Paper: | SA-PM-PS1.12 |
Session: | Image Registration |
Time: | Saturday, April 8, 13:30 - 14:50 |
Presentation: |
Poster
|
Title: |
Registering Richly Labelled 3D Images |
Authors: |
Kolawale Babalola; University of Manchester | | |
| Tim Cootes; University of Manchester | | |
Abstract: |
We propose a method of registering 3D images in which many regions have been segmented and labelled. Images in which some regions have been labelled can be registered by generating distance transform planes, one for each individual label class, and applying registration algorithms to the multi-plane images. However, when there are many labels such an approach can lead to impractically large images. We demonstrate that good results can be obtained by mapping each label value to a vector in a low dimensional space and applying a multi-plane registration algorithm to the resulting image.For the approach to work well, the vectors used for each label should be well separated, and chosen in such a way that there is minimal confusion between them. We demonstrate the method by using it to construct statistical shape models by applying a groupwise alignment method to a set of richly labelled 3D brain images. |