WashU Researchers Build Brain ‘Decoder’ to Control Spinal Cord Stimulation

Ismael Seáñez, assistant professor of biomedical engineering in the McKelvey School of Engineering at Washington University in St. Louis and of neurosurgery at WashU Medicine, and members of his lab, including Carolyn Atkinson, a doctoral student, developed a “decoder” to restore communication between the brain and spinal cord following a spinal cord injury.

When a spinal cord injury is sustained, normal communication between the brain and spinal circuits is interrupting, causing paralysis. Since the brain and spinal cord below the injury are functioning normally, the researchers are working to re-establish the communication to allow rehabilitation and possibly restore movement.

The researchers experimented on 17 human subjects in their lab without a spinal cord injury. They could cue lower leg movement with transcutaneous spinal cord stimulation (SCS). Results were published last week in the Journal of NeuroEngineering and Rehabilitation.

The team used a cap fitted with noninvasive electrodes that measure brain activity through electroencephalography (EEG). While wearing the cap, seated subjects were asked to extend their leg at the knee, then to only think about extending their leg while keeping it still so brain waves could be recorded in both exercises.

Neural activity was provided to the decoder (algorithm) to learn how the brain waves act in both situations. They discovered the actual movement and imagined movement used similar neural strategies.

“After we give the decoder this data, it learns to predict based on neural activity whenever there is movement or no movement,” Seáñez said. “We show that we can predict whenever someone is thinking about moving their leg, even if their leg does not actually move.”

The team used controls to make sure volunteer were truly imagining movement, not actually moving.

“Whenever people move, this can introduce signal noise, and we want to make sure that the signal noise is not what we’re learning to predict,” Seáñez said. “It’s movement intention or brain activity that we want to predict, so we have people imagine that they’re extending their leg and use the same algorithm that has been trained on people moving to predict whether they were imagining or not.”

He said this reveals two things: “One, that it’s more likely that we’re decoding movement intention and not an artifact, or noise, and second, whenever we employ this on people with spinal cord injury who will not have that ability to actually move their legs for us to label the data, we could use their imagination of moving a leg to train our decoder.”

The proof-of-concept study is the first step to building a noninvasive brain-spine interface that uses real-time predictions to deliver transcutaneous SCS to reinforce voluntary movement in a single joint in rehab patients with a spinal cord injury.

The team plans to test a generalized decoder trained on all participant data that could determine if a universal decoder might perform as well as a personalized one, and simplify its use in clinical settings.