeated for each eigen shape
  • Images are flipped, but the images to be segmented (or the training shapes) could be flipped instead.

Segmentation

  • ProstateSeg\ShapeBased\version20091203 => 1 executable (wholeseg)
    • Input: image to be segmented, and two points (at the left and right side of the prostate, on a center axial slice in IJK space)
    • Output: ?