Biotechnology

New study shows noninvasive brain imaging can differentiate between hands


LA JOLLA, CA, May 19, 2023 — Researchers from the University of California San Diego have found a way to distinguish people’s hand movements by simply examining data from non-invasive brain imaging, without information from the hand itself. The result is an early step in developing non-invasive brain-computer interfaces that may one day enable patients with paralysis, amputations of limbs, or other physical challenges to use their minds to control devices that assist with everyday tasks.

LA JOLLA, CA, May 19, 2023 — Researchers from the University of California San Diego have found a way to distinguish people’s hand movements by simply examining data from non-invasive brain imaging, without information from the hand itself. The result is an early step in developing non-invasive brain-computer interfaces that may one day enable patients with paralysis, amputations of limbs, or other physical challenges to use their minds to control devices that assist with everyday tasks.

The research was recently published online before being printed in a journal Cerebral cortexrepresents the best results so far in differentiating single-handed movements using a completely noninvasive technique, in this case, magnetoencephalography (MEG).

“Our goal was to bypass the invasive component,” said senior author of the paper Mingxiong Huang, PhD, co-director of the MEG Center at the Qualcomm Institute at UC San Diego. Huang is also affiliated with the Department of Electrical and Computer Engineering at the UC San Diego Jacobs School of Engineering and the Department of Radiology at the UC San Diego School of Medicine, as well as the San Diego Veterans Affairs (VA) Health System. “MEG provides a safe and accurate option for developing brain-computer interfaces that could ultimately help patients.”

The researchers underscored the advantages of MEG, which uses a helmet with an array of 306 embedded sensors to detect magnetic fields generated by electrical currents of nerves moving between neurons in the brain. Alternative brain-computer interface techniques include electrocorticography (ECoG), which requires implantation of electrodes on the surface of the brain, and scalp electroencephalography (EEG), which locates brain activity less precisely.

“With MEG, I can see the thinking brain without removing the skull and placing electrodes on the brain itself,” said study co-author Roland Lee, MD, director of the MEG Center at the UC San Diego Qualcomm Institute, emeritus professor of radiology at the UC San Diego School of Medicine, and doctors with the VA San Diego Healthcare System. “I just need to put MEG helmets on their heads. No electrodes to break when implanted inside the head; no complicated and expensive brain surgery; there is no possibility of brain infection.”

Lee likened the safety of MEG to taking a patient’s temperature. “MEG measures the magnetic energy your brain gives off, much like a thermometer measures the heat your body gives off. That makes it completely non-invasive and safe.”

Rock paper scissors

The current study evaluated the ability to use MEG to discriminate between hand movements made by 12 volunteer subjects. Volunteers were equipped with MEG helmets and randomly instructed to make one of the gestures used in the game Rock Paper Scissors (as in previous similar studies). MEG functional information is superimposed on MRI images, which provide structural information on the brain.

To interpret the resulting data, Yifeng (“Troy”) Bu, an electrical and computer engineering PhD student at the UC San Diego Jacobs School of Engineering and first author of the paper, wrote a high-performance deep learning model called MEG-RPSnet.

“The specialty of this network is that it combines spatial and temporal features together,” said Bu. “That’s the main reason it works better than previous models.”

When the research results came in, the researchers found that their technique could be used to differentiate hand movements with over 85% accuracy. These results are comparable to previous studies with a much smaller sample size using an invasive ECoG brain-computer interface.

The team also found that MEG measurements of only half the brain region sampled could produce results with only a slight (2 – 3%) loss in accuracy, indicating that future MEG helmets may require even fewer sensors.

Looking ahead, Bu noted, “This work establishes the foundation for the future development of MEG-based brain-computer interfaces.”

In addition to Huang, Lee and Bu, the article, “Magnetoencephalogram-based brain-computer interface for decoding hand movements using deep learning” (https://doi.org/10.1093/cercor/bhad173), authored by Deborah L Harrington, Qian Shen and Annemarie Angeles-Quinto of the VA San Diego Healthcare System and UC San Diego School of Medicine; Hayden Hansen of the VA San Diego Healthcare System; Zhengwei Ji, Jaqueline Hernandez-Lucas, Jared Baumgartner, Tao Song and Sharon Nichols of UC San Diego School of Medicine; Dewleen Baker of the VA Center of Excellence for Stress and Mental Health and UC San Diego School of Medicine; Imanuel Lerman of UC San Diego, School of Medicine and VA Center of Excellence for Stress and Mental Health; and Ramesh Rao (director of the Qualcomm Institute), Tuo Lin and Xin Ming Tu of UC San Diego.

The work was supported in part by the U.S. Department of Veterans Affairs Merit Review Grants, the Naval Medical Research Center’s Advanced Medical Development program and the Congressional Directed Medical Research/Department of Defense Program.




Source link

Related Articles

Back to top button