Researchers attempt to use a deep learning framework to understand better how mental illness and other disorders affect the brain. The team is combining various types of brain imaging data to identify patterns indicative of brain disorders. The National Institute of Biomedical Imaging and Bioengineering funds their research with a $2.4 million, four-year grant.
Due to advances in brain imaging, researchers now have access to more data than in the past. Still, the relationships between modalities or data types captured could be more complex and better understood. The researchers attempt to characterize these relationships by combining and analyzing data from various sources.
The team will develop and train algorithms on thousands of existing datasets using the deep learning framework. They can determine which modalities or brain regions are most relevant to specific disorders by examining the data alongside two spectra, mood, and psychosis. The goal is to create multimodal biomarkers that healthcare professionals can use to diagnose mental health disorders like schizophrenia, depression, and bipolar disorder.
The researchers will investigate how APOE2, a gene that lowers the risk of Alzheimer’s, alters the brain to protect against neurodegenerative disease. The team will examine brain scans from Alzheimer’s patients using COINSTAC, a software tool developed by them that allows researchers worldwide to participate in extensive brain imaging analysis while protecting patient data.
Related Content: Pseudo-Random Speckle Illumination For High-Resolution Imaging