Key result
Autonomous 2D image-guided endovascular navigation achieves high success with only a ~3% failure rate.
Why the study?
Physicians rely on planar DSA and X-ray fluoroscopy to interpret vessel anatomy and device motion during endovascular interventions, but converting these two-dimensional images into feedback for autonomous navigation remains difficult.
Does a 2D image feedback-based perception and rule-based control framework enable reliable autonomous endovascular navigation on a physical dual-device robotic platform using simulator-rendered planar projections?
Does a 2D image feedback-based perception and rule-based control framework enable reliable autonomous endovascular navigation on a physical dual-device robotic platform using simulator-rendered planar projections?
This engineering validation study demonstrates that a topology-constrained, path-relative state abstraction and deterministic rule-based controller can achieve high route-level guidewire navigation progress (≥0.95 in 100% of runs, with 3.1% failure rate) on a physical robotic platform using 2D simulator projections.
Answers are grounded in this paper and cite their sources.
Simulator success in 65 runs supports preclinical refinement; leaves open clinical translation of autonomous endovascular navigation.
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.
No takes yet. Share an insight, caveat, or question.
Cao et al. (2026) studied Simulated endovascular intervention (n=65). 2D image feedback-based autonomous endovascular navigation method was evaluated on Stop-based run failure (three or more autonomous stop events in one run). The 2D image-guided autonomous endovascular navigation method achieved ≥0.95 guidewire progress in 100% of 65 physical-robot simulator runs, with only 2 runs meeting the stop-based failure threshold.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: