DocumentCode :
2723292
Title :
Segmentation of 2D stress echocardiography sequences using rest-based patient-specific prior information
Author :
Zabair, Adeala T. ; Noble, J. Alison
Author_Institution :
Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK
fYear :
2010
fDate :
14-17 April 2010
Firstpage :
304
Lastpage :
307
Abstract :
In stress echocardiography, the heart is imaged at rest and again when stressed to observe the change in function between these two states; the idea being that abnormalities will be exaggerated and therefore easier to identify in stress, but importantly this is referenced to the rest state. Despite the development of segmentation and tracking techniques for the heart at rest, there is little literature on the same for the stressed heart. First we propose a patient-specific segmentation technique that gives a prediction of stress dataset segmentation given rest dataset segmentation for a healthy heart through the use of a global motion model based on Canonical Correlation Analysis (CCA). Secondly, we refine this prior segmentation using texture measures from the rest dataset as reference parameters for maximum likelihood estimation of the boundary in the stress dataset. Results show that for 52 out of 78 datasets, our model gives better results than using the technique described in.
Keywords :
correlation methods; echocardiography; image segmentation; image sequences; image texture; medical image processing; 2D stress echocardiography; canonical correlation analysis; global motion model; heart; image sequences; maximum likelihood estimation; rest-based patient-specific prior information; segmentation; texture measures; Biomedical engineering; Biomedical measurements; Cardiac disease; Cardiovascular diseases; Echocardiography; Heart; Image segmentation; Predictive models; Stress measurement; Ultrasonic imaging; Segmentation; echocardiography; stress;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2010 IEEE International Symposium on
Conference_Location :
Rotterdam
ISSN :
1945-7928
Print_ISBN :
978-1-4244-4125-9
Electronic_ISBN :
1945-7928
Type :
conf
DOI :
10.1109/ISBI.2010.5490348
Filename :
5490348
Link To Document :
بازگشت