An interactive B-spline snake and its application

Due to the poor quality of ultrasound images, fully automatic segmentation methods are not feasible, This article describes a novel approach to the semiautomatic segmentation of ultrasound images. The key idea of the algorithm is to combine user intervention into the traditional B-spline snake models. By introducing a new kind of force fields, the interactive B-spline snakes are constrained by the user interaction with a new control point insertion strategy. The statistical parameters of the snake models are trained on-the-fly by observing boundaries accepted by the user. The resulting algorithm is especially useful in dealing with successive slices and provides fast, reliable and verifiable segmentation in ultrasound images.