Multivariate analysis for the Imaging of Neuronal activity using Deep architectureS

Obiettivo

Functional magnetic resonance imaging (fMRI) is the dominating approach to research in the mapping of neural activity in the human brain. State of the art data analysis techniques employ a statistical parametric mapping (SPM) strategy to convert raw signal into interpretable images by processing data in a pipeline of task-specific modules. This approach, despite its simplicity and reliability, presents a set of inconveniences, including low interconnectivity among modules, resulting in suboptimal solutions. In this project we aim at making a major contribution to the field by replacing the step-by-step data processing pipeline by a deep neural network. We hypothesise that this will achieve better solutions by propagating the effects of module-based decisions through the network, jointly optimizing the whole processing pipeline. Moreover, fMRI low temporal resolution will be alleviated by means of a post-processing treatment, where advanced interpolation techniques will be used. We will release a freely accessible software tool that integrates with SPM, supplying an easy-to-use framework including advanced techniques for an automatic multivariate non-linear data analysis. The generated deep network solution will be applied in a multidisciplinary study in neurofeedback, where subjects will learn relaxation strategies guided by fMRI technology. At the end of the project, we expect our tool to become a useful standard practise in the field.