Adaptive Multi-Resolution Myocardial Motion Analysis of B-Mode Echocardiography Images using Combined Local/Global Optical Flow
Since myocardial motion is directly related to cardiac vascular supply, it can be helpful in diagnosing the heart abnormalities. The most comprehensive and available imaging study of the cardiac function is echocardiography and therefore it is important to make the echocardiography motion more quant...
Saved in:
Published in: | 2008 2nd International Conference on Bioinformatics and Biomedical Engineering Vol. 2; pp. 2303 - 2306 |
---|---|
Main Authors: | , , , , , |
Format: | Conference Proceeding Journal Article |
Language: | English |
Published: |
IEEE
2008
|
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Since myocardial motion is directly related to cardiac vascular supply, it can be helpful in diagnosing the heart abnormalities. The most comprehensive and available imaging study of the cardiac function is echocardiography and therefore it is important to make the echocardiography motion more quantitative. To overcome the sensitivity to shear, rotation and wide range of motion, we propose an adaptive hybrid method based on combined local global (CLG) optical flow in combination with adaptive multi-resolution spatiotemporal spline moments. In adaptive multi-resolution strategy the coarse moments are applied on the coarse moving regions and the fine moments are applied on the fine moving areas. The fine and coarse moving regions are obtained using motion segmentation. The evaluation was performed on simulated, synthetic, real data. The proposed method achieved rotational error of 2.8 degrees per frame and amplitude error of 2.2 percent per frame. These results demonstrate a better performance with respect to other B-Mode echocardiography motion estimation techniques such as Lucas-Kanade, Horn-Shunck and spatiotemporal affine technique. |
---|---|
Bibliography: | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
ISBN: | 9781424417476 1424417473 |
ISSN: | 2151-7614 2151-7622 |
DOI: | 10.1109/ICBBE.2008.908 |