Autonomous guidewire navigation using 2D image feedback for endovascular surgery
A 2D Image Feedback-Based Autonomous Endovascular Navigation Method: A Perception and Control Framework
Robotics
Summary
Doctors use two-dimensional X-ray images to guide thin tools through blood vessels during surgery, but it is hard to automate this process. The authors created a method that turns these images into a map and tracks the tool’s tip to understand how far and where it has moved. A rule-based system then controls the tool’s motion to follow planned paths and handle branches or obstacles. They tested this on a robotic setup using simulated images and showed reliable navigation along different vessel routes. Further testing on real clinical images and diverse anatomy is still needed.
What this means in practice
- •For medical device engineers: Develop robotic systems that use 2D X-ray images for autonomous navigation of guidewires during minimally invasive surgeries.$Commercial implications: This method supports autonomous robotic catheter guidance products for hospitals by interpreting standard 2D imaging in real time.
- •For robotic surgery teams: Use image feedback from fluoroscopy to improve control strategies for navigating devices within patient blood vessels.
Authors
Sheng Cao, Shuxiang Guo, Yonggan Yan, Jian Guo, Chunying Li, Bin Wang, Mingchao Ding, Yongxin Zhang, Yongwei Zhang, Pengfei Yang, Jianmin Liu
Abstract
In endovascular interventions, physicians rely on planar DSA and X-ray fluoroscopy to interpret vessel anatomy and device motion, yet converting these images into feedback for autonomous navigation remains difficult. A perception and control method is formulated for two-dimensional image feedback. Vessel masks are converted into a labeled centerline graph, and device-tip estimates are projected onto a planned path to obtain progress, deviation, and direction. A rule-based controller uses these quantities for delivery, branch selection, probing, rollback, and recovery. The method was evaluated on a physical dual-device robotic platform in 65 closed-loop runs using simulator-rendered planar images across three paths. All runs reached at least 0.95 maximum observed guidewire progress; two runs (3.1%) met the prespecified failure rule of three or more autonomous stop events. The results establish route-level performance on the tested platform; clinical image sequences and broader anatomy remain to be evaluated.