Frequency-Based Nonrigid Motion Analysis: Application to Four Dimensional Medical Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
International Journal of Computer Vision
MyoTrack: A 3D Deformation Field Method to Measure Cardiac Motion from Gated SPECT
MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
Multiframe temporal estimation of cardiac nonrigid motion
IEEE Transactions on Image Processing
Estimating myocardial motion by 4D image warping
Pattern Recognition
Myocardial motion and strain rate analysis from ultrasound sequences
IWCM'04 Proceedings of the 1st international conference on Complex motion
Spatio-temporal registration of real time 3D ultrasound to cardiovascular MR sequences
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Bilinear point distribution models for heart motion analysis
ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Consistent estimation of cardiac motions by 4D image registration
MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Pairwise active appearance model and its application to echocardiography tracking
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
| Hi-index | 0.00 |
In this article we propose a cardiac motion estimation technique that uses non-rigid registration to compute the dense cardiac displacement field from 2D ultrasound sequences. Our method employs a semi-local deformation model which provides controlled smoothness. We apply a multiresolution optimization strategy for better speed and robustness. To further improve the accuracy, the sequence is registered in both forward and backward directions. We calculate additional parameters from the displacement field, such as total displacement and strain.We create an artificial ultrasound sequence ofon e heart cycle using a motion model and use it to validate the accuracy oft he algorithm. Finally, we present results on real data from normal and pathological subjects that show the clinical applicability of our method.