In an article published by Science Robotics, a team of researchers from Boston Children's Hospital in USA, Université de Strasbourg in France, and Taipei Veterans General Hospital in Taiwan, built an autonomous robotic catheter equipped with an optical sensor to fix, blood-filled heart to a leaky valve.

The researchers used a map of cardiac anatomy and preoperative scans, for the robotic catheter to navigate using an optical touch sensor that was developed in the lab of senior investigator Pierre Dupont, PhD, chief of Paediatric Cardiac Bioengineering at Boston Children's Hospital. Using AI and image processing algorithms, the touch sensor enabled the catheter to ascertain its location in the heart and where it needed to go.

The team demonstrated a procedure called a paravalvular aortic leak closure, which involves repairing replacement heart valves that have begun leaking around the edges.  The robotic catheter performed a navigational technique called "wall following," wherein it's optical touch sensor sampled its environment at regular intervals. The sensor told the catheter whether it was touching blood, the heart wall or a valve - through images from a tip-mounted camera - and how hard it was pressing.  It traced the base of the heart, along the wall of the left ventricle and around the leaky valve until it reached the location of the leak.  

"The algorithms help the catheter figure out what type of tissue it's touching, where it is in the heart, and how it should choose its next motion to get where we want it to go and though the navigation time was statistically equivalent for all, which we think is pretty impressive given that you're inside the blood-filled beating heart and trying to reach a millimetre-scale target on a specific valve," Dupont said. 

The robot's ability to visualise and sense its environment could eliminate the need for fluoroscopic imaging, which is typically used during the operation and exposes patients to ionising radiation.Dupont states there is global potential of autonomous surgical robots pooling their data to continuously improve performance, especially now that the US Food and Drug Administration is trying to develop regulations for AI-enabled devices.

"This would not only level the playing field, but it would also raise it," said Dupont. "Every clinician in the world would be operating at a level of skill and experience equivalent to the best in their field. This has always been the promise of medical robots. Autonomy may be what gets us there."