Multivariate analysis for the Imaging of Neuronal activity using Deep architectureS

Funding: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 659860.
Duration: 11.01.2016-10.01.2018

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 (Figure 1).

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.

Figure 1: fMRI data processing pipeline. (Based on M.A. Lindquist (2008). The Statistical Analysis of fMRI Data. Statistical Science 23 (4), 439–464.)