Detection of the lumen and media-adventitia borders in IVUS imaging

The detection of the lumen and media-adventitia borders is a key step in intravascular ultrasound (IVUS) processing. The traditional method for IVUS is based on the snake model or GVF Snake model. Actually, it is not easy to get the precise lumen and adventitia border of the IVUS image by only using the one of the above method. In this paper a new way is used in IVUS image processing. At first, the IVUS original image is preprocessed with the Canny edge detection of the Gaussian filters in different variances and circle Hough transform, or binary image processing. Then the preprocessed image is transformed by GVF. Finally, the noise dots on the GVF transforming image are removed and the desirable lumen and media-adventitia borders of IVUS image are obtained. The experimental results confirm the validity of the new method.

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

[2]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  O DudaRichard,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972 .

[4]  Bridget Carragher,et al.  Automatic particle detection through efficient Hough transforms , 2003, IEEE Transactions on Medical Imaging.

[5]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.