Quantification of aortic regurgitation using proximal isovelocity surface area: an effective segmentation approach based on fuzzy clustering Online publication date: Mon, 11-Aug-2014
by P. Abdul Khayum; P.V. Sridevi; M.N. Giriprasad
International Journal of Medical Engineering and Informatics (IJMEI), Vol. 4, No. 1, 2012
Abstract: Echocardiography is mainly to assess valvular regurgitation and get valuable information on the severity of aortic regurgitation (AR). It has several applications, but this paper focuses only on its use in the quantitative evaluation of AR. Proximal isovelocity surface area (PISA) evaluates the severity of AR. The quantification of the effective regurgitant orifice area (EROA) in AR is presented utilising Doppler echocardiography aided by clustering based image segmentation and PISA techniques. Pre-processing is done subjecting the colour Doppler echocardiography image to Gaussian filtering which improves the signal to noise ratio of the image. Subsequently, the image was enhanced with the aid of an image contrast enhancement method that utilises contrast-limited adaptive histogram equalisation. Then this image is segmented by using fuzzy-k means clustering to enable more precise quantification of the AR. PISA method is employed for calculating the quantitative parameters of AR such as, EROA, regurgitant volume (RV), regurgitant fraction (RF), etc. The proximal flow convergence method is used to quantify valvular regurgitation by analysing the converging flow field proximal to the mild, severe or eccentric AR lesion. Experimental evaluation on the commonly accessible dataset illustrates the enhanced performance of the proposed approach effectively.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Medical Engineering and Informatics (IJMEI):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com