Image moments-based ultrasound visual servoing

Abstract

A new visual servoing method based on B-mode ultrasound images is proposed to automatically control the motion of a 2D ultrasound probe held by a medical robot in order to reach a desired B-scan image of an object of interest. In this approach, combinations of image moments extracted from the current observed object cross-section are used as feedback visual features. The analytical form of the interaction matrix, relating the time variation of these visual features to the probe velocity, is derived and used in the control law. Simulations performed with a static ultrasound volume containing an egg-shaped object, and in-vitro experiments using a robotized ultrasound probe that interacts with a rabbit heart immersed in water, show the validity of this new approach and its robustness with respect to modeling and measurements errors.