Gastrointestinal (GI) endoscopy is the gold standard in the detection and treatment of early and advanced GI cancers. However, conventional endoscopic techniques are technically demanding and require visual-spatial skills and significant hands-on experience. GI endoscopy simulators represent a valid solution to allow doctors to practice in a pre-clinical scenario. From the first endoscopy mannequin, developed in 1969, several simulation platforms have been developed, ranging from purely mechanical systems to more complex mechatronic devices and animal-based models. Considering the recent advancement of technologies (e.g., artificial intelligence, augmented reality, robotics), simulation platforms can now reach high levels of realism, representing a valid and smart alternative to standard trainee/mentor learning programs. This is particularly true nowadays, when the current demographic trend and the most recent pandemic demand, more than ever, the ability to cope with many patients. This review offers a broad view of the technology available for GI endoscopy training, including platforms currently in the market and the relevant advancements in this research and application field. Additionally, new training needs and new emerging technologies are discussed to understand where medical education is heading.

The Human Machine Interface (HMI) of intraluminal robots has a crucial impact on the clinician's performance. It increases or decreases the difficulty of the tasks, and is connected to the users' physical and mental stress. Objective: This article presents a framework to compare and evaluate different HMIs for robotic colonoscopy, with the objective of identifying the optimal HMI that minimises the clinician's effort and maximises the clinical outcomes. Methods: The framework comprises a 1) a virtual simulator (clinically validated), 2) wearable sensors measuring the cognitive load, 3) a data collection unit of metrics correlated to the clinical performance, and 4) questionnaires exploring the users' impressions and perceived stress. The framework was tested with 42 clinicians investigating the optimal device for tele-operated control of robotic colonoscopes. Two control devices were selected and compared: a haptic serial-kinematic device and a standard videogame joypad. Results: The haptic device was preferred by the endoscopists, but the joypad enabled better clinical performance and reduced cognitive and physical load. Conclusion: The framework can be used to evaluate different aspects of a HMI, both hardware and software, and determine the optimal HMI that can reduce the burden on clinicians while improving the clinical outcome. Significance: The findings of this study, and of future studies performed with this framework, can inform the design and development of HMIs for intraluminal robots, leading to improved clinical performance, reduced physical and mental stress for clinicians, and ultimately better patient outcomes.

Purpose: Endoscopy implies high demanding procedures, and their practice requires structured formation curricula supported by adequate training platforms. Physical platforms are the most standardised solution for surgical training, but over the last few years, virtual platforms have been progressively introduced. This research work presents a new hybrid, physic-virtual, endoscopic training platform that exploits the benefits of the two kind of platforms combining realistic tools and phantoms together with the capacity of measuring all relevant parameters along the execution of the exercises and of providing an objective assessment performance. Methods: The developed platform, EndoTrainer, has been designed to train and assess surgical skills in hysteroscopy and cystoscopy following a structured curricula. The initial development and validation is focused on hysteroscopic exercises proposed in the Gynaecological Endoscopic Surgical Education and Assessment (GESEA) Certification Programme from The Academy and European Society for Gynaecological Endoscopy (ESGE) and analyses the obtained results of an extensive study with 80 gynaecologists executing 30 trials of the standard 30 degree endoscope navigation exercise. Results: The experiments demonstrate the benefits of the presented hybrid platform. Multi-variable statistical analysis points out that all subjects have obtained statistically significant improvement in all relevant parameters: shorter and safer trajectories, improved 30-degree endoscope navigation, accurate positioning over the targets and reduction of the execution time. Conclusion: This paper presents a new hybrid approach for training, and evaluating whether it provides an objectivable improvement of camera navigation endoscopic basic skills. The obtained results demonstrate the initial hypothesis: all subjects have improved their camera handling and navigation skills.

This paper presents an accurate and robust tracking vision algorithm for Fetoscopic Laser Photo-coagulation (FLP) surgery for Twin-Twin Transfusion Syndrome (TTTS). The aim of the proposed method is to assist surgeons during anastomosis localization, coagulation and review using a tele-operated robotic system. The algorithm computes the relative position of the fetoscope tool tip with respect to the placenta, via local vascular structure registration.The algorithm uses image features (local superficial vascular structures of the placenta’s surface) to automatically match consecutive fetoscopic images. It is composed of three sequential steps: image processing (filtering, binarization and vascular structures segmentation); relevant Points Of Interest (POIs) seletion; and image registration between consecutive images.The algorithm has to deal with the low quality of fetoscopic images, the liquid and dirty environment inside the placenta jointly with the thin diameter of the fetoscope optics and low amount of environment light reduces the image quality. The obtained images are blurred, noisy and with very poor color components.The tracking system has been tested using real video sequences of FLP surgery for TTTS. The computational performance enables real time tracking, locally guiding the robot over the placenta’s surface with enough accuracy.