Decoding cortical responses from visual input using an endovascular brain-computer interface

Objective.Implantable neural interfaces enable recording of high-quality brain signals that can improve our understanding of brain function. This work examined the feasibility of using a minimally invasive endovascular neural interface (ENI) to record interpretable cortical activity from the visual cortex.Approach. A sheep model (n= 5) was used to record and decode visually evoked potentials from the cortex both with an ENI and a subdural electrode grid. Sets of distinct experimental visual stimuli were presented to attempt decoding from the recorded cortical potentials, using perceptual categories of colour, contrast, movement direction orientation, spatial frequency and temporal frequency. Decoding performances are presented as accuracy scores from K-fold cross-validation of a stratified random forest classification model. The study compared the signal quality and decoding performance between the ENI and electrocorticography (ECoG) electrodes.Main results. Recordings from the ENI array resulted in lower decoding performances than the ECoG array, but the classification scores were significantly above chance in the stimuli categories of colour, contrast, direction and temporal frequency. This study is the first report of visually evoked neural activity using a minimally-invasive ENI.Significance. Overall, the results show that implantable macro-electrodes yield sufficient neural signal definition to discern primary visual percepts, using both endo-vascular and intracranial surgical placements.