Learning-based endovascular navigation through the use of non-rigid registration for collaborative robotic catheterization.

PURPOSE: Endovascular intervention is limited by two-dimensional intraoperative imaging and prolonged procedure times in the presence of complex anatomies. Robotic catheter technology could offer benefits such as reduced radiation exposure to the clinician and improved intravascular navigation. Incorporating three-dimensional preoperative imaging into a semiautonomous robotic catheterization platform has the potential for safer and more precise navigation. This paper discusses a semiautonomous robotic catheter platform based on previous work (Rafii-Tari et al., in: MICCAI2013, pp 369-377. https://doi.org/10.1007/978-3-642-40763-5_46 , 2013) by proposing a method to address anatomical variability among aortic arches. It incorporates anatomical information in the process of catheter trajectories optimization, hence can adapt to the scale and orientation differences among patient-specific anatomies. METHODS: Statistical modeling is implemented to encode the catheter motions of both proximal and distal sites based on cannulation data obtained from a single phantom by an expert operator. Non-rigid registration is applied to obtain a warping function to map catheter tip trajectories into other anatomically similar but shape/scale/orientation different models. The remapped trajectories were used to generate robot trajectories to conduct a collaborative cannulation task under flow simulations. Cross-validations were performed to test the performance of the non-rigid registration. Success rates of the cannulation task executed by the robotic platform were measured. The quality of the catheterization was also assessed using performance metrics for manual and robotic approaches. Furthermore, the contact forces between the instruments and the phantoms were measured and compared for both approaches. RESULTS: The success rate for semiautomatic cannulation is 98.1% under dry simulation and 94.4% under continuous flow simulation. The proposed robotic approach achieved smoother catheter paths than manual approach. The mean contact forces have been reduced by 33.3% with the robotic approach, and 70.6% less STDEV forces were observed with the robot. CONCLUSIONS: This work provides insights into catheter task planning and an improved design of hands-on ergonomic catheter navigation robots.

Objective Assessment of Endovascular Navigation Skills with Force Sensing.

Despite the increasing popularity of endovascular intervention in clinical practice, there remains a lack of objective and quantitative metrics for skill evaluation of endovascular techniques. Data relating to the forces exerted during endovascular procedures and the behavioral patterns of endovascular clinicians is currently limited. This research proposes two platforms for measuring tool forces applied by operators and contact forces resulting from catheter-tissue interactions, as a means of providing accurate, objective metrics of operator skill within a realistic simulation environment. Operator manipulation patterns are compared across different experience levels performing various complex catheterization tasks, and different performance metrics relating to tool forces, catheter motion dynamics, and forces exerted on the vasculature are extracted. The results depict significant differences between the two experience groups in their force and motion patterns across different phases of the procedures, with support vector machine (SVM) classification showing cross-validation accuracies as high as 90% between the two skill levels. This is the first robust study, validated across a large pool of endovascular specialists, to present objective measures of endovascular skill based on exerted forces. The study also provides significant insights into the design of optimized metrics for improved training and performance assessment of catheterization tasks.

Reducing contact forces in the arch and supra-aortic vessels using the Magellan robot.

