TubeTK/Events/2010.07.26

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 15)
  • Delivery and education
  • Can we get better in simulation?
  • Connectivity analysis

Casey

• Primary goal: Compare populations of vascular networks
• Near term (0.5, Aug 1)
  • Collaborate with Patrick
    • Feature extraction
      • Patch-based features (max, median, quantiles)
      • Scales / neighborhood
    • Feature research
      • Width estimate from Stephen (concern, time)
      • 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.)
  • Data for Retinas
• Medium term (1 months, Aug 15)
  • Review previous processing pipeline with Stephen
  • Research on methods for comparing spatial graphs / adjacency matrices
  • Begin Port and test existing adjacency code
  • Process retinal data
  • Complete port and test of existing adjacency code
    • Prepare IJ article

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
    • 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.
    • You can also access the tex, bib, etc files in my Work directory: Work/Andinet/TensorIJ
• Near term (August 2)
  • Move article to TubeTK/Documentation/2010.TensorIJ
    • 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)
  • Update registration code
  • Begin investigation of registration metrics that depend on ultrasound probe orientation
    • Get data from InnerOptic
      • http://www.insight-journal.org/midas/item/view/2206
      • http://www.insight-journal.org/midas/item/view/117
• Medium term (August 16)
  • Investigate use of speckle in ultrasound registration
  • Model-based deformation field interpolation