Advancing sensory neuroprosthetics using artificial brain networks

Abstract

Implementation of effective brain or neural stimulation protocols for restoration of complex sensory perception, e.g., in the visual domain, is an unresolved challenge. By leveraging the capacity of deep learning to model the brain’s visual system, optic nerve stimulation patterns could be derived that are predictive of neural responses of higher-level cortical visual areas in silico. This novel approach could be generalized to optimize different types of neuroprosthetics or bidirectional brain-computer interfaces (BCIs). Implementation of effective brain or neural stimulation protocols for restoration of complex sensory perception, e.g., in the visual domain, is an unresolved challenge. By leveraging the capacity of deep learning to model the brain’s visual system, optic nerve stimulation patterns could be derived that are predictive of neural responses of higher-level cortical visual areas in silico. This novel approach could be generalized to optimize different types of neuroprosthetics or bidirectional brain-computer interfaces (BCIs). While neuroprosthetics for restoration of movement have substantially advanced over the last years, implementing effective sensory neuroprosthetics proved very challenging because effective brain/neural stimulation protocols were lacking. In this issue of Patterns, Romeni et al. propose a method to optimize optic nerve stimulation parameters for vision restoration using an artificial brain network.1Romeni S. Zoccolan D. Micera S. A machine learning framework to optimize optic nerve electrical stimulation for vision restoration.Patterns. 2021; 2https://doi.org/10.1016/j.patter.2021.100286Abstract Full Text Full Text PDF Scopus (3) Google Scholar By performing in silico experiments, they found that their stimulation framework achieves results comparable to natural vision. Such work highlights the potential of neurotechnology informed by artificial models of the brain and suggests that artificial neural networks may substantially aid the development of bidirectional brain-computer interfaces (BCIs) restoring both perception and action. Neuroprosthetics, i.e., systems that substitute for motor, sensory, or cognitive functions, require neural interfaces that can interact with the brain. Such interaction builds on brain/neural signal decoding, e.g., to restore motor function in paralysis,2Soekadar S.R. Witkowski M. Gomez C. Opisso E. Medina J. Cortese M. Cempini M. Carrozza M.C. Cohen L.G. Birbaumer N. Vitiello N. Hybrid EEG/EOG-based brain/neural hand exoskeleton restores fully independent daily living activities after quadriplegia.Science Robotics. 2016; 1: eaag3296Crossref PubMed Scopus (110) Google Scholar and stimulation of neural tissue or nerves, e.g., for restoration of sensory function. Based on operant conditioning of neural cell assemblies and machine learning, motor and cognitive neuroprosthetics have achieved remarkable versatility, e.g., continuous control of individual finger, wrist, and hand movements using surface or implanted functional electric stimulation (FES).3Bouton C.E. Shaikhouni A. Annetta N.V. Bockbrader M.A. Friedenberg D.A. Nielson D.M. Sharma G. Sederberg P.B. Glenn B.C. Mysiw W.J. et al.Restoring cortical control of functional movement in a human with quadriplegia.Nature. 2016; 533: 247-250Crossref PubMed Scopus (449) Google Scholar,4Ajiboye A.B. Willett F.R. Young D.R. Memberg W.D. Murphy B.A. Miller J.P. Walter B.L. Sweet J.A. Hoyen H.A. Keith M.W. et al.Restoration of reaching and grasping movements through brain-controlled muscle stimulation in a person with tetraplegia: a proof-of-concept demonstration.Lancet. 2017; 389: 1821-1830Abstract Full Text Full Text PDF PubMed Scopus (365) Google Scholar Recently, such a system was successfully enhanced by somatosensory cortex stimulation that substantially improved prosthetic hand and arm control by evoking tactile sensations.5Flesher S.N. Downey J.E. Weiss J.M. Hughes C.L. Herrera A.J. Tyler-Kabara E.C. Boninger M.L.