OBJECTIVE: Conventional catheter manipulation in the arch and supra-aortic trunks carries a risk of cerebral embolization. This study proposes a platform for detailed quantitative analysis of contact forces (CF) exerted on the vasculature, in order to investigate the potential advantages of robotic navigation. METHODS: An anthropomorphic phantom representing a type I bovine arch was mounted and coupled onto a force/torque sensor. Three-axis force readings provided an average root-mean-square modulus, indicating the total forces exerted on the phantom. Each of the left subclavian, left common carotid, and right common carotid arteries was cannulated within a simulated endovascular suite with conventional (n = 42) vs robotic techniques (n = 30) by two operator groups: experts and novices. The procedure path was divided into three phases, and performance metrics corresponding to mean and maximum forces, force impact over time, standard deviation of forces, and number of significant catheter contacts with the arterial wall were extracted. RESULTS: Overall, median CF were reduced from 1.20 N (interquartile range [IQR], 0.98-1.56 N) to 0.31 N (IQR, 0.26-0.40 N; P < .001) for the right common carotid artery; 1.59 N (IQR, 1.11-1.85 N) to 0.33 N (IQR, 0.29-0.43 N; P < .001) for the left common carotid artery; and 0.84 N (IQR, 0.47-1.08 N) to 0.10 N (IQR, 0.07-0.17 N; P < .001) for the left subclavian artery. Robotic navigation resulted in significant reductions for the mean and maximum forces for each procedural phase. Significant improvements were also seen in other metrics, particularly at the target vessel ostium and for the more anatomically challenging procedural phases. Force reductions using robotic technology were evident for both novice and expert groups. CONCLUSIONS: Robotic navigation can potentially reduce CF and catheter-tissue contact points in an in vitro model, by enhancing catheter stability and control during endovascular manipulation.

Panorama Ultrasound for Navigation and Guidance of Epidural Anesthesia.

Despite the common use of epidural anesthesia in obstetrics and surgery, the procedure can be challenging, especially for obese patients. We propose the use of an ultrasound guidance system employing a transducer-mounted camera to create 3-D panorama ultrasound volumes of the spine, thereby allowing identification of vertebrae and selection of puncture site, needle trajectory and depth of insertion. The camera achieves absolute position estimation of the transducer with respect to the patient using a specialized marker strip attached to the skin surface. The guidance system is validated first on a phantom against a commercial optical tracking system and then in vivo by comparing panorama images from human subjects against independent measurements by an experienced sonographer. The results for measuring depth to the epidural space, intervertebral spacing and registration of interspinous gaps to the skin prove the potential of the system for improving guidance of epidural anesthesia. The tracking and visualization are implemented in real time using the 3D Slicer software package.

Force-Sensing Enhanced Simulation Environment (ForSense) for laparoscopic surgery training and assessment.

BACKGROUND: Excessive or inappropriate tissue interaction force during laparoscopic surgery is a recognized contributor to surgical error, especially for robotic surgery. Measurement of force at the tool-tissue interface is, therefore, a clinically relevant skill assessment variable that may improve effectiveness of surgical simulation. Popular box trainer simulators lack the necessary technology to measure force. The aim of this study was to develop a force sensing unit that may be integrated easily with existing box trainer simulators and to (1) validate multiple force variables as objective measurements of laparoscopic skill, and (2) determine concurrent validity of a revised scoring metric. METHODS: A base plate unit sensitized to a force transducer was retrofitted to a box trainer. Participants of 3 different levels of operative experience performed 5 repetitions of a peg transfer and suture task. Multiple outcome variables of force were assessed as well as a revised scoring metric that incorporated a penalty for force error. RESULTS: Mean, maximum, and overall magnitudes of force were significantly different among the 3 levels of experience, as well as force error. Experts were found to exert the least force and fastest task completion times, and vice versa for novices. Overall magnitude of force was the variable most correlated with experience level and task completion time. The revised scoring metric had similar predictive strength for experience level compared with the standard scoring metric. CONCLUSION: Current box trainer simulators can be adapted for enhanced objective measurements of skill involving force sensing. These outcomes are significantly influenced by level of expertise and are relevant to operative safety in laparoscopic surgery. Conventional proficiency standards that focus predominantly on task completion time may be integrated with force-based outcomes to be more accurately reflective of skill quality.

Hierarchical HMM based learning of navigation primitives for cooperative robotic endovascular catheterization.

