Evaluation of 2D and 3D ultrasound tracking algorithms and impact on ultrasound-guided liver radiotherapy margins.

PURPOSE: Compensation for respiratory motion is important during abdominal cancer treatments. In this work we report the results of the 2015 MICCAI Challenge on Liver Ultrasound Tracking and extend the 2D results to relate them to clinical relevance in form of reducing treatment margins and hence sparing healthy tissues, while maintaining full duty cycle. METHODS: We describe methodologies for estimating and temporally predicting respiratory liver motion from continuous ultrasound imaging, used during ultrasound-guided radiation therapy. Furthermore, we investigated the trade-off between tracking accuracy and runtime in combination with temporal prediction strategies and their impact on treatment margins. RESULTS: Based on 2D ultrasound sequences from 39 volunteers, a mean tracking accuracy of 0.9 mm was achieved when combining the results from the 4 challenge submissions (1.2 to 3.3 mm). The two submissions for the 3D sequences from 14 volunteers provided mean accuracies of 1.7 and 1.8 mm. In combination with temporal prediction, using the faster (41 vs 228 ms) but less accurate (1.4 vs 0.9 mm) tracking method resulted in substantially reduced treatment margins (70% vs 39%) in contrast to mid-ventilation margins, as it avoided non-linear temporal prediction by keeping the treatment system latency low (150 vs 400 ms). Acceleration of the best tracking method would improve the margin reduction to 75%. CONCLUSIONS: Liver motion estimation and prediction during free-breathing from 2D ultrasound images can substantially reduce the in-plane motion uncertainty and hence treatment margins. Employing an accurate tracking method while avoiding non-linear temporal prediction would be favorable. This approach has the potential to shorten treatment time compared to breath-hold and gated approaches, and increase treatment efficiency and safety.

Real-time target tracking of soft tissues in 3D ultrasound images based on robust visual information and mechanical simulation.

In this paper, we present a real-time approach that allows tracking deformable structures in 3D ultrasound sequences. Our method consists in obtaining the target displacements by combining robust dense motion estimation and mechanical model simulation. We perform evaluation of our method through simulated data, phantom data, and real-data. Results demonstrate that this novel approach has the advantage of providing correct motion estimation regarding different ultrasound shortcomings including speckle noise, large shadows and ultrasound gain variation. Furthermore, we show the good performance of our method with respect to state-of-the-art techniques by testing on the 3D databases provided by MICCAI CLUST'14 and CLUST'15 challenges.

Shearlet transform: a good candidate for compressed sensing in optical coherence tomography.

This paper deals with the development of a fast and smart acquisition technique of Optical Coherence Tomography (OCT) data that has the capability to reconstruct missing data of OCT image. The main objective is to reduce the acquisition time (i.e., increase the frame rate) of an OCT-scan system by choosing a trajectory that covers entirely the image but that does not take all the measurements. The reconstruction of the missing data is achieved by applying an updated Fast Iterative Soft-Thresholding Algorithm (FISTA) on a sparse representation of the image. Several sparse representations have been tested and the shearlets-based approach seems to outperform the other ones (e.g. wavelets, curvelets and by applying bilinear interpolation). The targeted application is a fast OCT imaging solution allowing an efficient compensation of the artefacts induced by the patient physiological motions for diagnostic purpose through optical biopsies (3D micrometric resolution optical images). The obtained results seem promising in terms of low time processing and improvement of the quality of the reconstructed image compared to the traditional sparse acquisition.

3D steering of a flexible needle by visual servoing.

This paper presents a robotic control method for 3D steering of a beveled-tip flexible needle. The solution is based on a new duty-cycling control strategy that makes possible to control three degrees of freedom of the needle. A visual servoing control scheme using two orthogonal cameras observing a translucent phantom is then proposed to automatically steer a needle toward a 3D target point. Experimental results show a final positioning error of 0.4 mm and demonstrate the feasibility of this promising approach and its robustness to model errors.

Automatic tracking of an organ section with an ultrasound probe: compensation of respiratory motion.

In minimally invasive surgery or needle insertion procedures, the ultrasound imaging can easily and safely be used to visualize the target to reach. However the manual stabilization of the view of this target, which undergoes the physiological motions of the patient, can be a challenge for the surgeon. In this paper, we propose to perform this stabilization with a robotic arm equipped with a 2D ultrasound probe. The six degrees of freedom of the probe are controlled by an image-based approach, where we choose as visual feedback the image intensity. The accuracy of the control law is ensured by the consideration of the periodicity of the physiological motions in a predictive controller. Tracking tasks performed on a realistic abdominal phantom validate the proposed approach and its robustness to deformation is assessed on a gelatin-made deformable phantom.

Automatic guidance of an ultrasound probe by visual servoing based on B-mode image moments.

We propose a new visual servo approach to automatically control in real-time the full motion of a 2D ultrasound (US) probe held by a medical robot in order to reach a desired image of motionless soft tissue object in B-mode ultrasound imaging. Combinations of image moments of the observed object cross-section are used as feedback information in the visual control scheme. These visual features are extracted in real-time from the US image thanks to a fast image segmentation method. Simulations performed with a static US volume containing an egg-shaped object, and ex-vivo experiments using a robotized US probe that interacts with a motionless rabbit heart immersed in water, show the validity of this new approach and its robustness to different perturbations. This method shows promise for a variety of US-guided medical interventions that require real-time servoing.

Real-time tissue tracking with B-mode ultrasound using speckle and visual servoing.

We present a method for real-time tracking of moving soft tissue with B-mode ultrasound (US). The method makes use of the speckle information contained in the US images to estimate the in-plane and out-of-plane motion of a fixed target relative to the ultrasound scan plane. The motion information is then used as closed-loop feedback to a robot which corrects for the target motion. The concept is demonstrated for translation motions in an experimental setup consisting of an ultrasound speckle phantom, a robot for simulating tissue motion, and a robot that performs motion stabilization from US images. This concept shows promise for US-guided procedures that require real-time motion tracking and compensation.