Cătalina Cîrnațu, XI D
What are brain decoders? A brain decoder is a fairly new emergent device, created to aid individuals who have lost their ability to speak or write. Currently, most brain decoders use recordings from implanting electrodes (a conductor that is used to make contact with a nonmetallic part of a circuit), and are primarily used for people with motor system disorders. However, implanting afore mentioned electrodes is quite an invasive and risky procedure, which is why scientists weren’t too hopeful regarding the usage of the brain decoder.
At least, not until recently, when neuroscientists at the University of Texas managed to surmount this problem. Unlike other language decoding systems in development, their system does not require subjects to have surgical implants, making the process noninvasive. The study, published in the journal Nature Neuroscience, was led by Jerry Tang, a doctoral student in computer science, and Alex Huth, an assistant professor of neuroscience and computer science at UT Austin. The study’s other co-authors are Amanda LeBel, a former research assistant in the Huth lab, and Shailee Jain, a computer science graduate student at UT Austin.
How does it work?
Following rigorous training of the decoder—during which the subject listens to hours of podcasts in the scanner—brain activity is assessed using an fMRI scanner. Later, listening to a new narrative or picturing giving a story enables the computer to create equivalent text from brain activity alone, if the subject is willing to have their thoughts processed.
Granted, the result isn’t perfect. The decoder is designed to capture the gist of what is being thought, not to transcribe it word for word.
For example, in experiments, a participant listening to a speaker say, “I don’t have my driver’s license yet” had their thoughts translated as, “She has not even started to learn to drive yet.” Listening to the words, “I didn’t know whether to scream, cry or run away. Instead, I said, ‘Leave me alone!’” was decoded as, “Started to scream and cry, and then she just said, ‘I told you to leave me alone.’” (quotation from UT News )
Starting with an earlier draft of the work that was published online as a preprint, the researchers tackled concerns about possible technological abuse. The decoder was trained solely by cooperative people who voluntarily engaged in the process, as the report explains. Findings for subjects on whom the decoder had not been trained were incomprehensible, and findings were equally useless if subjects on whom the decoder had been trained subsequently showed resistance, for as by imagining other ideas.
Because the method currently depends on the time required on an fMRI machine, it is not viable for application outside of the laboratory. However, the scientists believe that their findings may apply to other, more transportable brain-imaging devices, such as functional near-infrared spectroscopy (fNIRS).
“fNIRS measures where there’s more or less blood flow in the brain at different points in time, which, it turns out, is exactly the same kind of signal that fMRI is measuring,” Huth said. “So, our exact kind of approach should translate to fNIRS,” although, he noted, the resolution with fNIRS would be lower.
Brain decoders significantly advance neuroscience by mapping neural activity and understanding brain disorders, while also revolutionizing healthcare through applications in neurorehabilitation, prosthetics, and human–computer interaction, albeit raising ethical considerations regarding privacy and societal impact.