Difference between revisions of "2012 Summer Project Week:UtahAutoScar"

From NAMIC Wiki
Jump to: navigation, search
 
(3 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
<gallery>
 
<gallery>
 
Image:PW-MIT2012.png|[[2012_Summer_Project_Week#Projects|Projects List]]
 
Image:PW-MIT2012.png|[[2012_Summer_Project_Week#Projects|Projects List]]
 +
Image:CARMA-scar-snapshot-module.png|Updated module with logos/acknowledgements
 
Image:carma_afib_auto_scar.png|Automatic Left Atrial Scar Segmentation
 
Image:carma_afib_auto_scar.png|Automatic Left Atrial Scar Segmentation
 
</gallery>
 
</gallery>
Line 12: Line 13:
  
 
<h3>Objective</h3>
 
<h3>Objective</h3>
We are developing methods for automatically detecting post-procedural scar in LGE-MRI images. The goal is to be able to make statistical group comparisons based on the spatial distribution and amount of scar.
+
We are developing methods for automatically detecting post-procedural scar in LGE-MRI images. The goal is to make statistical group comparisons based on the spatial distribution and amount of scar.
  
  
Line 34: Line 35:
  
 
<h3>Progress</h3>
 
<h3>Progress</h3>
Software for the automatic scar segmentation has been implemented [http://wiki.na-mic.org/Wiki/index.php/DBP3:Utah:SlicerModuleAutoScar]. We need to create documentations and tutorials as well as finalize the migration to Slicer 4We have begun statistical analysis and validation of the module.
+
Software for the automatic scar segmentation has been implemented [http://wiki.na-mic.org/Wiki/index.php/DBP3:Utah:SlicerModuleAutoScar]. We have created documentation/tutorial for the moduleLastly, we have updated the acknowledgements section to include the appropriate logos and information.  The module is now available as a loadable extension in Slicer 4.
  
  

Latest revision as of 20:07, 21 June 2012

Home < 2012 Summer Project Week:UtahAutoScar

Key Investigators

  • Utah: Danny Perry, Alan Morris, Josh Cates, Rob MacLeod

Objective

We are developing methods for automatically detecting post-procedural scar in LGE-MRI images. The goal is to make statistical group comparisons based on the spatial distribution and amount of scar.




Approach, Plan

Our approach for automatic scar segmentation is summarized in the SPIE 2012 reference below. Briefly, we are using k-means clustering to tease apart the normalized pixel intensities corresponding to different tissue types (e.g., healthy, scar, blood).

Our plan for the project week is to test our module, and ensure that it meets "Ron's Rules" and develop supporting documentation/examples. We will present a tutorial on this module during the project week tutorial contest [1]

Progress

Software for the automatic scar segmentation has been implemented [2]. We have created documentation/tutorial for the module. Lastly, we have updated the acknowledgements section to include the appropriate logos and information. The module is now available as a loadable extension in Slicer 4.


Delivery Mechanism

This work will be delivered to the NA-MIC Kit as a

  1. ITK Module - NO
  2. Slicer Module
    1. Built-in - NO
    2. Extension -- commandline - YES
    3. Extension -- loadable - NO
  3. Other (Please specify)

References

  • Daniel Perry, Alan Morris, Nathan Burgon, Christopher McGann, Robert MacLeod, Joshua Cates. "Automatic classification of scar tissue in late gadolinium enhancement cardiac MRI for the assessment of left-atrial wall injury after radiofrequency ablation". SPIE Medical Imaging: Computer Aided Diagnosis, Feb 2012.