Clinicians or researchers studying brain scan scans from functional magnetic resonance imaging (fMRI) typically see a static distribution of captured brain signals in a single instant. Today, researchers at the University of Maryland seeking to develop a new method for understanding mental activity over periods of time turned to an unexpected source: Hollywood blockbusters.
In a paperpublished last month in Computational Biology PLOS, Luiz Pessoa, professor of psychology and director of the Maryland Neuroimaging Center, and Joseph JaJa, professor and acting president of electrical and computer engineering with a joint appointment at the Institute of Advanced Computational Studies at the University of Maryland, presented a novel based on machine learning approaches to uncover this temporal information otherwise hidden in fMRI brain scans.
The neural network algorithms they developed, along with new statistical approaches, have been applied to a large public dataset of fMRI scans of subjects watching humorous or thriller movie clips like “Home Alone,” ” Star Wars “and” Ocean’s 11 “.
Their hypothesis was that after a neural network – an artificial intelligence system inspired by the human brain – digested the data from these brain scans while watching blockbuster movies, it would recognize similar information in the new fMRI scans that would otherwise remain latent. Instead of a simple snapshot, Pessoa and JaJa showed how recurrent neural networks (which focus on temporal sequences) can extract information about the brain’s responses over longer timescales in contexts similar to those that we encounter in everyday life.
“Neuroscience integrates extremely sophisticated data analysis, including machine learning, neural networks and advanced statistical methods,” said Pessoa. “The collaboration with Joseph JaJa allows neuroscientists to work with engineers to advance our understanding of the brain. “
The article and collaboration were born out of a 2017 UMD seed grant Institute of Brain and Behavior (BBI).
“The BBI is proud to support exciting new research partnerships in the life and physical sciences, such as the collaboration between Pessoa and JaJa,” said Elizabeth Quinlan, Professor of Biology, Clark Leadership Chair in Neuroscience and Director of the BBI . “The development and application of machine learning techniques and artificial intelligence approaches are driving the vital growth and expansion of collaborative neuroscience on our campus. “
With recent funding at Pessoa of the National Institute of Mental Health, the researchers plan to continue their studies on the brain mechanisms of emotion and motivation.
“We need to break down silos and promote integration between disciplines,” Pessoa noted. “This interdisciplinarity is the only way to make serious progress in trying to understand one of the most difficult problems in all of science: the brain.”