Cognitive-motor brain–machine interfaces

Abstract

Brain–machine interfaces (BMIs) open new horizons for the treatment of paralyzed persons, giving hope for the artificial restoration of lost physiological functions. Whereas BMI development has mainly focused on motor rehabilitation, recent studies have suggested that higher cognitive functions can also be deciphered from brain activity, bypassing low level planning and execution functions, and replacing them by computer-controlled effectors. This review describes the new generation of cognitive-motor BMIs, focusing on three BMI types: Speech BMI – reconstructing a person’s speech based on the neuronal activity.Direct object control – controlling object movement without mimicking the limb movement that would yield the desired object movement.Decoding internal processes, such as neuronal representations of sensory information and decision making. By outlining recent progress in developing these BMI types, we aim to provide a unified view of contemporary research towards the replacement of behavioral outputs of cognitive processes by direct interaction with the brain.

Toward More Versatile and Intuitive Cortical Brain–Machine Interfaces

“…Thus, speech BMIs could read out both cognitive and motor signals to provide fast, intuitive speech output [59, 61, 63-65]. Importantly, critical parts of the speech network actuate during both overt and covert speech production [62, 66], suggesting that their activity may be available even after the onset of the locked-in state [67].…”

Visual epidural field potentials possess high functional specificity in single trials

“…Although we dedicated a good extent of the work to increase the classifier's overall performance as a proxy for both the selectivity and reliability of the EFP signal, it is important to note that it was not the goal of the study to find, or suggest, the optimal procedure. Particularly in somatosensory cortex, much emphasis has been put on optimization of classifiers and procedures, selection of signals, and choice of features, mostly using subdural or intracortical signals (Krusienski et al, 2011;Tankus et al, 2014;Slutzky and Flint, 2017). Yet, while some studies showed that also the EFP conveys sufficient information to be candidate as a source for BCI (Flint et al, 2012), the specific procedures that were applied, the experimental and clinical conditions, or the area delivering the neural signals usually not allowed to assess the functional specificity of the EFP.…”

Decoding Speech for Understanding and Treating Aphasia

“…For speech production, articulatory representations are likely coded in the frontal lobe within motor, premotor, and Broca’s areas (Bouchard et al, 2013; Goense and Logothetis, 2008; Hickok and Poeppel, 2007; Sahin et al, 2009; Tankus et al, 2013). At the lowest level, these areas may code the activation of individual muscles within the vocal tract (Lofqvist, 1999) that control the complex sequence of movements during articulation.…”

“…Recent work has also demonstrated how this approach can be usefully applied to study different aspects of speech or language in the human cortex (Brumberg et al, 2010; Tankus et al, 2013). Multiple levels of speech representation have been successfully decoded using intracranial neural signals.…”