E-learning has revolutionized medical education by providing flexible, accessible, and interactive learning opportunities. This article explores the transformative impact of e-learning on gastroenterology education, highlighting the advancements and benefits brought by the American Society for Gastrointestinal Endoscopy (ASGE) platforms. ASGE's e-learning platforms offer specialized content, interactive tools, and continuous updates, enhancing the learning experience for gastroenterologists.

Both the feasibility and clinical benefits of endoscopic interventions for colon lesions have been demonstrated by pioneering surgeons. Yet endoscopic approaches have not been widely deployed clinically because they are challenging to learn and perform with conventional endoscopes. Motivated by this, several robotic platforms have been created over the past few years with the goal of enhancing surgeon dexterity. To date, all such robots have used custom-made endoscopes with integrated manipulators. This typically results in robots significantly larger than conventional endoscopes, and the systems proposed would ultimately require hospitals to completely replace their conventional endoscopes with a new robotic solution, leading to undesirable cost and workflow ramifications. It has never before been possible to use conventional endoscopes directly with this type of system, because there were no robotic manipulators small, dexterous, and strong enough to pass through existing endoscope ports and enable the maneuvers needed to perform the surgery. In this paper, we show that the recent invention of steerable sheaths based on the concentric push-pull principle makes it possible to convert conventional endoscopes into multi-arm robotic platforms for colon procedures. We demonstrate our system in endoscopic submucosal dissection (ESD) in ex vivo porcine feasibility experiments. Even users with no prior experience in endoscopic submucosal dissection were able to successfully perform the procedure using our system.

Deep learning has the potential to improve colonoscopy by enabling 3D reconstruction of the colon, providing a comprehensive view of mucosal surfaces and lesions, and facilitating the identification of unexplored areas. However, the development of robust methods is limited by the scarcity of large-scale ground truth data. We propose RealSynCol, a highly realistic synthetic dataset designed to replicate the endoscopic environment. Colon geometries extracted from 10 CT scans were imported into a virtual environment that closely mimics intraoperative conditions and rendered with realistic vascular textures. The resulting dataset comprises 28 130 frames, paired with ground truth depth maps, optical flow, surface normals, 3D meshes, and camera trajectories. A benchmark study was conducted to evaluate the available synthetic colon datasets for the tasks of depth and pose estimation. Results demonstrate that the high realism and variability of RealSynCol significantly enhance generalization performance on clinical images, proving it to be a powerful tool for developing deep learning algorithms to support endoscopic diagnosis.

New endoscopists require a large volume of expert-proctored colonoscopies to attain minimal competency. Developing multi-fingered, synchronized control of a colonoscope requires significant time and exposure to the device. Current training methods inhibit this development by relying on tool hand-off for expert demonstrations. There is a need for colonoscopy training tools that enable in-hand expert guidance in real-time. We present a new concept of a tandem training system that uses a telemanipulated preceptor colonoscope to guide novice users as they perform a colonoscopy. This system is capable of dual-control and can automatically toggle between expert and novice control of a standard colonoscope's angulation control wheels. Preliminary results from a user study with novice and expert users show the effectiveness of this device as a skill acquisition tool. We believe that this device has the potential to accelerate skill acquisition for colonoscopy and, in the future, enable individualized instruction and responsive teaching through bidirectional actuation.

INTRODUCTION:Magnetic actuation of endoscopes is promising-as the endoscope can be pulled from its front. Our team developed a novel magnetic flexible endoscope (MFE) that uses magnetic field sensing, robotic control, and real-time image processing for colonoscopy. We conducted a Phase 1 first-in-human clinical trial to assess platform safety and tolerability. METHODS:Platform: The MFE contains an internal permanent magnet, camera, illumination module, and channels for instruments, insufflation/camera cleaning, irrigation, and suction. A robotic arm maneuvers a second permanent magnet coupled to the MFE. System software facilitates controlled intelligent magnetic actuation. Experiment: 5 patients scheduled for screening colonoscopy ( ICD-10 z12.11) were enrolled. Patients underwent standard of care colonoscopy with monitored anesthesia care. On withdrawal of the colonoscope, sedation was stopped, and after colonoscope removal, the MFE was inserted into the colon through the anus. The MFE was advanced through the colon while the patient was unsedated. After colon traversal, the MFE was withdrawn. Outcomes of interest included safety and tolerability of the MFE, participant sentiment through structured interview, platform usability, and robot pose data. RESULTS:All patients underwent successful standard of care colonoscopy. All patients were awake and alert for MFE colonoscopy, tolerating the examination well without discomfort, pain, or other complaint. There were no adverse events or trauma. The system was robust without software or function failure. DISCUSSION:The MFE successfully traversed the human colon without adverse event or patient discomfort. System performance was successful without unanticipated events. This is the first-time safety and tolerability of the novel platform has been demonstrated in vivo .

