AI-based Agents for Automated Robotic Endovascular Guidewire Manipulation

Abstract

An endovascular guidewire manipulation is essential for minimally-invasive clinical applications; Percutaneous Coronary Intervention (PCI) is used to open narrowed coronary arteries and restore arterial blood flow to heart tissue, Mechanical thrombectomy techniques for acute ischemic stroke (AIS) to remove blood clots from the brain veins, and Transjugular intrahepatic portosystemic shunt (TIPS) for liver portal hypertension use a special needle and position a wire between the portal vein through the liver. All procedures commonly require 3D vessel geometries from 3D CTA (Computed Tomography Angiography) images (Fig. 1). During these procedures, the clinician generally places a guiding catheter in the ostium of the relevant vessel and then manipulates a wire through the catheter and across the blockage. The clinician only uses X-ray fluoroscopy intermittently to visualize and guide the catheter, guidewire, and other devices (e.g., angioplasty balloons and stents). Various types of endovascular robot-assisted systems [1, 2] are being developed to provide efficient positional control of devices, helping clinicians to mitigate therapeutical risks. The primary motions that a clinician can use to control the movement and direction of the wire are rotation and pushing/retracting from the proximal end of the wire outside the insertion point on the patient’s body. Even with these robotic devices, clinicians passively control guidewires/catheters by relying on limited indirect obser- vation (i.e., 2D partial view of devices, and intermittent updates due to radiation limit) from X-ray fluoroscopy. Modeling and controlling the guidewire manipulation in coronary vessels remains challenging because of the complicated interaction between guidewire motions with different physical properties (i.e., loads, coating) and vessel geometries with lumen conditions resulting in a highly non- linear system.