Ultrasound-Guided Regional Anesthesia (UGRA) becomes a standard procedure in surgical operations and contributes to pain management. It offers the advantages of the targeted nerve detection and provides the visualization of regions of interest such as anatomical structures. However, nerve detection is one of the most challenging tasks that anesthetists can encounter in the UGRA procedure. A computer-aided system that can detect automatically the nerve region would facilitate the anesthetist's daily routine and allow them to concentrate more on the anesthetic delivery. In this paper, we propose a new method based on merging deep learning models from different data to detect the median nerve. The merged architecture consists of two branches, one being one-dimensional (1D) convolutional neural networks (CNN) branch and another 2D CNN branch. The merged architecture aims to learn the high-level features from 1D handcrafted noise-robust features and 2D ultrasound images. The obtained results show the validity and high accuracy of the proposed approach and its robustness.

Medical telerobotic systems provide a framework for performing interventional and diagnostic procedures remotely utilizing communication networks. Over the past decade, various systems have demonstrated the feasibility and the significance of telerobotics, some of which have been already adopted in clinical practice. In this study, we elaborate on the potential and discuss associated challenges focusing on the enabling technologies, namely robotic manipulation, telecommunications, and vision systems. A case study of an end-to-end mobile teleechography software platform using the MELODY robotic system is presented, investigating the capability of commercially available 4G (and beyond) wireless networks to communicate clinically lossless medical video for remote diagnosis purposes. Performance analysis demonstrates that medical video transmission approaching the clinical standards of in-hospital examination while conforming to strict delay requirements is achievable.

In this paper, we provide a new generalized kinematic formulation of the Remote Center of Motion (RCM) constraint for serial robotic arms to be useful for implementation in torque-controlled robots. A minimally invasive surgery assisted by a serial robot could be used for inserting a surgical tool through a desired insertion position, i.e. trocar position. The restricted movement caused by the trocar, i.e. the RCM constraint, must be guaranteed by the robotic system in order to avoid injury to the patient. The generalized formulation, presented in this paper, associates the task-space with the RCM constraint coordinates, which are described by the minimum distance between the surgical tool and the trocar position. In order to simultaneously achieve the surgical tool-tip trajectory and the RCM constraint, two control methods are proposed and compared, one using a projection in the null-space, the other by combining both tasks using a task-space augmentation method. Moreover, when additional lower priority tasks have to be implemented in the null-space of the two higher priority tasks, the kinematic formulation simplifies the calculation of the null-space projectors. Furthermore, unlike the previous studies, the formulation represented can be applied not only in a kinematic control but also in a dynamic control approach. Simulations were conducted to validate effectiveness of the proposed formulation, using a planar 4-DOF system as well as the dynamic model of a Kuka LBR 7 iiwa R800 robot arm.

The leading advantage of Ultrasound-Guided Regional Anesthesia (UGRA) is the ability to visualize the anatomical structure of interest. The nerve detection should translate into greater efficacy, by ensuring accurate deposition and spread of local anesthetic around the target nerve. The identification of nerve is among the most difficult tasks that anesthetists can encounter in the UGRA procedure. It is important to develop an automatic nerve detection algorithm to assist the UGRA practitioners. However, robust and automated nerve detection is challenging due to inherent noise and artifacts in ultrasound images and to the variability of the nerve structure. In order to deal with such a problem we propose a new method based on learning and estimating a dynamic on-line model of nerve position consistency and confidence measure by using generalized Gaussian distribution assumption. Based on that, Naive Bayesian measure is used to indicate whether a detected nerve region is reliable or not. Experiments were conducted on 7000 ultrasound images from 10 patients achieving an average f-score of 83%.

In this paper, we present a dynamically consistent control approach for manipulators with Cartesian Admittance Control (CAC) while guaranteeing a Remote Center of Motion (RCM) constraint. The dynamically consistent extended formulation was used in order to achieve a dynamically decoupled redundancy resolution, while a null-motion feedback was implemented that improves the tracking of the null-motion. Minimally Invasive Surgery (MIS) procedures are proposed as applications of the control approach formulated in this paper. The effectiveness of the proposed control approach was verified in simulation by using the Kuka LBR 7 iiwa R800 robot arm.

Ultrasound-guided regional anaesthesia (UGRA) is growing rapidly in the medical field, and becomes a standard procedure in many worldwide hospitals. UGRA can specifically benefit from image processing and machine learning techniques. Very few studies have been developed for that purpose. This paper focuses on automatic localization of nerve in ultrasound images, in order to assist anaesthetists during UGRA procedure. Due to the complex structure of nerve and poor quality of ultrasound images, the automatic detection of nerve region is a challenging problem. To handle such issue, several processing phases are required. For that purpose, we propose a new method, based on despeckling, feature ranking and majority vote classification, for a robust and accurate median nerve localization. The proposed method is applied on a real dataset obtained from eight patients. The obtained results showed high performance for median nerve detection achieving accuracy of 89% of the f-score measure.

