Symmetric Log-Domain Diffeomorphic Registration: A Demons-Based Approach
MICCAI '08 Proceedings of the 11th international conference on Medical Image Computing and Computer-Assisted Intervention - Part I
A fast B-spline pseudo-inversion algorithm for consistent image registration
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
On the influence of interpolation on probabilistic models for ultrasonic images
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Fast parametric elastic image registration
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Hi-index | 0.00 |
The heart motion estimation plays an important role in identifying different types of pathology. For this purpose, ultrasound imaging has commonly used due to its high time resolution. In this modality, the speckle is used as a characteristic feature of tissues to improve the accuracy of heart motion estimation which has important clinical implications. However, speckle tracking methods are commonly based on the statistics of speckle, which are affected by the preprocessing steps during the acquisition. This work aims for developing a speckle tracking method for myocardial motion estimation that considers the interpolation step performed to achieve the Cartesian arrangement of the ultrasonic image. The evaluation of the method was carried out using two types of synthetic images and by comparing to other state-of-the-art methods. Results showed that the methods based on speckle features provide a more realistic motion of the heart and follow the natural torsion than others. Besides, the proposed method obtains the best registration performance in most of the deformations tested.