Neuroscientist Sumner Norman and AE Studio are developing free, open-source tools for the brain-computer interface (BCI) space.
BCI technology has become one of the hottest areas in medical technology. Companies are developing a host of methods with their own systems that would allow patients to control a computer with their brains. Such technology could allow immobile people to control a mouse cursor, keyboard, mobile device/tablet, wheelchair or prosthesis by thinking only.
“My goal is to restore capabilities to those who have lost them and eventually improve the way we all interact with technology and each other – the ultimate human-machine interface,” Norman said. Medical design and outsourcing. “And what could be more human than our brain, the organ that contains all of our memories, thoughts and intentions?”
Norman’s experience includes designing haptic interfaces for teleoperated robotics and exoskeleton robotics to aid motor recovery after neurological injuries like stroke. During his doctorate. studies, he has used BCIs to teach patients to create brain states through a process called neurofeedback. He said the method produced good results but was limited in terms of efficacy and cost/availability.
However, his experiences with BCIs led him to look for ways to build better ones. This includes hardware, software and protocol improvements, he said. Norman has spent the past five years developing ultrasound-based hardware to read brain signals. This method is now transitioning to human use, he said.
“At AE studio, we push the boundaries of BCI software,” said Norman. “We develop open-source and free tools to lower barriers to entry to contribute to neurotechnology and to accelerate researchers from all walks of life as much as possible. We also work with industry leaders in BCI hardware manufacturing to unlock every performance possible.
What is BCI and why is it gaining popularity?
Norman considers BCIs to be “a pretty simple concept at its core”.
They require a method of detecting the biophysical effects that occur when brain activity changes. Using an electrode, you can feel the voltage potential created by the neurons as they “spike”. Behavior or attempted behavior such as the movement of a person’s hand must be measured. Machine learning methods then find the correlation between brain patterns and behavior.
“Once this ‘decoder’ is good enough, we can measure the state of the brain to infer the intended behavior without directly measuring the behavior,” Norman said. “We then turn this intended behavior into commands. …Over time, the user learns and adapts to control the BCI more directly.
BCIs represent “the final frontier” in human-computer interaction, Norman said. With a significant portion of the world already spending much of their lives connected to the internet, it’s now about ‘waking up to the possibilities’. Advances in machine learning, cloud architecture, and advanced computing power mean that BCIs are possible. It’s not science fiction anymore, it’s just science.
“Like the internet, they have the potential to completely change the way we live, work and interact,” Norman said. “And yet, we are only scratching the surface of what is possible today. That’s exciting.”
Who are the space actors?
Some heavy hitters have invested their resources in the development of BCI technology. This includes Elon Musk’s Neuralink and Meta’s Reality Labs. However, a number of companies without the backing of a billionaire like Musk or a Mark Zuckerberg have paved the way for themselves.
Testing of Blackrock Neurotech’s technology has been ongoing in human patients for nearly 20 years. In 2021, Blackrock has received FDA Breakthrough Device Designation for its MoveAgain BCI System. It offers immobile patients the ability to control a range of devices by thinking alone. Blackrock is an example of companies collaborating with AE to advance BCI technology.
Meanwhile, Synchron is developing the catheter-delivered Stentrode brain-computer interface (BCI) implant. The company believes it is the only BCI company to tap into blood vessels to pick up signals from the brain. Synchronous to trials of its technology underway at several siteswith human implants already made.
Neuralink and Reality Labs “capture the headlines, sure, but bands like Paradromics, Synchronized and Blackrock Neurotech, are arguably better positioned to capture the first generation of BCI users,” Norman said. “As Neuralink continues to push for its first-in-human testing, Blackrock devices have already been implanted in nearly 40 humans, and Synchron is in the midst of its first clinical trial.”
Still, Norman says the first generation of BCI users will be limited to those with severe forms of neurological injury and disease. It’s because the BCI bandwidth is too slow or the costs are too high, he said. However, that is changing.
“The real winners will be those who create the BCI hardware and software that will justify its use by people with mild to moderate neurological injuries and diseases and/or psychiatric and cognitive disorders, and ultimately enable use for everyone,” Norman said. “Most of the bands making progress in building the next generation of BCIs aren’t making headlines yet.”
What is AE Studio and how does it contribute to BCI development?
Founded in 2016, AE’s goal is to empower human agency through technology. It aims to develop a BCI operating system to maximize human agency. Norman said the company wants to avoid a future in which BCI’s “crowning glory” is rising consumer spending.
AE helps startups and enterprise customers grow their software with data science and software development consulting. Some revenue is channeled into BCI software development, Norman said.
For the BCI software, AE builds models that Norman says are “robust, more efficiently calibrated, more easily scaled, and more easily deployed.” Data in the BCI domain is complex, he said. Experts estimate that around 86 billion neurons exist in the brain, with each neuron connected to around 1,000 neighboring neurons.
Today’s BCIs interface with “only” hundreds of thousands of neurons, Norman said. However, these neurons can drift in and out of sight of an electrode, forcing the BCI out of calibration. He explained that most BCI users need to recalibrate every few hours. One of AE’s projects stabilizes decoders over long periods for less time to calibrate, which includes tedious exercise of various learned behaviors.
Norman said the true potential of a platform technology lies in user data. However, one of AE’s focus areas centers around privacy in this sense.
“At AE, we’re building tools today, when the number of users is small, to protect all users as their numbers grow,” Norman said. “For example, we are currently building a tool that allows us to train sophisticated machine learning models that benefit many users without ever requiring the data to leave the user’s device. When privacy drives performance, everyone wins.
The future of BCIs
Norman said the first generation of commercial BCIs will focus on motor intent. An example of a first step would be to replace a computer mouse with a BCI-controlled cursor. Still, questions remain as to whether the BCI control will be a replacement for something like a keyboard due to difficulties in replicating or improving the speed of ten fingers on a keyboard.
“Silent speech” is the holy grail of BCI, Norman said, because speech remains the fastest method of communication between humans. There are still many hurdles to overcome before silent speech can be integrated into a commercial BCI.
Another class of BCI relies on the ability to “write” information to the brain instead of reading it. If BCIs are expanding there, Norman said, cochlear implants for the deaf represent “probably the most impactful BCI modality” to date. Thus, restoring sight to the blind offers another space in which BCI could settle.
Norman explained that as BCI hardware evolves to interact with the brain, so does their application space.
“The next generation of BCI will be versatile, significantly improving their value proposition,” said Norman. “And if enough people have BCIs, we can test many other approaches that we haven’t even thought of yet.”