Colonoscopy is widely performed for direct visualization and therapeutic intervention in the colon. Although colonoscopy is a relatively safe procedure, there are several limitations because of the unintuitive drive mechanism and mechanical design of current conventional colonoscopes (CCs). These include sedation-related events, patient discomfort because of looping, perforation and colonic trauma, long learning curve and training time, variable quality, and endoscopist injury because of poor ergonomics.

Colonoscopy demands multi-finger coordinated motion to achieve safe navigation. As a result, training for colonoscopists is challenging and skill assessment currently relies on subjective scoring by expert proctors. There is a need to provide tools for skill assessment and aid with training new interventionalists. This paper presents a new concept of an in-hand robotic mediation device that can be used for both skill assessment and training. The robotic device can be used to infer the kinematic motion as well as the power input of a user - both of which are proposed to be used for skill assessment and subtask skill classification. Preliminary results collected expert and novice users performing colonoscopy navigation are used to demonstrate this device as a skill assessment tool. A machine-learning model (classification and regression trees) is used for subtask classification of skill and evaluating the most important classification features. A user study demonstrates the effectiveness of this in hand haptic training and assessment tool. We believe that, in the future, this device will enable accelerated skill assessment and training and possible semi-automation of difficult maneuvers.

An understanding of the biological environment, and in particular the physical morphology, is crucial for those developing medical devices and software applications. It not only informs appropriate design inputs, but provides the opportunity to evaluate outputs via virtual or synthetic models before investing in costly clinical investigations. The large bowel is a pertinent example, having a major demand for effective technological solutions to clinical unmet needs. Despite numerous efforts in this area, there remains a paucity of accurate and reliable data in literature. This work reviews what is available, including both processed datasets and raw medical images, before providing a comprehensive quantitative description of the environment for biomedical engineers in this and related regions of the body. Computed tomography images from 75 patients, and a blend of different mathematical and computational methods, are used to calculate and define several crucial metrics, including: a typical adult size (abdominal girth) and abdominal shape, location (or depth) of the bowel inside the abdomen, large bowel length, lumen diameter, flexure number and characteristics, volume and anatomical tortuosity. These metrics are reviewed and defined by both gender and body posture, as well as-wherever possible-being spilt into the various anatomical regions of the large bowel. The resulting data can be used to describe a realistic 'average' adult large bowel environment and so drive both design specifications and high fidelity test environments.

Wirelessly actuated miniature soft robots actuated by magnetic fields that can overcome gravity by climbing soft and wet tissues are promising for accessing challenging enclosed and confined spaces with minimal invasion for targeted medical operation. However, existing designs lack the directional steerability to traverse complex terrains and perform agile medical operations. Here we propose a rod-shaped millimeter-size climbing robot that can be omnidirectionally steered with a steering angle up to 360 degrees during climbing beyond existing soft miniature robots. The design innovation includes the rod-shaped robot body, its special magnetization profile, and the spherical robot footpads, allowing directional bending of the body under external magnetic fields and out-of-plane motion of the body for delivery of medical patches. With further integrated bio-adhesives and microstructures on the footpads, we experimentally demonstrated inverted climbing of the robot on porcine gastrointestinal (GI) tract tissues and deployment of a medical patch for targeted drug delivery.

Vanderbilt University Medical Center, USA.

Magnetically actuated robots have become increasingly popular in medical endoscopy over the past decade. Despite the significant improvements in autonomy and control methods, progress within the field of medical magnetic endoscopes has mainly been in the domain of enhanced navigation. Interventional tasks such as biopsy, polyp removal, and clip placement are a major procedural component of endoscopy. Little advancement has been done in this area due to the problem of adequately controlling and stabilizing magnetically actuated endoscopes for interventional tasks. In the present paper we discuss a novel model-based Linear Parameter Varying (LPV) control approach to provide stability during interventional maneuvers. This method linearizes the non-linear dynamic interaction between the external actuation system and the endoscope in a set of equilibria, associated to different distances between the magnetic source and the endoscope, and computes different controllers for each equilibrium. This approach provides the global stability of the overall system and robustness against external disturbances. The performance of the LPV approach is compared to an intelligent teleoperation control method (based on a Proportional Integral Derivative (PID) controller), on the Magnetic Flexible Endoscope (MFE) platform. Four biopsies in different regions of the colon and at two different system equilibria are performed. Both controllers are asked to stabilize the endoscope in the presence of external disturbances (i.e. the introduction of the biopsy forceps through the working channel of the endoscope). The experiments, performed in a benchtop colon simulator, show a maximum reduction of the mean orientation error of the endoscope of 45.8% with the LPV control compared to the PID controller.

