Intention decoding from PPC

Neural decoding uses brain activity to infer internal representations of the environmental states or predict behavior. Our study aimed to decode neural signal from the Posterior Parietal Cortex (V6A), to investigate intention coding and control of assistive devices. Data were recorded during delayed reaching in three different gaze/target conditions allowing to dissociate the retinotopic and the oculomotor reference frames. We used Deep Neural Networks to learn to decode the lateral displacement and the depth of the reached target from neural data averaged over four epochs, including pre-fixation, fixation, target, and movement, in each conditions (12 decoders in total). Decoding was then tested on every epoch/condition. We found, intuitively, that the decoders were able to infer the correct target position as soon as the subject received information about it. Importantly, we also obtained high generalization performance. First, generalization within condition, accross epochs suggests that the recorded V6A neurons encode motor plans, or intentions, in agreement with previous results. Second, the decoders also generalized across condition, which indicates a common target-coding reference frame resulting from the combination of oculomotor and retinotopic coordinates. This common reference frame corresponds to body-centered spatial coding required for the computation of motor plans implementing actions independently of gazing direction, and can be used for the efficient control of assistive devices.