The use of robots in the autonomous treatment of stroke patients could widen access to time-sensitive emergency mechanical thrombectomy procedures, as evidenced by a recent paper from researchers at King’s College London (London, UK).
In the paper—now published online in the International Journal of Computer Assisted Radiology and Surgery—researchers sought to evaluate whether surgical robots guided autonomously by artificial intelligence (AI) could be used to enhance safety and reduce procedure times.
The initial stage of a mechanical thrombectomy procedure involves navigating catheters and wires from the groin into the neck vessels—and, in their analysis, the team of King’s researchers deployed computer modelling to show that this step has the potential to be undertaken autonomously using AI navigation.
The researchers also believe that another possible implication of their work is the potential for inverse reinforcement learning (IRL) to train new AI models.
“Our research uses AI to show, for the first time, how to autonomously navigate medical instruments from the groin to the neck in blood vessels,” said King’s PhD student Harry Robertshaw. “This is an important part of mechanical thrombectomy, which removes clots from blood vessels. We also explored various methods to teach the AI.
“We found that using real-life examples to guide the AI—a technique known as ‘inverse reinforcement learning’—improves its performance compared to the best current methods.
“Moving forward, we can use these new techniques to create models which may be able to navigate unseen patient blood vessels, moving us closer to realising the full benefits of robotic mechanical thrombectomy with autonomous assistance.”
“Our work is another step forwards towards improved procedural accessibility and precision of autonomous endovascular navigation tasks,” added Thomas Booth, a neuroimaging reader in the School of Biomedical Engineering and Imaging Sciences at King’s. “For mechanical thrombectomy, the work plausibly lays the foundation for potentially transformative patient care—for example, by treating patients more safely by using AI assistive navigation technologies.”
