New bionic eye technology could help restore sight to more people living with blindness.
US researchers have demonstrated that artificial intelligence has the potential to make bionic eyes more precise, predictable and responsive.
University of California – Santa Barbara computer science associate Michael Beyeler said the new research used a deep-learning model to design patterns of electrical stimulation for electrodes temporarily implanted in the visual cortex.
He said this work showed the potential of devices implanted in this cortex to better communicate with the brain.
“A useful visual prosthesis cannot rely on a fixed recipe,” Dr Beyeler said.
“It has to learn how an individual brain responds and adapt the stimulation accordingly. Ultimately, the device should adapt to the person, not the other way around.”
The UCSB study report said researchers had attempted to develop visual prostheses for decades, but with limited success.
Some devices targeted the retina, the light-sensitive layer at the back of the eye, while others stimulated later stages of the visual system.
“Cortical prostheses take a different approach by bypassing the eyes and optic nerves and delivering electrical stimulation directly to the visual cortex,” the report said.
“The approach could eventually benefit some people whose visual pathways have been damaged but whose visual cortex remains capable of responding to stimulation, such as people whose blindness resulted from strokes, neurodegenerative diseases, and brain injuries.”
Dr Beyeler said the potential benefit may be particularly meaningful for those “who have been able to see for part of their life, but then, because of an inherited eye disease or an accident, have lost their vision”.
“For those people, the desire may be very strong to get some vision back,” he said.
The researchers said producing a desired pattern of brain activity was only one part of the equation.
The also had to determine how that activity became a visual experience for the person using the prosthesis.
“Engineers naturally want to treat phosphenes like pixels: stimulate more electrodes, and you should get a more complete image,” Dr Beyeler said.
“But the brain does not work that way. Electrodes interact, neural responses fluctuate, and what we put into the brain is not necessarily what the person perceives. The challenge is to learn more about that transformation.”
More details are available here
Newsreel
