Difference between revisions of "NeedleFinder"

From NAMIC Wiki
Jump to: navigation, search
Line 18: Line 18:
 
* Improve performance and usability of NeedleFinder [ADD A SHORT MOVIE TO SHOW WHAT IT DOES TODAY]
 
* Improve performance and usability of NeedleFinder [ADD A SHORT MOVIE TO SHOW WHAT IT DOES TODAY]
 
** Code profiling, refactoring
 
** Code profiling, refactoring
−
** Provide Bounding Box/Region of Interest
 
 
** GUI simplification
 
** GUI simplification
−
**Automatic needle tip (and body) detection  
+
*** Provide Bounding Box/Region of Interest
 +
** Semi-Automatic needle tip (and body) detection  
 
** Parameter optimization
 
** Parameter optimization
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Approach, Plan</h3>
 
<h3>Approach, Plan</h3>
−
* SimpleITK filtering (e.g. derivatives: gradient magnitude, vesselness etc.)
+
* Improvements of the source code quality, algorithms and GUI (usability):
−
* Rigid registration of CAD models to (preprocessed) scene (ICP, Besl)
+
** Ad-hoc python profiling concept (method tagging, logging and message boxes as code probes)
−
* Machine learning (genetic algorithm etc.)
+
** Improved standardized and guided workflow more usable by MDs (state machine)
−
* New ad-hoc python profiling concept (logging and message boxes as code probes)
+
*** Interaction protocol using existing tools for MD to provide bounding-box quickly
−
* Improved standardized and guided workflow more usable by MDs (disabling unsuitable buttons)
+
** Incorporate SimpleITK filtering/preprocessing and a little user interaction (try e.g. derivatives: gradient magnitude, vesselness)
 +
** Look into machine learning (implement simple genetic algorithm & compare to brute-force grid search)
 +
<!-- ** Rigid registration of CAD models to (preprocessed) scene (ICP, Besl) -->
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">

Revision as of 17:00, 19 December 2014

Home < NeedleFinder

Key Investigators

Andre Mastmeyer, Guillaume Pernelle, Yang Gao, Tina Kapur, Steve Pieper, Ron Kikinis

Project Description

Objective

  • Improve performance and usability of NeedleFinder [ADD A SHORT MOVIE TO SHOW WHAT IT DOES TODAY]
    • Code profiling, refactoring
    • GUI simplification
      • Provide Bounding Box/Region of Interest
    • Semi-Automatic needle tip (and body) detection
    • Parameter optimization

Approach, Plan

  • Improvements of the source code quality, algorithms and GUI (usability):
    • Ad-hoc python profiling concept (method tagging, logging and message boxes as code probes)
    • Improved standardized and guided workflow more usable by MDs (state machine)
      • Interaction protocol using existing tools for MD to provide bounding-box quickly
    • Incorporate SimpleITK filtering/preprocessing and a little user interaction (try e.g. derivatives: gradient magnitude, vesselness)
    • Look into machine learning (implement simple genetic algorithm & compare to brute-force grid search)

Progress

  • N/Y
  • N/Y
  • N/Y
  • N/Y
  • N/Y

References

Retrieved from "https://www.na-mic.org/w/index.php?title=NeedleFinder&oldid=88009"