Skip to Content

Nimble-Fingered Robot Outperforms the Best Human Surgeons

A surgical robot was able to repair pigs’ bowels more accurately than human doctors.

A robot surgeon has been taught to perform a delicate procedure—stitching soft tissue together with a needle and thread—more precisely and reliably than even the best human doctor.

The Smart Tissue Autonomous Robot (STAR), developed by researchers at Children’s National Health System in Washington, D.C., uses an advanced 3-D imaging system and very precise force sensing to apply stitches with submillimeter precision. The system was designed to copy state-of-the art surgical practice, but in tests involving living pigs, it proved capable of outperforming its teachers.

Currently, most surgical robots are controlled remotely, and no automated surgical system has been used to manipulate soft tissue. So the work, described today in the journal Science Translational Medicine, shows the potential for automated surgical tools to improve patient outcomes. More than 45 million soft-tissue surgeries are performed in the U.S. each year. Examples include hernia operations and repairs of torn muscles.

“Imagine that you need a surgery, or your loved one needs a surgery,” says Peter Kim, a pediatric surgeon at Children’s National, who led the work. “Wouldn’t it be critical to have the best surgeon and the best surgical techniques available?”

An autonomous robot that can perform surgery, shown here sewing pig intestinal tissue.

Kim does not see the technology replacing human surgeons. He explains that a surgeon still oversees the robot’s work and will take over in an emergency, such as unexpected bleeding.

“Even though we take pride in our craft of doing surgical procedures, to have a machine or tool that works with us in ensuring better outcome safety and reducing complications—[there] would be a tremendous benefit,” Kim says. The new system is an impressive example of a robot performing delicate manipulation. If robots can master human-level dexterity, they could conceivably take on many more tasks and jobs.

STAR consists of an industrial robot equipped with several custom-made components. The researchers developed a force-sensitive device for suturing and, most important, a near-infrared camera capable of imaging soft tissue in detail when fluorescent markers are injected.

“It’s an important result,” says Ken Goldberg, a professor at UC Berkeley who is also developing robotic surgical systems. “The innovation in 3-D sensing is particularly interesting.”

Goldberg’s team is developed surgical robots that could be more flexible than STAR because instead of being manually programmed, they can learn automatically by observing expert surgeons. “Copying the skill of experts is really the next step here,” he says.

 

 

Keep Reading

Most Popular

Scientists are finding signals of long covid in blood. They could lead to new treatments.

Faults in a certain part of the immune system might be at the root of some long covid cases, new research suggests.

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.