TubeTK/Events/2010.07.26: Difference between revisions

From KitwarePublic
< TubeTK‎ | Events
Jump to navigationJump to search
No edit summary
No edit summary
Line 1: Line 1:
= Patrick =
= Topics =
* Dashboards auto update?
** tubetk/CMake/DashboardScripts tubetk/CMake/CTestCustom...
* Batch Processing
** Python vs BatchMake vs Any
* Slicer
** TubeNet Viewer
** Slicer load .tre
** Slicer Loadable Module
* Registration
** Speckle in ultrasound registration
** Model-based deformation field interpolation
** Fluid deformation (Marc)
** Registration metrics based on ultrasound probe orientation
* Segmentation
** Unit test VTree code
*** 3D
*** 2D
** Automated vessel tree extraction
*** Using spatial prior
*** Seed selection
** Automated distinguishing arteries from veins based on spatial prior
* Atlas formation
** Retinal data
*** Email from UIowa (still waiting)
** Brain data
*** Vessel extractions from Liz
** Port pipeline to VTree
 
= Status =
 
== Patrick ==
* Primary goal: Bump and dent identification on IC images
* Primary goal: Bump and dent identification on IC images
* Accomplishments
* Accomplishments
Line 18: Line 49:
**** Normalizing for inter-acquisition (or inter-slice) variations?
**** Normalizing for inter-acquisition (or inter-slice) variations?
** Work with new collaborator at Kitware.
** Work with new collaborator at Kitware.
* Medium term (August 15)
* Medium term (August 9)
** Delivery and education
** Delivery and education
** Can we get better in simulation?
** Can we get better in simulation?
** Connectivity analysis
** chip-to-chip matching
** connectivity analysis


= Casey =
== Casey ==
* Primary goal: Compare populations of vascular networks
* Primary goal: Compare populations of vascular networks
* Near term (0.5, Aug 1)
* Near term (Aug 2)
** Collaborate with Patrick
** Feature extraction
*** Feature extraction
*** Patch-based features (max, median, quantiles)
**** Patch-based features (max, median, quantiles)
*** Scales / neighborhood
**** Scales / neighborhood
** Feature research
*** Feature research
*** Width estimate
**** Width estimate from Stephen (concern, time)
**** Not the same as Gaussian blur
**** Location of local max in ridgeness
*** New patch features
**** Subsample centerlines
*** Location of local max in ridgeness
**** Optimal match filter
*** Subsample centerlines
*** Classifiers
*** Optimal match filter
**** Comparison
** Classifiers
**** Implementation for transfer to USC
*** Comparison
**** Hierarchy (Good/bad.  If bad, then add/sub.)
*** Implementation for transfer to USC
** Data for Retinas
*** Hierarchy (Good/bad.  If bad, then add/sub.)
* Medium term (1 months, Aug 15)
* Medium term (Aug 9)
** Review previous processing pipeline with Stephen
** Connectivity analysis
** Research on methods for comparing spatial graphs / adjacency matrices
** chip-to-chip comparison
** Begin Port and test existing adjacency code
** Process retinal data
** Complete port and test of existing adjacency code
*** Prepare IJ article


= Andinet =
== Andinet ==
* Primary goal: Data from Duke for BWH
* Primary goal: Data from Duke for BWH
* Accomplishments  
* Accomplishments  
Line 59: Line 87:
*** Based upon the conversation I had with you, may be we should probably look into saving data off the BrainLab system itself not bother with the SD-5000.
*** Based upon the conversation I had with you, may be we should probably look into saving data off the BrainLab system itself not bother with the SD-5000.
** Write IJ article
** Write IJ article
*** Hua and I have made progress writing the IJ article. Hua helped me a lot generating results using synthetic data. We have now a solid outline and some write up in most of the sections. We will add more texts, figures and results and clean it up more. I will also put together self-contained source code tree containing the classes that we will submit with this paper Please see attached the latest version.
*** Made progress writing the IJ article. Hua helped me a lot generating results using synthetic data. We have now a solid outline and some write up in most of the sections
*** You can also access the tex, bib, etc files in my Work directory: Work/Andinet/TensorIJ
*** You can also access the tex, bib, etc files in my Work directory: Work/Andinet/TensorIJ
* Near term (August 2)
* Near term (August 2)
** Move article to TubeTK/Documentation/2010.TensorIJ
** IJ Article
*** Move article to TubeTK/Documentation/2010.TensorIJ
*** Add more texts, figures and results and clean it up more.
*** Put together self-contained source code tree containing the classes that we will submit with this paper.
*** Refer to TubeTK
*** Cite grant proposal in article
*** Cite grant proposal in article
** Install VV at Duke
** Install VV at Duke
* Medium term (August 9)
* Medium term (August 9)


