Explore the vast range of titles available.

The global numbers of robotic gastrointestinal surgeries are increasing. However, the evidence base for robotic gastrointestinal surgery does not yet support its widespread adoption or justify its cost. The reasons for its continued popularity are complex, but a notable driver is the push for innovation — robotic surgery is seen as a compelling solution for delivering on the promise of minimally invasive precision surgery — and a changing commercial landscape delivers the promise of increased affordability. Novel systems will leverage the robot as a data-driven platform, integrating advances in imaging, artificial intelligence and machine learning for decision support. However, if this vision is to be realized, lessons must be heeded from current clinical trials and translational strategies, which have failed to demonstrate patient benefit. In this Perspective, we critically appraise current research to define the principles on which the next generation of gastrointestinal robotics trials should be based. We also discuss the emerging commercial landscape and define existing and new technologies.The evidence base for robotic gastrointestinal surgery does not yet support its widespread adoption. Here, Kinross et al. discuss this evidence base and the principles on which future gastrointestinal surgical trials should be based, as well as emerging technologies.

This systematic review analyses advancements in cognitive state recognition from 2010 to early 2024, evaluating 405 relevant articles from an initial pool of 2398 records identified through five databases: Scopus, Engineering Village, Web of Science, IEEE Xplore, and PubMed. Studies were included if they assessed cognitive states using physiological signals and applied machine learning (ML) or deep learning (DL) techniques in practical task settings. The review highlights a pivotal shift from shallow ML to DL approaches for analysing physiological signals, driven by DL’s ability to autonomously learn complex patterns in large datasets. By 2023, DL has become the dominant methodology, though traditional ML techniques remain relevant. Additionally, there has been a move from neuroimaging to multimodal physiological modalities, with the decrease in neuroimaging use reflecting a trend towards integrating various physiological signals for more comprehensive insights. Cognitive state recognition is applied across diverse domains such as the automotive, aviation, maritime, and healthcare industries, enhancing performance and safety in high-stakes environments. Electrocardiogram (ECG) is the most utilised modality, with convolutional neural networks (CNNs) being the primary DL approach. The trend in cognitive state recognition research is moving towards integrating ECG signals with CNNs and adopting privacy-preserving methodologies like differential privacy and federated learning, highlighting the potential of cognitive state recognition to enhance performance, safety, and innovation across various real-world applications.

Tendon–sheath structures are commonly utilized to drive surgical robots due to their compact size, flexibility, and straightforward controllability. However, long-distance cable tension estimation poses a significant challenge due to its frictional characteristics affected by complicated factors. This paper proposes a miniature tension sensor array for an endoscopic cable-driven parallel robot, aiming to integrate sensors into the distal end of long and flexible surgical instruments to sense cable tension and alleviate friction between the tendon and sheath. The sensor array, mounted at the distal end of the robot, boasts the advantages of a small size (16 mm outer diameter) and reduced frictional impact. A force compensation strategy was presented and verified on a platform with a single cable and subsequently implemented on the robot. The robot demonstrated good performance in a series of palpation tests, exhibiting a 0.173 N average error in force estimation and a 0.213 N root-mean-square error. In blind tests, all ten participants were able to differentiate between silicone pads with varying hardness through force feedback provided by a haptic device.

Minimally invasive surgery (MIS) presents many constraints on the design of robotic devices that can assist medical staff with a procedure. The limitations of conventional, rigid robotic devices have sparked interest in soft robotic devices for medical applications. However, problems still remain with the force exertion and positioning capabilities of soft robotic actuators, in conjunction with size restrictions necessary for MIS. In this article we present hydraulically actuated soft actuators that demonstrate highly repeatable open loop positioning and the ability to exert significant forces in the context of MIS. Open loop position control is achieved by changing the actuator volume, which causes contraction. In one degree of freedom (DOF) configurations, root mean square error (RMSE) values of 0.471 mm, 1.506 mm, and 0.350 mm were recorded for a single actuator against gravity, a single actuator with a pulley, and a horizontal antagonistic configuration, respectively. Hysteresis values of 0.711 mm, 0.958 mm, and 0.515 mm were reported in these experiments. In addition, different numbers of soft actuators were used in configurations two and three DOFs to demonstrate position control. When deactivated, the soft actuators are low-profile and flexible as they are constructed from thin films. As such, a robot with a deployable structure and three soft actuators was constructed. The robot is therefore able to reversibly transition from low to high volume and stiffness, which has potential applications in MIS. A user successfully controlled the deployable robot in a circle tracing task.

