A Framework for Automating Interventional Surgeries (Catheter detection and Automation of a crucial step in Percutaneous Coronary Interventional surgery - PCI)

Interventional Cardiologists and Neuro-surgeons are facing a grave danger daily by being exposed to X-ray radiations while performing surgery. A few robotic systems exist in the market to aid them. This work is a first step for automating such interventional surgeries using robotic systems capable of navigating standard surgical guide wires and catheters. Reaching the Bovine Aortic Arch is the first step after selection of the required guide wire and catheter for most of the interventional procedures. In this paper guide lines are developed for the robotic system to perform the procedure of advancing a guide catheter into the aortic arch, following an optimal path automatically, using image based catheter (Simmons 22 catheter) detection in X-ray images taken from a surgery trainer (VIST simulator -- Mentice AB). The X-ray imagery is captured by a camera and the images obtained are pre-processed and the guidewire/catheter is recognized using a level by level thresholding technique. This data is fed to a Kalman filter to enhance the recognition rate. This work also shows that the surgical tasks can be learned and automated such that the use of radioactive dye inside the patient body can be reduced. Thus reducing the radiation dangers to the patient.