Toward Autonomous Cannulation in Endovascular Intervention

点击翻译按钮获取中文摘要

Recently, many robotic systems for endovascular intervention have been proposedin academia or industry. These teleoperation platforms commonlyconsist of master and slave robots. Hence, the device architectures addresslow levels of robotic autonomy. Examples of novel robotic platforms areMagellan and Sensei X2 (AurisHealth, USA), R-one (Robocath, France),CorPath GRX (Corindus, USA), CathBot (Imperial College London, UK).Clinical trials demonstrated the applicability of different platforms. Beyondthat, novel master interfaces were described for optimised teleoperation feedback,transparency, and usability. Alternatively, manual manipulation ofstandard catheters was sensed without feedback and was replicated to aremote slave platform. Furthermore, designs of slave kinematics addresseddifferent electromechanical configurations for instrument manipulation, i.e.,translation/rotation, and coupling interfaces. Within all those aspects, machinelearning has been used to improve the assistive features which includedeep learning applications to handle the tracking challenges implied by thesystem. Those features allow the development of higher levels of autonomy.This PhD project aims to develop autonomous cannulation and tracking solutionsbased on machine learning, bioelectrical localization, and robotics.The novel autonomous cannulation and tracking technology will be incorporatedwithin a state-of-the-art robotic steering system for cooperativecatheter insertion. The system will feature multiple degrees of freedom toaccurately control the insertion process, haptic feedback for an improveduser experience, and the option for manual or autonomous robotic insertion.The result will be a novel, autonomous, and radiation-free system forendovascular surgery.