Learning-based catheter and guidewire-driven autonomous vascular intervention robotic system for reduced repulsive force

Abstract Manual vascular interventional radiology (VIR) procedures have been performed under radiation exposure conditions, and many commercial master–slave VIR robot systems recently developed to overcome this issue. However, still limitations. The operator must reside near the master device control slave using only device. In addition, simultaneously process recognition of surgical tool from X-ray image while operating To limitations systems, we propose an autonomous system with a deep learning algorithm that excludes proposed drives tools target blood vessel location performing recognition. detects based on supervised algorithm, controls reinforcement-learning algorithm. Experiments are conducted two types phantoms verify effectiveness system. experimental results phantom show comparison between in terms repulsive force, task completion time, success rate during operation. is shown exhibit significant reduction force 96% ratio phantom.