Towards end-to-end optimisation of functional image analysis pipelines
This addresses the issue of fragmented optimization in neuroimaging for researchers, though it is incremental as it builds on existing neural network methods.
The authors tackled the problem of suboptimal parameter settings in functional MRI analysis pipelines by converting the entire pipeline into a deep neural network for joint optimization, resulting in adaptive spatial smoothing validated in a brain decoding experiment.
The study of neurocognitive tasks requiring accurate localisation of activity often rely on functional Magnetic Resonance Imaging, a widely adopted technique that makes use of a pipeline of data processing modules, each involving a variety of parameters. These parameters are frequently set according to the local goal of each specific module, not accounting for the rest of the pipeline. Given recent success of neural network research in many different domains, we propose to convert the whole data pipeline into a deep neural network, where the parameters involved are jointly optimised by the network to best serve a common global goal. As a proof of concept, we develop a module able to adaptively apply the most suitable spatial smoothing to every brain volume for each specific neuroimaging task, and we validate its results in a standard brain decoding experiment.