Neural Decoding of Electrocorticographic Signals
Kei Majima · NAIST Digital Library (Nara Institute of Science and Technology) · 2014
Over the last decade, neural decoding technology based on machine learning has enabled us to extract fine information on visual experiences and motor commands from measured neural signals, which is becoming a powerful tool for investigating neural representations and generating commands for controlling brain-machine interfaces (BMIs).To extract information with high predictive performance, neural recording methods that provide high spatiotemporal resolution and signal stability are required.One candidate is electrocorticogram (ECoG), which measures population activity of neurons with electrodes placed on the surface of the brain.Here, with the aim of highperformance decoding with ECoG, we tested the utility of ECoG systems in animal and human studies, and improved techniques to extract information from ECoG data.As the first contribution of this thesis, the signal stability of ECoG responses recorded via a newly developed high-density mesh electrode array was tested.Collaborators applied it to the visual cortex in rats and this thesis demonstrates above-chance, generalized decoding performance for simple visual stimulation, using six hours of continuous data (chapter 2).Second, by applying decoding analysis to simultaneously recorded ECoG, LFP, and MUA signals from the monkey IT cortex, extractable information on visually presented objects was compared.The resultant decoding performance with ECoG was high and comparable to LFP and MUA (chapter 3).Next, ECoG was used to investigate how face-selective regions and written word-selective regions are distributed on the human cortex, which is considered a challenging task with fMRI.Results reveal that there exist multiple, separate face-and written word-selective regions in the human cortex (chapter 4).Finally, using ECoG responses from human patients when they viewed