analiza aiqbench
This in-vitro study tests how clinicians work with robotic navigation systems at different levels of AI autonomy during mechanical thrombectomy. The main finding is that fully autonomous navigation dropped from 81% success in simulation to 23% in a physical phantom, while clinician-AI shared-autonomy modes reached 92-97%. For AI readers, the result is a concrete case of sim-to-real domain shift and of human-in-the-loop designs partly mitigating it, though the evidence comes from a phantom with 13 participants and is not clinical validation.
Clinician-AI Collaboration in Endovascular Neurointerventions: In-Vitro User Study of Copilot Assistance Modes for Robotic Navigation Across the Autonomy Spectrum
arXiv:2611.03446v1 Announce Type: new Abstract: Mechanical thrombectomy (MT) is an effective treatment for acute ischemic stroke, yet access remains limited by the availability of neurointerventional expertise. Telerobotic and AI-assisted systems may help address this challenge, but it remains unclear how clinicians interact with different levels of autonomy and how autonomous navigation systems perform in realistic environments. This work introduces Copilot Assistance Modes (CAMs), a framework for clinician-AI collaboration in robotic endovascular navigation spanning the autonomy spectrum from manual operation to full autonomy. In the first in-vitro user study comparing clinician-AI collaboration strategies, 11 experts and two students evaluated six navigation modes in a patient-specific vascular phantom. Objective performance metrics were combined with subjective assessments, including workload and usability. Autonomous performance was additionally evaluated both in silico and in vitro to investigate sim-to-real transfer. Hands-on manual navigation achieved the strongest overall performance (100% success). While fully autonomous navigation achieved 81% success in simulation, performance dropped to 23% in vitro. In contrast, several clinician-AI shared-autonomy modes achieved success rates of 92-97%, approximately four times higher than full autonomy and comparable to direct robotic control (95%), demonstrating mitigation of sim-to-real domain shift through clinician-AI collaboration. Among the evaluated AI-driven approaches, user-directed task delegation and rotational shared control demonstrated the most favorable balance between performance and clinician acceptance. These findings suggest that effective clinician-AI collaboration and allocation of control authority may currently be more important for reliable robotic neurointerventional navigation than increasing autonomy alone.
Authors:Nikola Fischer, Harry Robertshaw, S.M.Hadi Sadati, Xingyu Chen, Weiyuan Deng, Benjamin Jackson, Michael Adofo Kwakye, Sara Sciacca, Naga Kandasamy, Parthiban Balasundaram, Sahan Guruge, Charles Cummins, Joe Leyon, Nasr Abdelsalam, Matthew Benger, Andrew Falzon, Alejandro Granados, Christos Bergeles, Thomas Booth
Abstract:Mechanical thrombectomy (MT) is an effective treatment for acute ischemic stroke, yet access remains limited by the availability of neurointerventional expertise. Telerobotic and AI-assisted systems may help address this challenge, but it remains unclear how clinicians interact with different levels of autonomy and how autonomous navigation systems perform in realistic environments. This work introduces Copilot Assistance Modes (CAMs), a framework for clinician-AI collaboration in robotic endovascular navigation spanning the autonomy spectrum from manual operation to full autonomy. In the first in-vitro user study comparing clinician-AI collaboration strategies, 11 experts and two students evaluated six navigation modes in a patient-specific vascular phantom. Objective performance metrics were combined with subjective assessments, including workload and usability. Autonomous performance was additionally evaluated both in silico and in vitro to investigate sim-to-real transfer. Hands-on manual navigation achieved the strongest overall performance (100% success). While fully autonomous navigation achieved 81% success in simulation, performance dropped to 23% in vitro. In contrast, several clinician-AI shared-autonomy modes achieved success rates of 92-97%, approximately four times higher than full autonomy and comparable to direct robotic control (95%), demonstrating mitigation of sim-to-real domain shift through clinician-AI collaboration. Among the evaluated AI-driven approaches, user-directed task delegation and rotational shared control demonstrated the most favorable balance between performance and clinician acceptance. These findings suggest that effective clinician-AI collaboration and allocation of control authority may currently be more important for reliable robotic neurointerventional navigation than increasing autonomy alone.
Robotics (cs.RO)
arXiv:2611.03446 [cs.RO]
(or arXiv:2611.03446v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2611.03446 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 291 cuvinte