We propose an endoscopic image mosaicking algorithm that is robust to light conditioning changes, specular reflections, and feature-less scenes. These conditions are especially common in minimally invasive surgery where the light source moves with the camera to dynamically illuminate close range scenes. This makes it difficult for a single image registration method to robustly track camera motion and then generate consistent mosaics of the expanded surgical scene across different and heterogeneous environments. Instead of relying on one specialised feature extractor or image registration method, we propose to fuse different image registration algorithms according to their uncertainties, formulating the problem as affine pose graph optimisation. This allows to combine landmarks, dense intensity registration, and learning-based approaches in a single framework. To demonstrate our application we consider deep learning-based optical flow, hand-crafted features, and intensity-based registration, however, the framework is general and could take as input other sources of motion estimation, including other sensor modalities. We validate the performance of our approach on three datasets with very different characteristics to highlighting its generalisability, demonstrating the advantages of our proposed fusion framework. While each individual registration algorithm eventually fails drastically on certain surgical scenes, the fusion approach flexibly determines which algorithms to use and in which proportion to more robustly obtain consistent mosaics.

Magnetically actuated endoscopes are currently transitioning in to clinical use for procedures such as colonoscopy, presenting numerous benefits over their conventional counterparts. Intelligent and easy-to-use control strategies are an essential part of their clinical effectiveness due to the un-intuitive nature of magnetic field interaction. However, work on developing intelligent control for these devices has mainly been focused on general purpose endoscope navigation. In this work, we investigate the use of autonomous robotic control for magnetic colonoscope intervention via biopsy, another major component of clinical viability. We have developed control strategies with varying levels of robotic autonomy, including semi-autonomous routines for identifying and performing targeted biopsy, as well as random quadrant biopsy. We present and compare the performance of these approaches to magnetic endoscope biopsy against the use of a standard flexible endoscope on bench-top using a colonoscopy training simulator and silicone colon model. The semi-autonomous routines for targeted and random quadrant biopsy were shown to reduce user workload with comparable times to using a standard flexible endoscope.

James Martin: NO financial relationship with a commercial interest

Background: End-stage liver disease (ESLD) is associated with high morbidity and mortality, with liver transplantation as the only existing cure. Despite reduced quality of life and limited life expectancy, referral to palliative care (PC) rarely occurs. Moreover, there is scarcity of data on the appropriate timing and type of PC intervention needed. Aim: To evaluate PC utilization and documentation in ESLD patients declined or delisted for transplant at a tertiary care medical center with a large liver transplantation program. Methods: We performed a retrospective cohort study of all patients discussed in Liver Transplant Committee (LTC) at our academic medical center between August 2018 and May 2020 in the United States. Patients declined or delisted for liver transplantation were included. Baseline demographics, model for end-stage liver disease (MELD) score, decompensation events, and reason for transplant ineligibility were recorded. The primary outcome was PC referral. Secondary outcomes included survival from LTC decision, time from LTC decision to PC referral, and code status in relation to PC referral. Results: Of 769 patients discussed at LTC, 135 were declined for transplantation. Thirty-seven (27%) received referral to PC. When adjusting for body mass index and age, MELD score of 21-30 had odds ratio (OR) of 4.5 (95% confidence interval [CI]: 1.7-12.3) and MELD score >30 had OR of 12.8 (95% CI: 3.9-47.7) for PC referral when compared with MELD score <20. When adjusting for MELD score, presence of ascites had OR of 4.6 (95% CI: 1.1-19.1) and presence of multiple complications had OR of 2.2 (95% CI: 2.2-3.8). Conclusions: Only 37 (27%) patients delisted or declined for liver transplantation were referred to PC. MELD score and degree of decompensation were important factors associated with referral. Continued exploration of these data could help guide future studies and help determine timing and criteria for PC referral.

Continuum manipulators, inspired by nature, have drawn significant interest within the robotics community. They can facilitate motion within complex environments where traditional rigid robots may be ineffective, while maintaining a reasonable degree of precision. Soft continuum manipulators have emerged as a growing subfield of continuum robotics, with promise for applications requiring high compliance, including certain medical procedures. This has driven demand for new control schemes designed to precisely control these highly flexible manipulators, whose kinematics may be sensitive to external loads, such as gravity. This article presents one such approach, utilizing a rapidly computed kinematic model based on Cosserat rod theory, coupled with sensor feedback to facilitate closed-loop control, for a soft continuum manipulator under tip follower actuation and external loading. This approach is suited to soft manipulators undergoing quasi-static deployment, where actuators apply a follower wrench (i.e., one that is in a constant body frame direction regardless of robot configuration) anywhere along the continuum structure, as can be done in water-jet propulsion. In this article we apply the framework specifically to a tip actuated soft continuum manipulator. The proposed control scheme employs both actuator feedback and pose feedback. The actuator feedback is utilized to both regulate the follower load and to compensate for non-linearities of the actuation system that can introduce kinematic model error. Pose feedback is required to maintain accurate path following. Experimental results demonstrate successful path following with the closed-loop control scheme, with significant performance improvements gained through the use of sensor feedback when compared with the open-loop case.