Who is better at performing surgery: experienced surgeons or robots?

Typically, surgeons have to make relatively large incisions during surgery, while the robot’s small instruments can fit into smaller incisions. Given this advantage of robotic systems, it is now common for surgeons to use remotely-controlled robotic arms to perform procedures—combining the precision of experienced humans with the minimal invasiveness of small robotic arms. In these cases, however, the surgeon still needs to control the robot, and fully automated robotic systems that outperform the surgeon in terms of precision have not yet been realized.

However, a recent development suggests that robots may demonstrate superhuman performance in the near future. In a paper published May 10 in IEEE Transactions on Automation Science and Engineering, a multinational research team reports the results of a study in which robots were able to perform common procedures with the same precision as experienced surgeons Training tasks while completing them faster and more consistently.

Minho Hwang, an assistant professor at the Gyeongbuk Institute of Science and Technology in Daegu, South Korea, participated in the study. He noted that many robotic systems currently rely on automated control of cables, which are subject to friction, cable coupling and stretching, all of which can make precise positioning difficult.

“When a human controls the robot, they can compensate with the human’s visual feedback. But automation of robot-assisted surgery is very difficult because of [these] positional errors,” Hwang explained.

For their study, Hwang and colleagues took a standard da Vinci robotic system, a common phantom used in robot-assisted surgery, and strategically placed 3D-printed markers on its robotic arm. This enabled the team to track its movement using color and depth sensors. They then analyzed the arm’s movements using a machine learning algorithm. The results showed that the trained model could reduce the average tracking error by 78%, from 2.96 mm to 0.65 mm.

Next, the researchers tested their system against an experienced surgeon who had performed more than 900 surgeries, and nine volunteers with no surgical experience. Study participants were asked to complete the peg transfer task, a standardized test for surgeons in training that involves transferring six triangular blocks from one side of a pegboard to the other and back again. While the task sounds simple, it requires millimeter precision.

Study participants performed three different peg tasks using the da Vinci robotic system: unilateral (using one arm to move one peg), bilateral (using both arms to move two pegs at the same time), and bilateral crossover (using a single arm). arm picks up the peg, transfers to the other arm, and places the peg on the board). Their robot-assisted performance was compared with a fully automated robotic system designed by Hwang’s group.

Using one arm, surgeons outperform autonomous robots in terms of speed. But in more complex tasks involving both arms, the robot outperformed the surgeon.

For example, for the most difficult task (bilateral switching), the surgeons had a 100% success rate with an average transfer time of 7.9 seconds. The bots had the same success rate, but only had an average transfer time of 6.0 seconds.

Ken Goldberg, a professor in UC Berkeley’s Department of Electrical Engineering and Computer Science, also contributed to the research. He said: “We were very surprised by the speed and accuracy of the robot, because it was very difficult for it to surpass the skill of a trained human surgeon. We were also surprised by the consistency of the robot; it transferred 120 times perfectly, without A glitch.”

Goldberg and Hwang note that this is preliminary research in a controlled environment, and that more research is needed to realize fully automated robotic surgery. But to their knowledge, this is the first instance of a robot outperforming humans in a surgery-related training task.

“We have shown that fast and accurate automation is feasible for a surgical task involving rigid objects of known shape. The next step is to demonstrate this in other tasks and in more complex human settings,” Hwang said.

In future work, the team plans to extend its approach to automating surgical subtasks, such as tissue stapling, and hopes to build on its calibration, motion planning, visual servoing, and error recovery methods, he said.

Reviewing editor: Peng Jing

Leave a Reply

Your email address will not be published.