Semi-automatic technique for segmentation of the prostate from 2D ultrasound images

The segmentation technique is based on a deformable model that changes shape to fit the boundary of an object. Key to the success of the approach is the careful initialization of the contour, which requires the user to select only four points on the prostate boundary. Anatomic data and cubic interpolation are used to obtain an accurate estimate of the boundary. Gradient direction information is used during deformation to keep the contour from being attracted to extraneous boundaries.