Despite increased use of remote-controlled steerable catheter navigation systems for endovascular intervention, most current designs are based on master configurations which tend to alter natural operator tool interactions. This introduces problems to both ergonomics and shared human-robot control. This paper proposes a novel cooperative robotic catheterization system based on learning-from-demonstration. By encoding the higher-level structure of a catheterization task as a sequence of primitive motions, we demonstrate how to achieve prospective learning for complex tasks whilst incorporating subject-specific variations. A hierarchical Hidden Markov Model is used to model each movement primitive as well as their sequential relationship. This model is applied to generation of motion sequences, recognition of operator input, and prediction of future movements for the robot. The framework is validated by comparing catheter tip motions against the manual approach, showing significant improvements in the quality of catheterization. The results motivate the design of collaborative robotic systems that are intuitive to use, while reducing the cognitive workload of the operator.

Current and emerging robot-assisted endovascular catheterization technologies: a review.

Endovascular techniques have been embraced as a minimally-invasive treatment approach within different disciplines of interventional radiology and cardiology. The current practice of endovascular procedures, however, is limited by a number of factors including exposure to high doses of X-ray radiation, limited 3D imaging, and lack of contact force sensing from the endovascular tools and the vascular anatomy. More recently, advances in steerable catheters and development of master/slave robots have aimed to improve these practices by removing the operator from the radiation source and increasing the precision and stability of catheter motion with added degrees-of-freedom. Despite their increased application and a growing research interest in this area, many such systems have been designed without considering the natural manipulation skills and ergonomic preferences of the operators. Existing studies on tool interactions and natural manipulation skills of the operators are limited. In this manuscript, new technical developments in different aspects of robotic endovascular intervention including catheter instrumentation, intra-operative imaging and navigation techniques, as well as master/slave based robotic catheterization platforms are reviewed. We further address emerging trends and new research opportunities towards more widespread clinical acceptance of robotically assisted endovascular technologies.

Learning-based modeling of endovascular navigation for collaborative robotic catheterization.

Despite rapid growth of robot assisted catheterization in recent years, most current platforms are based on master-slave designs with limited operator-robot collaborative control and automation. Under this setup, information concerning subject specific behavior and context-driven manoeuvre is not re-utilized for subsequent intervention. For endovascular catheterization, the robot itself is designed with little consideration of underlying skills and associated motion patterns. This paper proposes a learning-based approach for generating optimum motion trajectories from multiple demonstrations of a catheterization task such that it can be used for automating catheter motion within a collaborative setting. Motion models are generated from experienced manipulation of a catheterization procedure and replicated using a robotic catheter driver to assist inexperienced operators. Catheter tip motions of the automated approach are compared against the manual training sets for validating the proposed framework. The results show significant improvements in the quality of catheterization, which facilitate the design of hands-on collaborative robots that make full use of the natural skills of the operators.

Utility of prepuncture ultrasound for localization of the thoracic epidural space.

BACKGROUND: Ultrasound has been shown to facilitate accurate identification of the intervertebral level and to predict skin-to-epidural depth in the lumbar epidural space with reliable precision. We hypothesized that we could accurately predict the skin-to-epidural depth and the intervertebral level in the thoracic spine with the use of ultrasound. METHODS: Twenty patients presenting for thoracic surgery were included in a feasibility study. The skin-to-epidural depth was measured using prepuncture ultrasound in the paramedian window, and the predicted depth was compared with the actual needle depth and the depth as measured by computed tomography. In addition, the intervertebral levels were identified by ultrasound using the "counting up" method, and the results were compared with the levels identified by anesthesiologists. RESULTS: The ultrasound-based depth measurements displayed a bias of 3.21 mm with 95% limits of agreement from -7.47 to 13.9 mm compared with the clinically determined needle depth. The intervertebral levels identified by the anesthesiologists and the sonographer matched in only 40% of cases. CONCLUSION: Ultrasound-based measurements of skin-to-epidural depth show acceptable agreement with the actual depth observed during epidural catheterization; however, the limits of agreement are wide, which restricts the predictive value of ultrasound-based measurements. Further study is required to delineate the role of ultrasound in thoracic epidural catheterizations.