Fast model based segmentation of ultrasound data using an active image

In the present paper we propose a method for fast segmentation of ultrasound data. It is based on setting up a model depending on user input. We apply a matching scheme in order to obtain initial contours for 2D segmentation of several cross-sections of the organ by a discrete dynamic contour. Further, we set up an active image which drives the deformation of the dynamic contour. The active image comprises both textural information based on image data as well as spatial information which we derive from the inital contour. We design the active image according to user input and image quality to aid the segmentation task.