Performing a robotized telemedicine act via specific networks brings forth two issues. One is transparency in order to enable the operator, e.g. the medical ultrasound specialist, to safely and accurately perform bilateral tele-operation tasks despite the long time delays inherent to the communication link. To counter these effects, two strategies are combined to improve, at the operator site, the rendering of the interactions between the remote robotic systems with its environment (i.e. the patient), and the control of the robot's orientation. The first approach is the development of a new control architecture based on an internal model providing an anticipated value of the distant environment stiffness; it is complemented with a graphic user interface (GUI) which provides the expert with the real-time relative position of the haptic probe with the robot's end effector for a better tele-operated control. These combined strategies provide the expert with an improved interactive tool for a tele-diagnosis.

This paper presents a new navigation method for mobile robots, based on direct kinematics model and predictive control approach. It is adaptable to all types of robots taking into account their specific constraints. The research of the optimal trajectory is shifted in the continuous parameters space, which enables the exploitation of all of the robot's capabilities. The use of a stochastic algorithm enables the determination of obstacle bypass trajectories, and simulation results show that the navigation in cluttered environment is improved.

This paper proposes a new ergonomic frame to describe the attitude of a robot arm and to be used for human-machine interface in telerobotic with application to telesonography. A three part psychophysical analysis enabled us to design this new system of angles exhibiting a good decorrelation among its degrees of freedom. A decorrelation improvement of up to 83% can be noticed compare to the standard 3-1-3 Euler angles. This new frame has been exploited to conceive human-machine interface with a low cost input device such as the standard IT mouse. Psychophysical results show indisputable superiority of our new system compare to the standard Euler one for orientation tracking in teleoperation conditions.

This paper presents two approaches developed to control our CyCab mobile robot. The first one introduces the notion of virtual axle to determine a flat Inverse Kinematics Model; the second one, based on the Escape Lanes method, uses the Direct Kinematics Model. In the last part of this paper, a comparison between the two methods is carried out in order to validate the inverse model and to discuss the two methods respective advantages.

This article addresses the omni directional mechanical architectures problematic for mobile robots using 3 motorized axles with 2 spherical orthogonal wheels. These wheels transmit a power torque according to a direction and are completely free with respect to the two others. They are used on 2 mechanical structures: SM1 and SM2. The complete kinematic study emphasizes the facility of controlling such omni-directional robots, and examines the problems involved in the transition of the wheel-to-floor contact on each axle. From this double study emerges an optimal theoretical architecture, but difficult to realize mechanically. We then present a controller which compensates for the errors related to the simplest mechanical structure; and it is validated on a mobile robot ROMNI using mechanical structure SM1

This paper presents a new tool for the evaluation of ultrasound image compression. The goal is to measure the image quality as easily as with a statistical criterion, and with the same reliability as the one provided by the medical assessment. An initial experiment is proposed to medical experts and represents our reference value for the comparison of evaluation criteria. Twenty-one statistical criteria are selected from the literature. A cumulative absolute similarity measure is defined as a distance between the criterion to evaluate and the reference value. A first fusion method based on a linear combination of criteria is proposed to improve the results obtained by each of them separately. The second proposed approach combines different statistical criteria and uses the medical assessment in a training phase with a support vector machine. Some experimental results are given and show the benefit of fusion.

This paper presents a tele-operated robot built within the OTELO European project framework. This six degree-of-freedom non-redundant probe-holder robot with a remote center of motion is dedicated to robotized medical tele-echography. The mechanical structure, chosen by end-users' specifications, presents a self-motion singularity within the working space of the medical expert. A strategy has been developed to counter the effect of the singularity located in the centre of the working space based on an real-time singularity control of the robotic tele-operated system. Thanks to the implementation of this real-time control, several clinical tele-echography tests have been successfully performed where medical specialists were able to propose a diagnosis in 80% of the studied cases.

This paper presents a new tele-operated robotic chain for real-time ultrasound image acquisition and medical diagnosis. This system has been developed in the frame of the Mobile Tele-Echography Using an Ultralight Robot European Project. A light-weight six degrees-of-freedom serial robot, with a remote center of motion, has been specially designed for this application. It holds and moves a real probe on a distant patient according to the expert gesture and permits an image acquisition using a standard ultrasound device. The combination of mechanical structure choice for the robot and dedicated control law, particularly nearby the singular configuration allows a good path following and a robotized gesture accuracy. The choice of compression techniques for image transmission enables a compromise between flow and quality. These combined approaches, for robotics and image processing, enable the medical specialist to better control the remote ultrasound probe holder system and to receive stable and good quality ultrasound images to make a diagnosis via any type of communication link from terrestrial to satellite. Clinical tests have been performed since April 2003. They used both satellite or Integrated Services Digital Network lines with a theoretical bandwidth of 384 Kb/s. They showed the tele-echography system helped to identify 66% of lesions and 83% of symptomatic pathologies.