This paper introduces a soft, cable-driven parallel robot for minimally invasive surgeries. The robot comprises a pneumatic inflatable scaffold, six hydraulic, folded pouch actuators, and a hollow, cylindrical end-effector offering five degrees of freedom. A key development is the design of the pouch actuators, which are small, low-profile, simple structures, capable of a high stroke of 180° angular displacement. The scaffold, actuators, and plastic cables are economically and rapidly fabricated using laser cutting and welding techniques. Constructed primarily from soft plastic materials, the robot can be compactly folded into a cylinder measuring 110 mm in length and 14 mm in diameter. Upon inflation, the scaffold transforms into a hexagonal prism structure with side lengths of 34 mm and edge lengths of 100 mm. The kinematic model of the robot has been developed for workspace calculation and control purposes. A series of tests have been conducted to evaluate the performance of the actuator and the robot. Repeatability tests demonstrate the robot’s high repeatability, with mean and root mean square errors of 0.3645 mm and 0.4186 mm, respectively. The direct connection between the end-effector and the actuators theoretically eliminates cable friction, resulting in a hysteresis angle of less than 2°, as confirmed by the tracking results. In addition, simulated surgical tasks have been performed to further demonstrate the robot’s performance.

Gastrointestinal endoscopy is a subjective procedure that frequently requires tissue samples for diagnosis. Contact optical biopsy (OB) techniques have the aim of providing direct diagnosis of endoscopic areas without excising tissue samples but lack the wide‐area coverage required for locating and resecting lesions. This article presents a large‐area robotically deployed OB imaging platform for endoscopic detection of colorectal cancer as an add‐on for conventional endoscopes. In vitro, in silicon colon phantoms, the platform achieves an optical resolution of 0.5 line pairs per millimeter, while resolving simulated cancer lesions down to 0.75 mm diameter across large‐area images (55‐103 cm2). Large‐area OB images were generated in an ex vivo porcine colon. The platform allows centimeter‐sized large‐area OB imaging in vitro and ex vivo with submillimeter resolution, including automatic data segmentation of simulated cancer areas. The ability for robotic actuation and spectrum collection is also shown for ex vivo animal colon. If successful, this technology could widen access to user‐independent high‐quality endoscopy and early detection of gastrointestinal cancers. This article presents a large‐area OB imaging platform as an endoscopic add‐on for the detection of colorectal cancer. The scanning range, resolution, and spectral classification performance of the integrated robotic deployment and actuation of a radial array of OB probes was determined in vitro and ex vivo. Data are processed in near real‐time to generate color and segmented large‐area images with submillimeter resolution, demonstrating potential for computer‐assisted detection and diagnosis of cancer.

Background Eye-tracking technology has been shown to improve trainee performance in the aircraft industry, radiology, and surgery. The ability to track the point-of-regard of a supervisor and reflect this onto a subjects’ laparoscopic screen to aid instruction of a simulated task is attractive, in particular when considering the multilingual make up of modern surgical teams and the development of collaborative surgical techniques. We tried to develop a bespoke interface to project a supervisors’ point-of-regard onto a subjects’ laparoscopic screen and to investigate whether using the supervisor’s eye-gaze could be used as a tool to aid the identification of a target during a surgical-simulated task. Methods We developed software to project a supervisors’ point-of-regard onto a subjects’ screen whilst undertaking surgically related laparoscopic tasks. Twenty-eight subjects with varying levels of operative experience and proficiency in English undertook a series of surgically minded laparoscopic tasks. Subjects were instructed with verbal queues (V), a cursor reflecting supervisor’s eye-gaze (E), or both (VE). Performance metrics included time to complete tasks, eye-gaze latency, and number of errors. Results Completion times and number of errors were significantly reduced when eye-gaze instruction was employed (VE, E). In addition, the time taken for the subject to correctly focus on the target (latency) was significantly reduced. Conclusions We have successfully demonstrated the effectiveness of a novel framework to enable a supervisor eye-gaze to be projected onto a trainee’s laparoscopic screen. Furthermore, we have shown that utilizing eye-tracking technology to provide visual instruction improves completion times and reduces errors in a simulated environment. Although this technology requires significant development, the potential applications are wide-ranging.

