Robot performs first laparoscopic surgery without human guidance
A robot performed laparoscopic surgery on the soft tissues of a pig without a human guiding its hand, a significant step in robotics on the path to fully automated operations on people. The autonomous Smart Tissue Autonomous Robot (STAR), developed by a team of researchers at Johns Hopkins University, is described in the journal Science Robotics.
“Our results show that we can automate one of the most complex and delicate tasks in surgery: reconnecting two ends of the intestine. STAR performed the procedure on four animals and achieved significantly better results than humans performing the same procedure”
The robot excelled at intestinal anastomosis, a procedure that requires a high level of repetitive movement and precision. Joining two ends of the intestine is arguably the most challenging step in gastrointestinal surgery, requiring the surgeon to place sutures with high accuracy and consistency. Even the slightest hand tremor or a poorly placed suture can lead to a leak, with catastrophic consequences for the patient.
Working with staff at Children's National Hospital in Washington, D.C., and Jin Kang, a professor of electrical and computer engineering at Johns Hopkins University, Krieger was able to create the robot, a vision-guided system designed specifically for suturing soft tissue. Its current iteration builds on a 2016 model that accurately repaired pig intestines but required a large incision to access the intestine and more guidance from humans.
The team equipped STAR with new features to increase autonomy and surgical accuracy, including specialized suturing tools and advanced computer vision systems that provide more precise visualization of the surgical field.
According to Krieger, soft tissue surgery is especially difficult for robots because of its unpredictability, which forces them to adapt quickly to unexpected obstacles. STAR has a new control system that can adjust the surgical plan in real time, just as a human surgeon would.
“What makes STAR special is that it is the first robotic system that plans, adapts and executes a surgical plan in soft tissue with minimal human intervention”
A three-dimensional endoscope based on structured light and a machine learning-based tracking algorithm, developed by Kang and his students, guide STAR. "We believe that advanced three-dimensional machine vision is essential to make intelligent surgical robots smarter and safer," the professor said.
According to Krieger, as medicine moves toward more laparoscopic approaches to surgery, it will be important to have an automated robotic system designed for such procedures.
“Robotic anastomosis is one way to ensure that surgical tasks requiring high precision and reproducibility can be performed more accurately for every patient, regardless of the surgeon's skill. We expect this to lead to a democratized surgical approach to treating patients with more predictable and consistent results”
"Autonomous robotic surgery can deliver efficiency, safety and consistency regardless of the skill and experience of an individual surgeon. Autonomous anastomosis is a challenging task in soft tissue surgery because it requires sophisticated imaging, tissue tracking and surgical planning, as well as precise execution using easily adaptable control strategies, often in unstructured and deformable environments," the study says.
In laparoscopic settings, such operations are even more complex due to the need for high maneuverability and repeatability under constraints on movement and vision.
The researchers' advanced autonomous strategy allows the operator to choose among autonomously generated surgical plans, while the robot independently performs a wide range of tasks. An enhanced autonomous strategy was then used to carry out autonomous robotic laparoscopic surgery for intestinal anastomosis on pig models over a one-week survival period.
The scientists compared anastomosis quality criteria, including needle position correction, spacing between sutures, suture size, completion time, lumen patency and leak pressure of the developed autonomous system, manual laparoscopic surgery and robotic surgery (RAS).
Data from the phantom model showed that their system outperforms the manual technique of experienced surgeons and the RAS technique in terms of consistency and accuracy. These results demonstrate that surgical robots exhibiting a high level of autonomy can improve consistency, improve patient outcomes and expand access to standard surgical technique.
