This paper presents a multi-task control method to maintain the visibility of an anatomic element of interest while the doctor tele-operates a 2D ultrasound probe held by a medical robot. The prior task consists in automatically maintaining several visual constraints that guarantee an inter-section between the ultrasound image plane and the anatomic object of interest and the second task allows the medical expert to manually apply probe motion through tele-operation. Unlike classical visual servoing technique which continually regulate the current visual features to desired values, our control approach gradually activates the regulation of one or several ultrasound visual features that go close to fixed limits in such a way to keep them in a safe domain. The main advantage of this approach is to give to the clinician the control of all the degrees of freedom of the probe to examine the patient while automatically preserving the visibility of the element of interest if required. Both simulations and experiments performed on an abdominal phantom demonstrate the efficiency of the visibility assistance task.

This paper presents an optimal parametric active contour method based on Fourier descriptors to detect and track a contour from a sequence of images in real-time. The advantage of this approach is that not only convex but also concave contours can be considered. We also propose a method to initialize the active contour using only three user's clicks in the first image of the sequence and to automatically re-initialize it when possible topological changes are detected during the tracking. Moreover, the algorithm is implemented on GPU to ensure the real-time tracking performance.