Paper: | FR-PM-OS2.5 |
Session: | Cardiac and Vascular Imaging |
Time: | Friday, April 7, 16:40 - 17:00 |
Presentation: |
Oral
|
Title: |
Complex Wavelets for Registration of Tagged MRI Sequences |
Authors: |
Estanislao Oubel; Pompeu Fabra University | | |
| Alejandro Frangi; Pompeu Fabra University | | |
| Alfred Hero; University of Michigan | | |
Abstract: |
Tagged Magnetic Resonance Imaging (MRI) is currently the reference MR modality for myocardial motion and strain analysis. MI-based non rigid registration has proven to be an accurate method to retrieve cardiac deformation fields. However, high frequency information in tags is not used. In a previous work this information was included by using feature vectors formed with wavelet coefficients and kNN graphs to estimate alpha-MI. It was shown that cardiac motion estimation was feasible with these features. In this work, features were derived from the complex wavelet Transform, which is shift invariant and provides more high frequency subimages than conventional wavelets. The results show that lower errors are obtained with respect to the use of pixel intensity, for both histograms and kNN graphs. |