= Hua =
== Hua ==
* Primary goal: ultrasound image processing
* Primary goal: ultrasound image processing
* Accomplished
* Accomplished
Line 78: Line 110:
**** http://www.insight-journal.org/midas/item/view/2206
**** http://www.insight-journal.org/midas/item/view/2206
**** http://www.insight-journal.org/midas/item/view/117
**** http://www.insight-journal.org/midas/item/view/117
* Medium term (August 16)
* Medium term (August 9)
** Investigate use of speckle in ultrasound registration
** Model-based deformation field interpolation

Revision as of 16:56, 26 July 2010

Topics

  • Dashboards auto update?
    • tubetk/CMake/DashboardScripts tubetk/CMake/CTestCustom...
  • Batch Processing
    • Python vs BatchMake vs Any
  • Slicer
    • TubeNet Viewer
    • Slicer load .tre
    • Slicer Loadable Module
  • Registration
    • Speckle in ultrasound registration
    • Model-based deformation field interpolation
    • Fluid deformation (Marc)
    • Registration metrics based on ultrasound probe orientation
  • Segmentation
    • Unit test VTree code
      • 3D
      • 2D
    • Automated vessel tree extraction
      • Using spatial prior
      • Seed selection
    • Automated distinguishing arteries from veins based on spatial prior
  • Atlas formation
    • Retinal data
      • Email from UIowa (still waiting)
    • Brain data
      • Vessel extractions from Liz
    • Port pipeline to VTree

Status

Patrick

  • Primary goal: Bump and dent identification on IC images
  • Accomplishments
    • Traveled to SSRL to view the acquisition and meet with Greg and Mike.
    • Modified the GenerateFeatures application to handle the input of arbitrary feature images
    • Using the previous features and Casey's new patch-based features, was able to achieve 95% pixel level accuracy in Weka and 23/25 defects found with 0 false positives in image space (after morphology).
    • Explore new features
      • evaluate a variety of standard deviations for intensity and ridge computations
  • Near Term (Aug 2)
    • Receiving code to simulate the tomography directly on GDS Layers
    • Compute dot-product between line (hessian) tangent and normal directions in ES and GDS images
    • 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?
    • Work with new collaborator at Kitware.
  • Medium term (August 9)
    • Delivery and education
    • Can we get better in simulation?
    • chip-to-chip matching
    • connectivity analysis

Casey

  • Primary goal: Compare populations of vascular networks
  • Near term (Aug 2)
    • Feature extraction
      • Patch-based features (max, median, quantiles)
      • Scales / neighborhood
    • Feature research
      • Width estimate
        • Not the same as Gaussian blur
      • New patch features
      • Location of local max in ridgeness
      • Subsample centerlines
      • Optimal match filter
    • Classifiers
      • Comparison
      • Implementation for transfer to USC
      • Hierarchy (Good/bad. If bad, then add/sub.)
  • Medium term (Aug 9)
    • Connectivity analysis
    • chip-to-chip comparison

Andinet

  • Primary goal: Data from Duke for BWH
  • Accomplishments
    • Data from Duke
      • Contacted several folks to gather information ( we had

questions regarding the machine at Duke) and check status.

        • BrainLab: Contacted Pratik. He is working on getting us VV license
        • Duke: Contacted Tanya and learned that SD-5000 ultrasound machine is not integrated with the BrainLab system. The machine is used to acquire ultrasound data independently.
        • Aloka: Contacted John Walsh at Aloka and learned that SD-5000 is very old model and doesn't come with research interface
      • Based upon the conversation I had with you, may be we should probably look into saving data off the BrainLab system itself not bother with the SD-5000.
    • Write IJ article
      • Made progress writing the IJ article. Hua helped me a lot generating results using synthetic data. We have now a solid outline and some write up in most of the sections
      • You can also access the tex, bib, etc files in my Work directory: Work/Andinet/TensorIJ
  • Near term (August 2)
    • IJ Article
      • Move article to TubeTK/Documentation/2010.TensorIJ
      • Add more texts, figures and results and clean it up more.
      • Put together self-contained source code tree containing the classes that we will submit with this paper.
      • Refer to TubeTK
      • Cite grant proposal in article
    • Install VV at Duke
  • Medium term (August 9)

Hua

  • Primary goal: ultrasound image processing
  • Accomplished
    • Correct a bug in itkAnisotropicHybridDiffusionImageFilter, and prepared figures for Andinet's Insight Journal paper.
    • Improve code coverage for uncovered filters under Application/CLI/** Increase coverage of TubeTK
  • Near term (August 2)
  • Medium term (August 9)