Segmentation of arterial geometry from ultrasound images using balloon models

A method for segmentation of arteries in ultrasound B-mode images using a modified balloon model is presented. The external force which pulls the contour to the arterial boundary is the combination of the gradient and the second order derivative of the image. For 3D segmentation the contour of the first slice is found, and this is used as the initial position for the next slice. As the initial position of the contour may be outside the artery, the pressure term is decided by comparing the feature of texture inside and outside of the contour, allowing the contour to expand or shrink. The model has been tested on 55 images from carotid arteries. The 'gold standard' boundary drawn by a radiologist and the segmented boundary showed an average difference of 0.40/spl plusmn/0.30mm. 3D data was obtained using an anatomically correct carotid bifurcation flow phantom and gridded ready for CFD.

[1]  Junaed Sattar Snakes , Shapes and Gradient Vector Flow , 2022 .

[2]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..

[3]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[4]  C M Chen,et al.  A dual-snake model of high penetrability for ultrasound image boundary extraction. , 2001, Ultrasound in medicine & biology.

[5]  Laurent D. Cohen,et al.  Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images , 1993, IEEE Trans. Pattern Anal. Mach. Intell..