First robot ‘surgeon’ performs operation without human help

By Stephen Beech

A robot "surgeon" trained on videos has performed the first realistic operation without human help.

The automaton conducted a lengthy phase of a gallbladder removal without the aid of humans in what scientists say is a "major leap" forward in robotics.

The robot operated for the first time on a "lifelike" patient, and during the procedure, responded to and learned from voice commands from the human team, like a novice surgeon working with a mentor.

Researchers say the robot surgeon performed "unflappably" across trials and with the expertise of a skilled human surgeon, even during unexpected scenarios typical in real-life medical emergencies.

The American team - led by scientists at Johns Hopkins University in Baltimore, Maryland - described the work as a "transformative advancement" in surgical robotics, where robots can perform with both mechanical precision and "human-like" adaptability and understanding.

Medical roboticist Dr. Axel Krieger, of Johns Hopkins University, said: “This advancement moves us from robots that can execute specific surgical tasks to robots that truly understand surgical procedures,

“This is a critical distinction that brings us significantly closer to clinically viable autonomous surgical systems that can work in the messy, unpredictable reality of actual patient care.”

In 2022, Dr. Krieger’s Smart Tissue Autonomous Robot, or STAR, performed the first autonomous robotic surgery on a live animal – a laparoscopic surgery on a pig.

But he said that robot required specially marked tissue, operated in a highly controlled environment, and followed a rigid, predetermined surgical plan.

Dr. Krieger described it as like teaching a robot to drive along a carefully mapped route.

But he says his new system “is like teaching a robot to navigate any road, in any condition, responding intelligently to whatever it encounters.”

Dr. Krieger said Surgical Robot Transformer-Hierarchy, or SRT-H, truly performs surgery, adapting to individual anatomical features in real-time, making decisions on the fly, and self-correcting when things don't go as expected.

Built with the same machine learning architecture that powers ChatGPT, SRT-H is also interactive, able to respond to spoken commands - such as “grab the gallbladder head” - and corrections, like “move the left arm a bit to the left”.

The robot learns from the feedback, according to the study published in the journal Science Robotics.

Lead author Dr .Ji Woong "Brian" Kim, who’s now with Stanford University, said: “This work represents a major leap from prior efforts because it tackles some of the fundamental barriers to deploying autonomous surgical robots in the real world.

“Our work shows that AI models can be made reliable enough for surgical autonomy—something that once felt far-off but is now demonstrably viable.”

Dr. Krieger’s team used the system last year to train a robot to perform three foundational surgical tasks: manipulating a needle, lifting body tissue, and stitching.

Those tasks took just a few seconds each.

But the team said the gallbladder removal procedure is much more complex, a string of 17 tasks across several minutes.

The robot had to identify certain ducts and arteries and grab them precisely, strategically place clips, and sever parts with scissors.

SRT-H learned how to do the gall bladder work by watching videos of Johns Hopkins surgeons doing it on dead pigs.

The team reinforced the visual training with captions describing the tasks.

After watching the videos, the robot performed the surgery with 100% accuracy.

Although the robot took longer to perform the work than a human surgeon, the results were comparable to an expert surgeon.

Study co-author Dr. Jeff Jopling, a Johns Hopkins surgeon, said: “Just as surgical residents often master different parts of an operation at different rates, this work illustrates the promise of developing autonomous robotic systems in a similarly modular and progressive manner.”

The robot performed "flawlessly" across anatomical conditions that weren’t uniform, and during unexpected detours, including when the researchers changed the robot’s starting position and when they added blood-like dyes that changed the appearance of the gallbladder and surrounding tissues.

Dr. Krieger added: “To me it really shows that it’s possible to perform complex surgical procedures autonomously.

“This is a proof of concept that it’s possible and this imitation learning framework can automate such complex procedure with such a high degree of robustness.”

His team now want to train and test the system on different types of operations and expand its capabilities to perform a complete autonomous surgery.