Difference between revisions of "2013 Winter Project Week:Hybrid registration"
From NAMIC Wiki
| (17 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
<gallery> | <gallery> | ||
Image:PW-SLC2013.png|[[2013_Winter_Project_Week#Projects|Projects List]] | Image:PW-SLC2013.png|[[2013_Winter_Project_Week#Projects|Projects List]] | ||
| + | |||
| + | Image:panel.png| | ||
| + | Image:registration.gif| | ||
</gallery> | </gallery> | ||
==Key Investigators== | ==Key Investigators== | ||
| − | Greg Sharp, | + | * 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. | |
<div style="margin: 20px;"> | <div style="margin: 20px;"> | ||
<div style="width: 27%; float: left; padding-right: 3%;"> | <div style="width: 27%; float: left; padding-right: 3%;"> | ||
<h3>Objective</h3> | <h3>Objective</h3> | ||
| − | * | + | * 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 |
</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> | ||
| − | + | * To introduce CLI in Slicer 4 as a part of Plastimatch Registration module | |
| + | * 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> | ||
| − | + | 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.
