Difference between revisions of "2013 Winter Project Week:Hybrid registration"

From NAMIC Wiki
Jump to: navigation, search
 
(3 intermediate revisions by the same user not shown)
Line 3: Line 3:
 
Image:PW-SLC2013.png|[[2013_Winter_Project_Week#Projects|Projects List]]
 
Image:PW-SLC2013.png|[[2013_Winter_Project_Week#Projects|Projects List]]
  
Image:fixed-namic.png|
+
Image:panel.png|
Image:moving-namic.png|
+
Image:registration.gif|
 
 
 
</gallery>
 
</gallery>
  
Line 25: Line 24:
 
<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>
* To introduce a command line module in Slicer 4 as a part of Plastimatch Registration model
+
* To introduce CLI in Slicer 4 as a part of Plastimatch Registration module
 
* Try the algorithm on various data sets
 
* Try the algorithm on various data sets
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Progress</h3>
 
<h3>Progress</h3>
* Progress here
+
We extended Plastimatch B-spline deformable registration module with landmark matching functionality. We tested the new feature on synthetic image and obtained satisfactory results. We set future goal to work on interactive real-time landmark placing.
 
</div>
 
</div>
 
</div>
 
</div>
 +
[[new wiki page]]

Latest revision as of 15:59, 12 June 2013

Home < 2013 Winter Project Week:Hybrid registration

Key Investigators

  • Nadya Shusharina, Greg Sharp, MGH
  • Steve Pieper, Isomics


We propose to augment B-spline deformable registration with landmark information. Matching of landmarks is performed by the optimization procedure applied to the cost function containing an intensity-based data term and two constraints, smoothing and an explicit landmark matching.

Objective

  • To develop the method to extend automatic algorithm of deformable image registration based on B-spline approximation
  • The method includes landmark matching in the form of explicit landmark constraint
  • The method is relevant for fast registrations that require matching of certain image features

Approach, Plan

  • To introduce CLI in Slicer 4 as a part of Plastimatch Registration module
  • Try the algorithm on various data sets

Progress

We extended Plastimatch B-spline deformable registration module with landmark matching functionality. We tested the new feature on synthetic image and obtained satisfactory results. We set future goal to work on interactive real-time landmark placing.

new wiki page