Introduction Current dietary assessment methods struggle to accurately capture individuals' dietary habits. The 'Standardised and Objective Dietary Intake Assessment Tool' (SODIAT)-1 study aims to assess the effectiveness of three emerging technologies (urine and capillary blood biomarkers, wearable camera technology) and two online self-reporting dietary assessment tools to monitor dietary intake. Methods This randomised controlled crossover trial was conducted at two sites (Hammersmith Hospital and the University of Reading) and aimed to recruit 30 UK participants (aged 18-70 years, BMI 20-30 kg/m 2). Exclusion criteria included recent weight change, food allergies/intolerances, restrictive diets, certain health conditions and medication use. Volunteers completed an online screening questionnaire via REDCap and eligible participants attended a pre-study visit. Participants consumed, in a random order, two highly-controlled diets (compliant/non-compliant with UK guidelines) for four consecutive days, separated by at least one-week. Dietary intake was monitored daily using wearable cameras and self-recorded using Intake24 (24HR). Two versions of the online eNutri FFQ were completed: at baseline to assess habitual diet and on day 4 of each test period to record food intake. Urine and capillary blood samples were collected for biomarker analysis. Data analysis will assess dietary reporting accuracy across these methods using Lin's concordance correlation coefficient. Discussion and ethical considerations The SODIAT project introduced a novel approach to dietary assessment, aiming to address the limitations like misreporting and inclusivity. However, challenges persist, such as variability in biomarker data due to failure to follow sample storage requirements and the practicalities of wearing cameras throughout the day. To protect privacy, participants removed cameras at inappropriate times, and AI removed non-food related images and blurred faces/device screens captured on the images. The accuracy of the tools in a highly-controlled setting will be evaluated in this study. Future studies are planned to validate these tools further in free-living and minority populations.

Accurate kinematic models are essential for effective control of surgical robots. For tendon driven robots, which are common for minimally invasive surgery, the high nonlinearities in the transmission make modelling complex. Machine learning techniques are a preferred approach to tackle this problem. However, surgical environments are rarely structured, due to organs being very soft and deformable, and unpredictable, for instance, because of fluids in the system, wear and break of the tendons that lead to changes of the system’s behaviour. Therefore, the model needs to quickly adapt. In this work, we propose a method to learn the kinematic model of a redundant surgical robot and control it to perform surgical tasks both autonomously and in teleoperation. The approach employs Feedforward Artificial Neural Networks (ANN) for building the kinematic model of the robot offline, and an online adaptive strategy in order to allow the system to conform to the changing environment. To prove the capabilities of the method, a comparison with a simple feedback controller for autonomous tracking is carried out. Simulation results show that the proposed method is capable of achieving very small tracking errors, even when unpredicted changes in the system occur, such as broken joints. The method proved effective also in guaranteeing accurate tracking in teleoperation.

Longitudinal changes in cortical function are known to accompany motor skills learning, and can be detected as an evolution in the activation map. These changes include attenuation in activation in the prefrontal cortex and increased activation in primary and secondary motor regions, the cerebellum and posterior parietal cortex. Despite this, comparatively little is known regarding the impact of the mode or type of training on the speed of activation map plasticity and on longitudinal variation in network architectures. To address this, we randomised twenty-one subjects to learn a complex motor tracking task delivered across six practice sessions in either “free-hand” or “gaze-contingent motor control” mode, during which frontoparietal cortical function was evaluated using functional near infrared spectroscopy. Results demonstrate that upon practice termination, gaze-assisted learners had achieved superior technical performance compared to free-hand learners. Furthermore, evolution in frontoparietal activation foci indicative of expertise was achieved at an earlier stage in practice amongst gaze-assisted learners. Both groups exhibited economical small world topology; however, networks in learners randomised to gaze-assistance were less costly and showed higher values of local efficiency suggesting improved frontoparietal communication in this group. We conclude that the benefits of gaze-assisted motor learning are evidenced by improved technical accuracy, more rapid task internalisation and greater neuronal efficiency. This form of assisted motor learning may have occupational relevance for high precision control such as in surgery or following re-learning as part of stroke rehabilitation. ► A neuroergonomic paradigm is employed to investigate technology assisted learning. ► Characterisation of longitudinal changes in frontoparietal networks with graph theory ► Gaze contingent learning leads to enhanced performance. ► Evolution in frontoparietal activation changes occurs earlier with gaze assistance. ► More economical and efficient frontoparietal networks were found with gaze assistance.