We need surgical robots to make it very fast, cheap, and highly reliable to replace aging organs with new organs grown in vats outside the body. Automation is key to higher quality and lower error rates. With that thought in mind, some Duke researchers are developing autonomous surgical robots.
DURHAM, N.C. -- As physician-guided robots routinely operate on patients at most major hospitals, the next generation robot could eliminate a surprising element from that scenario -- the doctor.
Feasibility studies conducted by Duke University bioengineers have demonstrated that a robot -- without any human assistance -- can locate a man-made, or phantom, lesion in simulated human organs, guide a device to the lesion and take multiple samples during a single session. The researchers believe that as the technology is further developed, autonomous robots could some day perform many more simple surgical tasks.
"Earlier this year we demonstrated that a robot directed by artificial intelligence can on its own locate simulated calcifications and cysts in simulated breast tissue with high repeatability and accuracy," said Kaicheng Liang, a former student in the laboratory of Stephen Smith, director of the Duke University Ultrasound Transducer Group at the Pratt School of Engineering and senior member of the research team. "Now we have shown that the robot can sample up to eight different spots in simulated human prostate tissue."
Automation is needed in order to achieve the highest quality. So robotic surgeons don't just hold out the hope of lower costs. They'll also make fewer errors. The best human hand skilled at guiding a blade will inevitably be surpassed by a computer-controlled high precision device.
By Randall Parker at 2010 July 21 10:38 PM Robots MedicineI wonder what the robot does if it gets into a little bleeding problem? Call a vascular surgical robot?
Color me skeptical. I'm a high tech guy, not a Luddite, but we're FAR from allowing autonomy in these complex situations. I just had robotic surgery but with the sturgeon (sic) in the loop.
"Forget the cods, Gill; he's gonna need a sturgeon."
I'm not so sanguine about the dexterity of surgical robots. Precision is no good if they can't tell what they're looking at and can't judge what needs to be done.
We still have airline pilots watching, even though the auto-pilot does the flying.
I assume that we will still have surgeons supervising, even if a robot does the cutting.
There is also the question of legal liability.
This will probably be a huge impediment to mass adoption of robo-surgery, self-driving cars, and other such automations.
Computers need to start succeeding at fuzzier applications such as speech recognition before I will trust them with something like surgery. There is too much randomness in human biology for computers to handle accurately with in a reasonable margin of error.