TubeTK/Events/2010.07.12: Difference between revisions

From KitwarePublic
< TubeTK‎ | Events
Jump to navigationJump to search
No edit summary
Line 25: Line 25:
** GenerateFeaturesForWeka
** GenerateFeaturesForWeka
* Near Term (Aug 1)
* Near Term (Aug 1)
** Get registered data from Greg
** compute dot-product between line (hessian) tangent and normal directions in ES and GDS images
** compute dot-product between line (hessian) tangent and normal directions in ES and GDS images
** write program that goes from weiki output to image and computes TPR/FPR scores on that image
** write program that goes from Weka output to image and computes TPR/FPR scores on that image
** Collaborate with Casey
** Collaborate with Casey
*** Choose classification scheme
*** Choose classification scheme
Line 32: Line 33:
**** Use neuralnets / parzenWindowing in ITK
**** Use neuralnets / parzenWindowing in ITK
*** Subselect features
*** Subselect features
*** Large number of test cases
** Product: ~ 5 slides / report to USC illustrating path chosen, strengths, and weaknesses.
** Product: ~ 5 slides to USC illustrating path chosen, strengths, and weaknesses.
*** Real-world tests / workflow
** Report to USC involving TPR/FPR for new technique
*** Does a trained classifier work on other layers?
*** Does a trained classifier work on other acquisitions?
**** i.e., do we need to insert modifications for training on every slice / acquisition / ?
**** Normalizing for inter-acquisition (or inter-slice) variations?
** Go to Synchrotron
** Go to Synchrotron
* Medium term (1 months, August 15)
* Medium term (1 months, August 15)
** Delivery and education
** Delivery and education
** Real-world tests / workflow
** Can we get better in simulation?
*** Does a trained classifier work on other layers?
*** Does a trained classifier work on other chips?
**** i.e., do we need to insert modifications for training on every slice / acquisition / ?
**** Normalizing for inter-acquisition (or inter-slice) variations?
** Connectivity analysis
** Connectivity analysis
** Can we get better in simulation?
** Get registered data from Greg


= Casey =
= Casey =

Revision as of 17:46, 12 July 2010

Andinet

  • Primary goal: Data from Duke for BWH
  • Accomplishments
    • Attend NAMIC AHM
    • Determine what is necessary to record data sent to OpenIGTLink from VectorVision system
      • Define data workflow and software architecture
      • Begin implementation
      • Product: powerpoint presentation: 5 slides
  • Near term (August 1)
    • Install VV at Duke
    • Determine if we can get US data from Duke machine
    • Write IJ article
      • Cite grant proposal in article
  • Medium term (1.5 months, August 15)
    • Investigate simulation of ultrasound from MR/CT
    • Code review of vessel segmentation method from Stephen

Patrick

  • Primary goal: Bump and dent identification on IC images
  • Accomplishments
    • Explore new features
      • z-score values from three different mean/stdDev joint histograms: add, subtract, and unchanged
      • evaluate a variety of standard deviations for intensity and ridge computations
    • New centerline method (skeletonization)
    • GenerateFeaturesForWeka
  • Near Term (Aug 1)
    • Get registered data from Greg
    • compute dot-product between line (hessian) tangent and normal directions in ES and GDS images
    • write program that goes from Weka output to image and computes TPR/FPR scores on that image
    • Collaborate with Casey
      • Choose classification scheme
      • Implement in C++ or python - in tubetk
        • Use neuralnets / parzenWindowing in ITK
      • Subselect features
    • Product: ~ 5 slides / report to USC illustrating path chosen, strengths, and weaknesses.
      • Real-world tests / workflow
      • Does a trained classifier work on other layers?
      • Does a trained classifier work on other acquisitions?
        • i.e., do we need to insert modifications for training on every slice / acquisition / ?
        • Normalizing for inter-acquisition (or inter-slice) variations?
    • Go to Synchrotron
  • Medium term (1 months, August 15)
    • Delivery and education
    • Can we get better in simulation?
    • Connectivity analysis

Casey

  • Primary goal: Compare populations of vascular networks
  • Near term (2 weeks, July 2nd)
    • Review previous processing pipeline with Stephen
    • Research on methods for comparing spatial graphs / adjacency matrices
    • Begin Port and test existing adjacency code
  • Medium term (1.5 months)
    • Process retinal data
    • Complete port and test of existing adjacency code
      • Prepare IJ article

Hua

  • Primary goal: ultrasound image processing
  • Near term (2 weeks, July 2nd)
    • Verify Andinet's code: add tests and help with IJ publication
      • Creating tests (sin pattern with known derivatives)
      • Done by next wednesday (June 23)
      • Choose Michel vs BWH
  • Medium term (1.5 months
    • Investigate use of speckle in ultrasound registration
    • Model-based deformation field interpolation
    • 2D-3D registration (data)
    • Simulating ultrasound from MR/CT
Retrieved from "https://public.kitware.com/Wiki/index.php?title=TubeTK/Events/2010.07.12&oldid=25026"