Autonomous Robot Improves Surgical Precision Using AI

Performing laparoscopic operations without the guidance of a surgeon’s hand.

Anastomosis—which involves connecting two tubular structures such as blood vessels or intestines—is often performed laparoscopically and is one of the most intricate and delicate tasks in surgery to automate: the reconnection of two ends of an intestine.

Despite being minimally invasive, the surgery has the potential for serious complications to the patient if any leakage occurs due to flawed suturing.

Because the patient is breathing, the two ends of the intestine tend to move. When this movement is larger than 3mm, and the autonomous robot can not adjust the suturing plan, leakage and imperfect suturing can occur.

Researchers developed machine learning, computer vision, and advanced control techniques to track the target tissue movement in response to patient breathing, detect the tissue deformations between different suturing steps, and operate the robot under motion constraints.

They trained CNNs using 9,294 examples of motion profiles from anastomosis procedures, to learn tissue motion based on breathing patterns and other tissue motion during surgery.