Information Assisted Dictionary Learning for fMRI data analysis

Extracting information from functional magnetic resonance images (fMRI) has been a major area of research for many years, but is still demanding more accurate techniques. Nowadays, we have a plenty of available information about the brain-behavior that can be used to develop more precise methods. Thus, this paper presents a new Dictionary Learning method that allows incorporating external information regarding the studied problem, through a novel sets of constraints. Finally, we apply this proposed method to synthetic fMRI data, where several tests show an improvement in the performance compared with other common techniques.