ATLANTA--Georgia State University researchers have received a five-year, $3 million grant from the National Institute of Mental Health to develop new strategies to identify mood disorders using whole brain dynamics, which considers changes in the shape, size or location of brain networks, as well as changes in the connections between brain networks.
The researchers will use the approaches they develop to integrate four-dimensional brain imaging with clinical and cognitive data to identify clues about how mental illness presents in the brain.
Distinguished University Professor of Psychology Vince Calhoun, director of the Center for Translational Research in Neuroimaging and Data Science (TReNDS), is the lead researcher on the project.
Mental illness and mood disorders like schizophrenia and bipolar disorder are complex and influenced by genetic and environmental factors. However, diagnoses are primarily based on symptoms, which overlap extensively in some cases, rather than biomarkers or other biological information.
The team will develop novel dynamic approaches and leverage these to better understand how mental illness affects the brain in its continuously changing state. The researchers will be able to identify complex relationships in the brain by merging high-dimensional data from different sources.
"Most analysis approaches use relatively simple models to look at average brain function over time, but they miss important information," said Calhoun, who is also a Georgia Research Alliance Eminent Scholar in Brain Health & Image Analysis.
The researchers will use functional MRI data that is four-dimensional -- or looking at the brain across space and time. They will develop multivariate approaches that can capture complex and nonlinear changes over time and space and apply their models to a large neuroimaging dataset to re-evaluate standard diagnostic categorization.
"We will use this powerful new set of tools to study dynamics within and between schizophrenia, bipolar disorder and autism spectrum disorder," said Calhoun. "Preliminary evidence suggests these developed approaches will be more sensitive to the complexities of brain disorders."
The study builds on the team's previous development of a new framework for understanding changes in the brain's activity and connections, which has implications for how to best model the mechanisms of disease in the brain.
The project is a collaboration with Tulay Adali, a Distinguished University Professor at the University of Maryland, Baltimore County, whose team will focus on methods.
"I am especially excited about identifying subgroups of subjects in a completely data-driven manner using neuroimaging data," said Adali. "We hope this will better define subtypes of mental disorders and inform effective and personalized forms of therapy."
The research findings will be open-source and available to researchers worldwide, which Calhoun says is a key component of the work.
"It is important as the approaches are very general and can be applied to study many different aspects of the brain," he said.
The TReNDS Center is supported by Georgia State, Georgia Institute of Technology and Emory University, and is focused on developing, applying and sharing advanced analytic approaches and neuroinformatics tools to advance brain imaging and translate findings into advances in brain health and disease. The center uses large-scale data sharing and multi-modal data fusion techniques, including deep learning, genomics, brain mapping and artificial intelligence.