The brain-computer interface translates imagined writing into typed text


Researchers at the BrainGate Collaboration (which includes researchers from Brown University, Massachusetts General Hospital, Harvard Medical School, Providence VA Medical Center, Stanford University, and Case Western Reserve University) have developed a new iteration of its brain-computer-enabled patient interface. with spinal cord injuries to write text on the computer screen. The patient imagines writing each letter by hand, and sensors implanted in the brain recognize the unique neural signature of each letter, allowing for a relatively fast writing speed of 90 characters per minute. The system can allow seriously injured patients to communicate with others and use the Internet more easily.

Brain-computer interface technology is developing at a rapid pace. The possibilities for paralyzed patients are immense, with the potential to improve communication, movement, and control of external devices. Many systems have focused on allowing patients to control robotic prostheses and wheelchairs. However, the written word is very important, especially in our increasingly digital society, and technologies that make it more accessible to these patients would be very welcome.

The latter system is a brain-computer interface that allows someone to “write” by simply imagining themselves by making the hand movements involved in writing each letter on a page. So far, it has been very successful, allowing a paralyzed patient more than double the previous record, 40 characters per minute, set up with a brain-computer interface.

“An important research mission of our BrainGate consortium is to restore intuitive and fast communication for people with severe motor or speech impairments,” said Leigh Hochberg, a researcher involved in the study, through an announcement from Brown University . “[This] the demonstration of a fast and precise neuronal decoding of handwriting marks an exciting new chapter in the development of clinically useful neurotechnologies ”.

Earlier versions of the system made participants think of moving a cursor over a screen containing a virtual keyboard and then selecting the desired letter. This system produced the previous record of 40 characters per minute, but for this new system the researchers resorted to handwriting and the thinking behind it.

The team implanted two electrodes in the brain region associated with the movement of the right hand and arm. When the participant imagined writing a specific letter by hand, this produced a unique neural signature that the system learned using a machine learning algorithm. Repeating similar movements allows the system to quickly detect which letter is intended, displaying it on the screen.

“We want to find new ways to allow people to communicate faster,” said Frank Willett, another researcher involved in the study. “This new system uses both the rich neuronal activity recorded by intracortical electrodes and the power of language models that, when applied to neuronally decoded letters, can create fast, accurate text.”

Watch a video on the technology below.

Study a Nature: High-performance brain-text communication through handwriting

Via: Brown University

Source link