Dynamic Bayesian Networks for multimodal brain imaging data

• Grant number: 16/02621-0
• Support type: Scholarships abroad - Research Internship - Doctorate (Direct)
• Effective date (Start): May 01, 2016
• Effective date (End): October 31, 2016
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Carlos Dias Maciel
• Grantee: Fernando Pasquini Santos
• Supervisor abroad: Tamer S. Ibrahim
• Home Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Local de pesquisa : University of Pittsburgh (Pitt), United States
• Associated to the scholarship: 12/24272-7 - Structure learning of non-stationary dynamic Bayesian networks, BP.DD

Abstract

Modeling effective connectivity in the brain is always a task limited by the size of the model intended and data required for training. In recent years, however, advances have been achieved with MRI equipment able to obtain images with better signal to noise ratio, tissue contrast and spatial/spectral resolution, such as the 7 tesla MRI equipment at the University of Pittsburgh. Furthermore, many effective connectivity studies started to employ multimodal techniques, integrating knowledge and data from many different types of images; as for example, the use of DTI helping fMRI analysis. Therefore, in the present project, Dynamic Bayesian Networks (DBNs) with higher dimensions will be learned given these more abundant data and multimodal techniques obtained at the radiology facility at the University of Pittsburgh, which will on their turn provide new findings about the human brain.