In an important advance, the UC San Francisco Weil Institute for Neurosciences researchers working towards a brain-controlled prosthesis has shown that machine learning technology allows a person to use their brain activity without the need for extensive daily retention. All previous brain-computer interface (BCI) efforts have been required to help control the computer cursor while doing so.
“The BCI field has made a lot of progress in recent years, but because existing systems have to reset and recalculate each day, they are not able to tap into the brain’s natural learning processes. It tells someone to learn to ride Is similar to. Bike from scratch repeatedly, “senior author Karunesh Ganguly, MD, PhD, study an associate professor in the UCSF Department of Neurology. “Adopting an artificial learning system to work smoothly with the brain’s sophisticated long-term learning schema is something that has never been shown before in a paralyzed person.”
The achievement of the “plug and play” display demonstrates the value of so-called ECOG electrode arrays for BCI applications. An ECOG array consists of electrodes about the size of a Post-It note placed surgically on the surface of the brain. They allow long-term, stable recordings of neural activity and have been approved for seizure monitoring in patients with epilepsy. In contrast, previous BCI efforts have used “pin-cushion” style arrays of sharp electrodes that penetrate the brain tissue for more sensitive recording but shift or lose signal over time. In this case, the authors obtained investigational device approval for long-term chronic implantation of ECOG arrays in paralyzed subjects to test their safety and efficacy as long-term, stable BCI implants.
His new paper, published on September 7, 2020 Nature Biotechnology , Ganguly’s team documented the use of an ECOG electrode array in an individual with paralysis of all four organs (tetraplegia). The participant is also enrolled in a clinical trial designed to test the use of ECoG arrays to allow paralyzed patients to control the prosthetic arm and arm, but in the new paper, the participant Used implants to control a computer cursor on a screen.
The researchers developed a BCI algorithm that uses machine learning to match the brain activity recorded by the ECOG electrode to the user’s desired cursor movements. Initially, the researchers followed the standard practice of resetting the algorithm each day. The participant will begin by imagining specific neck and wrist movements while watching the cursor move across the screen. Gradually the computer algorithm will update itself to match the movements of the cursor. This arises from the effective control of the cursor for the user. However, starting this process every day can lead to a serious limitation on the level of control that can be achieved. The device can take hours to control, and in a few days the participant had to give up completely.
The researchers then allowed the algorithm to switch so that it would continue to match the participant’s brain activity without resetting it each day. They found that continuous gaps between brain signals and machine learning-integrated algorithms resulted in continuous improvement in performance for several days. Initially there was little lost ground to make each day, but soon the participant was able to quickly achieve top level performance.
Ganguly, a neurologist who practices with UCSF Health and San Francisco veterans, said, “We found that we could improve learning by ensuring that the algorithm is not being rapidly updated by the brain – once every 10 seconds At the rate. ” Administration Medical Center’s Neurology and Rehabilitation Service. “We see this as an attempt to create a partnership between two learning systems — the brain and the computer — that ultimately lets the artificial interface become an extension of the user, such as their own hands or hands.”
Over time, the participant’s brain was able to increase the pattern of neural activity it could use to most effectively run the artificial interface through the ECOG array, while eliminating less effective signals – a complex process. Much like how the brain considers its complex function. Researchers say. They observed that the activity of the participant’s brain appears to develop an efficient and consistent mental “model” for controlling the BCI interface, something that had never happened with daily resetting and recalculation. When the interface was reset after continuous learning for several weeks, the participant reestablished a similar pattern of neural activity to control the device – effectively retracting the algorithm to its former position.
“Once the user has established permanent memory of the solution to control the interface, there is no need to reset,” Ganguly said. “The brain simply converts rapidly to a single solution.”
Finally, once expertise is established, researchers show that they can close the need to completely update the algorithm, and the participant can start using the interface every day, with no need or iteration. . The performance did not drop for more than 44 days due to lack of retraction, and the participant could spend the day even without practice and a slight drop in performance. Establishing static expertise in a form of BCI control (moving the cursor) allowed researchers to introduce additional learned skills such as “stacking” – such as “clicking” virtual buttons – without loss of performance.
Such instant “plug and play” BCI performance has long been a target in the field, but has become inaccessible as the “pincushion-style” electrodes used by most researchers move over time, each electrode. Change the signals seen by. Furthermore, as these electrodes enter the brain tissue, the immune system rejects them, gradually impairing their signal. ECoG arrays are less sensitive than these conventional implants, but their long-term stability appears to compensate for this deficiency. The stability of ECOG recordings may be even more important for the long-term control of more complex robotic systems such as prostheses, a major goal of Ganguly’s next phase of research.
“We always think of the need to design technology that doesn’t end in a drawer, so to speak, but will actually improve the lives of paralyzed patients,” Ganguly said. “These data suggest that ECOG-based BCI may be the foundation of such technology.”
Mind on the Body: Improving the Brain-Computer Interface
Plug-and-play control of the brain-computer interface via neural map stabilization, Nature Biotechnology (2020). DOI: 10.1038 / s41587-020-0662-5, www.nature.com/articles/s41587-020-0662-5
Provided by University of California, San Francisco
Quotes: First ‘plug and play’ brain prosthesis displayed in paralyzed person (2020, 7 September) from https://medicalxpress.com/news/2020-09-brain-prosthesis-demoed.paralyzed-person.html, 7 September 2020 get
This document is subject to copyright. No part may be reproduced without written permission, except for any impartial behavior intended for personal study or research. The content is provided for information purposes only.