Difference between revisions of "2012 Winter Project Week:FastInterpolation"
From NAMIC Wiki
Ivan.kolesov (talk | contribs) |
Ivan.kolesov (talk | contribs) |
||
| (4 intermediate revisions by the same user not shown) | |||
| Line 3: | Line 3: | ||
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]] | Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]] | ||
Image:phantom_double.png|Synthetic example used for tests. | Image:phantom_double.png|Synthetic example used for tests. | ||
| + | Image:2DMix.png|Ovelay of images to register. | ||
| + | Image:2DMix_reg.png| Registered images. | ||
| + | Image:2DDefField.png| Computed deformation field. | ||
</gallery> | </gallery> | ||
| Line 14: | Line 17: | ||
<h3>Objective</h3> | <h3>Objective</h3> | ||
| − | *Goal: Create a deformable registration approach | + | *Goal: Create a deformable registration approach for computing large deformations(e.g. in the presence of abnormalities, between different patients) |
*A stochastic registration algorithm has been implemented. | *A stochastic registration algorithm has been implemented. | ||
*Bottleneck is performing image interpolation quickly. | *Bottleneck is performing image interpolation quickly. | ||
| Line 27: | Line 30: | ||
*Take advantage of the structure of deformation (parameterized deformation field). | *Take advantage of the structure of deformation (parameterized deformation field). | ||
*Perform approximate interpolation. | *Perform approximate interpolation. | ||
| − | *Make algorithmic improvements to | + | *Make algorithmic improvements to allow for large 3D datasets to be used. |
</div> | </div> | ||
| Line 34: | Line 37: | ||
<h3>Progress</h3> | <h3>Progress</h3> | ||
| + | *Proposed an optimization ~100x faster than previous version | ||
| + | *Tested on the 2D phantom image above. | ||
</div> | </div> | ||
Latest revision as of 23:14, 12 January 2012
Home < 2012 Winter Project Week:FastInterpolation
Synthetic example used for tests.
Ovelay of images to register.
Registered images.
Computed deformation field.
Key Investigators
- Ivan Kolesov : Georgia Institute of Technology
- Greg Sharp : MGH
- Allen Tannenbaum : Boston University
Objective
- Goal: Create a deformable registration approach for computing large deformations(e.g. in the presence of abnormalities, between different patients)
- A stochastic registration algorithm has been implemented.
- Bottleneck is performing image interpolation quickly.
Approach, Plan
- Take advantage of the structure of deformation (parameterized deformation field).
- Perform approximate interpolation.
- Make algorithmic improvements to allow for large 3D datasets to be used.
Progress
- Proposed an optimization ~100x faster than previous version
- Tested on the 2D phantom image above.
Delivery Mechanism
This work will be delivered to the NA-MIC Kit as a
- Slicer Module (via PLUS and OpenIGTLink)
