TubeTK/Events/2010.10.14: Difference between revisions

From KitwarePublic
< TubeTK‎ | Events
Jump to navigationJump to search
(Created page with "== Danielle == * Implementation of diffusion-based regularization ** itkImageToImageDiffusiveDeformableRegistrationFilter ** itkImageToImageDiffusiveDeformableRegistrationFunctio...")
 
No edit summary
Line 5: Line 5:
** Extends itkPDEDeformableRegistrationFilter/Function, with similar modifications as Andinet's itkAnisotropicDiffusionTensorImageFilter/itkAnisotropicDiffusionTensorFunction (which extend itkFiniteDifferenceImageFilter/itkFiniteDifferenceFunction)
** Extends itkPDEDeformableRegistrationFilter/Function, with similar modifications as Andinet's itkAnisotropicDiffusionTensorImageFilter/itkAnisotropicDiffusionTensorFunction (which extend itkFiniteDifferenceImageFilter/itkFiniteDifferenceFunction)
* Implementation of regularization smoothing in the tangential direction:
* Implementation of regularization smoothing in the tangential direction:
** Artificial motion field:
** Artificial deformation field:
*** Vectors are [-0.5, 0.5, 0] or [0.5, 0.5, 0], plus white noise of variance 0.1
*** Known normal, for now use w = 1 (smoothing entirely in tangential plane)
[[File:SlidingOrganTangentialDiffusionTest.png]]
** Registration is regularization only (20 iterations, time step 0.05)
** Original deformation field:
[[File:OriginalMotionField.png]]
** Deformation field after regularization:
*** Note border is maintained
[[File:SmoothedMotionField.png]]


* Future
* Future

Revision as of 17:22, 14 October 2010

Danielle

  • Implementation of diffusion-based regularization
    • itkImageToImageDiffusiveDeformableRegistrationFilter
    • itkImageToImageDiffusiveDeformableRegistrationFunction
    • Extends itkPDEDeformableRegistrationFilter/Function, with similar modifications as Andinet's itkAnisotropicDiffusionTensorImageFilter/itkAnisotropicDiffusionTensorFunction (which extend itkFiniteDifferenceImageFilter/itkFiniteDifferenceFunction)
  • Implementation of regularization smoothing in the tangential direction:
    • Artificial deformation field:
      • Vectors are [-0.5, 0.5, 0] or [0.5, 0.5, 0], plus white noise of variance 0.1
      • Known normal, for now use w = 1 (smoothing entirely in tangential plane)

SlidingOrganTangentialDiffusionTest.png

    • Registration is regularization only (20 iterations, time step 0.05)
    • Original deformation field:

OriginalMotionField.png

    • Deformation field after regularization:
      • Note border is maintained

SmoothedMotionField.png

  • Future
    • Boundary conditions
    • Regularization smoothing in normal direction
    • Add intensity distance function (simple using existing finite difference functions)
    • Compute weighting term = distance to organ border
    • Extract organ border normals from input data