PHILADELPHIA – A study using cloud-computing to track and display brain activity in real-time for the potential treatment of depression has netted Penn Medicine, Princeton University, Yale University and Intel Corporation with a Fierce Innovation Award. Given each year by FierceMarkets, Fierce Innovation Awards are presented to organizations that solve telecommunications challenges, such as issues with device and connection security, syncing, and signal quality. This year’s awards were presented at the Next Gen Wireless Networks Summit in Dallas this fall.
The goal of the Real-Time Attention Study is to provide a new avenue for depression treatment by using a cloud-based real-time image analysis system. Through the monitoring of reactions to negative stimuli during scanning sessions, patients are trained to focus their brains away from the negative and toward the positive, which researchers believe will reduce the frequency and intensity of symptoms of depression—which affects 300 million people worldwide.
“If we’re successful with this approach, it has the potential to transform the treatment of depression,” said C. William Hanson III, MD, chief medical information officer and vice president at Penn Medicine. “The brain has historically been a black box, where no one has been able to see exactly what’s going on.”
Hanson and his colleagues believe this form of brain-imaging could be a powerful tool in the field of cognitive therapy, the discipline of using stimuli to re-train the brain.
The Penn principal investigator on the project looking into its application to depression, Yvette Sheline, MD, the McLure professor of Psychiatry and Behavioral Research at Penn Medicine, explained that the project worked by using functional MRI (fMRI) —which follows blood flow to track brain activity—in order to get a real-time assessment of how the brain functions when reacting to different images patients are shown.
“We’re basically mapping what different combinations of brain regions can tell us about where somebody is looking when they see something stimulating,” Sheline said.
To find this out, people being scanned with fMRI are shown a picture display that is tied to an analysis algorithm. That algorithm responds immediately to feedback from the brain scan, so when someone reacts to a certain image, they see subsequent images that are determined by the brain’s response. Each display contains emotionally neutral images, such as a beach scene, and unpleasant images, like an angry face. When the patient is detected as focusing on the angry face, the algorithm seamlessly feeds in another set of images, this time making the angry face more prominent. The patient is directed to try focusing more on the emotionally neutral images and less on the angry faces. Ultimately, the hope is that patients will be able to train their brains to have less of a focus on or reaction to negative stimuli, which could help them when they are experiencing symptoms related to depression.
This project originated at Princeton University through a collaboration between Princeton computer scientists and neuroscientists who wished to develop fast fMRI data analysis methods and software. Intel joined the collaboration early on, both sponsoring and making technical contributions to the project. One breakthrough achievement that resulted from this joint effort was the ability to greatly accelerate data analysis of interactions between brain regions, taking the process from years to seconds.
Replicating this type of system in most clinical settings would be prohibitively expensive and cumbersome. So the Princeton and Intel researchers designed and implemented a cloud service capable of delivering closed-loop, real-time brain imaging to any clinic with an fMRI scanner and an internet connection. Penn Medicine signed on as the first clinical collaborator and pilot site to use this technology.
“This project has provided an example of the tremendous progress being made, and remarkable opportunities that are being developed for brain-based feedback,” said Jonathan Cohen, co-director of the Princeton Neuroscience Institute, the Robert Bendheim and Lynn Bendheim Thoman Professor in Neuroscience, and a professor of Psychology at the Princeton Neuroscience Institute. “For neuroscientists, real-time processing is a breakthrough that opens up a whole new area of research with the potential not only to accelerate basic brain science, but also to improve diagnosis and treatment of neuropsychiatric disorders. Now we have taken the step of deploying these advances as software and making them readily available to clinicians.”
The project is still ongoing and sharable results are likely a year away, but these efforts have already demonstrated that real-time imaging using cloud computing is possible.
Bringing the cloud into this project allows for heavy computing muscle to be beamed in and also brings in a necessary “agile environment,” explained Vasee Sivasegaran, associate chief information officer of Information Services infrastructure at Penn Medicine, whose team provided and deployed the cloud hardware, security and compliance for the study. Sivasegaran noted that on-site servers for a project like this would have taken days or weeks to install, whereas the cloud computing environment took only minutes.
The study also showed that hosting the technology in the cloud instead of on-premises reduced the price of mapping by nearly half, which points to the potential to scale the technology for broader use.
In addition to Cohen, researchers whose work is recognized with this award include Princeton’s Kenneth Norman, a professor of Psychology and the Princeton Neuroscience Institute and Chair, Department of Psychology; Kai Li, the Paul M. and Marcia R. Wythes Professor of Computer Science; and Anne Mennen, a PhD candidate; as well as Intel’s Ted Willke, senior principal engineer in Intel Labs, and Yale University’s Nicholas Turk-Browne, a professor of Psychology.
Penn Medicine is one of the world’s leading academic medical centers, dedicated to the related missions of medical education, biomedical research, and excellence in patient care. Penn Medicine consists of the Raymond and Ruth Perelman School of Medicine at the University of Pennsylvania (founded in 1765 as the nation’s first medical school) and the University of Pennsylvania Health System, which together form a $8.6 billion enterprise.
The Perelman School of Medicine has been ranked among the top medical schools in the United States for more than 20 years, according to U.S. News & World Report's survey of research-oriented medical schools. The School is consistently among the nation's top recipients of funding from the National Institutes of Health, with $494 million awarded in the 2019 fiscal year.
The University of Pennsylvania Health System’s patient care facilities include: the Hospital of the University of Pennsylvania and Penn Presbyterian Medical Center—which are recognized as one of the nation’s top “Honor Roll” hospitals by U.S. News & World Report—Chester County Hospital; Lancaster General Health; Penn Medicine Princeton Health; and Pennsylvania Hospital, the nation’s first hospital, founded in 1751. Additional facilities and enterprises include Good Shepherd Penn Partners, Penn Medicine at Home, Lancaster Behavioral Health Hospital, and Princeton House Behavioral Health, among others.
Penn Medicine is powered by a talented and dedicated workforce of more than 43,900 people. The organization also has alliances with top community health systems across both Southeastern Pennsylvania and Southern New Jersey, creating more options for patients no matter where they live.
Penn Medicine is committed to improving lives and health through a variety of community-based programs and activities. In fiscal year 2019, Penn Medicine provided more than $583 million to benefit our community.