A segmentation algorithm using dyadic wavelet transform and discrete dynamic contour
Bernard Chi Yuen Chiu, George H. Freeman, Magdy M. A. Salama, Aaron Fenster, Kamilia S. Rizkalla, D.B. Downey · 2004
Due to the quality of the ultrasound image, it is very difficult to develop a computerized method for defining the boundary of an object in this type of image. This paper focuses on developing a semiautomatic method for detecting the boundary of a prostate. The algorithm is based on Mallat's (1992) multiscale edge detection method and the discrete dynamic contour (DDC) model. The DDC model is made up of a set of connected vertices. When provided with an energy field that describes the features of the ultrasound image, the model automatically adjusts the vertices of the contour to attain a maximum energy. The proposed algorithm requires the user to enter four initialization points. The DDC model then updates the contour according to an energy field assigned based on the gradient modulus of the smoothed image obtained using the dyadic wavelet transform.