Difference between revisions of "2015 BRAINSFit registration in SimpleITK"
From NAMIC Wiki
(Created page with '__NOTOC__ <gallery> Image:PW-Summer2015.png|Projects List </gallery> ==Key Investigators== * Peter Behringer * Andriy Fedorov ==Project De…') |
|||
| (11 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
__NOTOC__ | __NOTOC__ | ||
| − | + | ||
| − | Image: | + | {| |
| − | + | | Case 25 | |
| + | |[[Image:HighIrregulation.gif |thumb|400px|High irregulations in ITKv4]] | ||
| + | |[[Image:fixedIrregulations.gif|thumb|400px|Resolved Irregulations ins ITKv4]] | ||
| + | |} | ||
==Key Investigators== | ==Key Investigators== | ||
* Peter Behringer | * Peter Behringer | ||
* Andriy Fedorov | * Andriy Fedorov | ||
| + | * Dženan Zukić | ||
==Project Description== | ==Project Description== | ||
| Line 13: | Line 17: | ||
<h3>Objective</h3> | <h3>Objective</h3> | ||
* Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4. | * Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4. | ||
| − | * One issue that we are getting with ITKv4 is that are a lot more irregular and unrealistic than what we used to get in ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here] | + | * One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary [http://www.na-mic.org/Wiki/index.php/BRAINSFit_prostate_registration here]) |
* The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here] | * The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated [http://onlinelibrary.wiley.com/doi/10.1002/jmri.23688/abstract;jsessionid=F9AADC56E72CA73A422B9C09728F7E81.f01t03 here] | ||
| − | |||
</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> | ||
| − | * | + | * Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK |
| − | * Get | + | * Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK |
| − | |||
</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> | ||
| − | * Initialization and rigid registration | + | * Initialization and rigid registration is implemented using SimpleITK |
| + | * We tracked the issue down using various parameters | ||
| + | * We used strongly dilated masks for the BSpline registration and results are looking much better | ||
</div> | </div> | ||
</div> | </div> | ||
Latest revision as of 14:48, 24 June 2015
Home < 2015 BRAINSFit registration in SimpleITK
| Case 25 |
Key Investigators
- Peter Behringer
- Andriy Fedorov
- Dženan Zukić
Project Description
Objective
- Our registration module for b-spline deformable registration of prostate MRI uses BRAINSFit in Slicer4/ITKv4.
- One issue that we are getting with Slicer4/ITKv4 is that they are a lot more irregular and unrealistic than what we used to get in Slicer3/ITKv3 (see summary here)
- The Slicer4/ITKv4 registration tool should be comparable with the functionality we had in Slicer3/ITKv3, which was evaluated here
Approach, Plan
- Implement a subset of BRAINSFit functionality used for supporting in-bore MRI-guided prostate biopsy in SimpleITK
- Get ideas from the community how the irregularity can be avoided and implemented in SimpleITK
Progress
- Initialization and rigid registration is implemented using SimpleITK
- We tracked the issue down using various parameters
- We used strongly dilated masks for the BSpline registration and results are looking much better
