Pregled bibliografske jedinice broj: 425792
A method for registration and model-based segmentation of Doppler ultrasound images
A method for registration and model-based segmentation of Doppler ultrasound images // Proceedings of SPIE Medical Imaging 2009 [7259-27]
Lake Buena Vista (FL), 2009. (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 425792 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A method for registration and model-based segmentation of Doppler ultrasound images
Autori
Kalinić, Hrvoje ; Lončarić, Sven ; Čikeš, Maja ; Davor Miličić ; Čikeš, Ivo ; Sutherland, G. R. ; Bijenens, Bart
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of SPIE Medical Imaging 2009 [7259-27]
/ - Lake Buena Vista (FL), 2009
Skup
SPIE Medical Imaging 2009
Mjesto i datum
Sjedinjene Američke Države, 07.02.2009. - 12.02.2009
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
model-based image segmentation; doppler ultrasound; image registration; aortic outflow velocity profile
Sažetak
Morphological changes of Doppler ultrasound images are an important source of information for diagnosis of cardiovascular diseases. Quantification of these flow profiles requires segmentation of the ultrasound images. In this article, we propose a new model-based method for segmentation of (aortic outflow) velocity profiles. The method is based on a procedure for registration using a geometric transformation specifically designed for matching Doppler ultrasound profiles. Mutual information is used as an image similarity measure, while optimization is performed by a genetic algorithm. The registration method is experimentally validated using an in-silico image phantom. The model based segmentation is evaluated in a series of aortic outflow Doppler ultrasound images from 30 normal volunteers, comparing the automated method to the manual delineation by an expert cardiologist. The experimental results confirm the accuracy of the approach and shows that the method can be used for the segmentation of clinically obtained aortic outflow velocity profiles.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Kliničke medicinske znanosti
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Medicinski fakultet, Zagreb
Profili:
Hrvoje Kalinić
(autor)
Sven Lončarić
(autor)
Davor Miličić
(autor)
Ivo Čikeš
(autor)
Maja Čikeš
(autor)