Generalizable spelling using a speech neuroprosthesis in an individual with severe limb and vocal paralysis

Metzger, Sean; Liu, Jessie R.; Moses, David A.; Dougherty, Max; Seaton, Margaret P.; Littlejohn, Kaylo T.; Chartier, Josh; Anumanchipalli, Gopala K.; Tu-Chan, Adelyn; Ganguly, Karunesh; Chang, Edward F.

doi:10.1038/s41467-022-33611-3

Cited by 73 publications

(87 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results from ECoG measurements further con rm the sensorimotor cortex as a suitable area for decoding speech-related brain activity. This includes the classi cation of phonemes 14 , vowels and consonants from consonant-vowel syllables 30 , letter sequences using code words 31 and sentences 32 .…”

Section: Discussionmentioning

confidence: 99%

Decoding single and paired phonemes using 7T functional MRI

Vitória,

Fernandes,

Boom

et al. 2023

Preprint

View full text Add to dashboard Cite

Several studies have shown that mouth movements related to the pronunciation of individual phonemes are represented in the sensorimotor cortex. This would theoretically allow for brain computer interfaces that are capable of decoding continuous speech by training classifiers based on the activity in the sensorimotor cortex related to the production of individual phonemes. To address this, we investigated the decodability of trials with individual and paired phonemes (pronounced consecutively with one second interval) using activity in the sensorimotor cortex. Fifteen participants pronounced 3 different phonemes and 3 combinations of two of the same phonemes in a 7T functional MRI experiment. We confirmed that support vector machine (SVM) classification of single and paired phonemes was possible. Importantly, by combining classifiers trained on single phonemes, we were able to classify paired phonemes with an accuracy of 53% (33% chance level), demonstrating that activity of isolated phonemes is present and distinguishable in combined phonemes. A SVM searchlight analysis showed that the phoneme representations are widely distributed in the ventral sensorimotor cortex. These findings provide insights about the neural representations of single and paired phonemes. Furthermore, it supports the notion that speech BCI may be feasible based on machine learning algorithms trained on individual phonemes using intracranial electrode grids.

show abstract

Section: Discussionmentioning

confidence: 99%

Decoding single and paired phonemes using 7T functional MRI

Vitória,

Fernandes,

Boom

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…27 Communication can be restored through mindcontrolled typing, [28][29][30][31] and preliminary data suggest the possibility to synthesize speech at a natural rate by decoding the neuronal activity of brain regions encoding kinematic representations of articulation. [32][33][34] Figure 1 summarizes the putative mechanisms and actuator options of motor braincomputer interface in children.…”

Section: Sensory Brain-computer Interfacementioning

confidence: 99%

Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and Ethical Considerations

et al. 2023

View full text Add to dashboard Cite

Invasive brain-computer interfaces hold promise to alleviate disabilities in individuals with neurologic injury, with fully implantable brain-computer interface systems expected to reach the clinic in the upcoming decade. Children with severe neurologic disabilities, like quadriplegic cerebral palsy or cervical spine trauma, could benefit from this technology. However, they have been excluded from clinical trials of intracortical brain-computer interface to date. In this manuscript, we discuss the ethical considerations related to the use of invasive brain-computer interface in children with severe neurologic disabilities. We first review the technical hardware and software considerations for the application of intracortical brain-computer interface in children. We then discuss ethical issues related to motor brain-computer interface use in pediatric neurosurgery. Finally, based on the input of a multidisciplinary panel of experts in fields related to brain-computer interface (functional and restorative neurosurgery, pediatric neurosurgery, mathematics and artificial intelligence research, neuroengineering, pediatric ethics, and pragmatic ethics), we then formulate initial recommendations regarding the clinical use of invasive brain-computer interfaces in children.

show abstract

“…Of course, this technology is still at a very early stage. The implantation of complex/advanced knowledge not only requires the co-implantation of multiple or even a large number of E-neurons but also relies on extensive and stable neural signal acquisition, [28][29][30] efficient and intelligent neural signal analysis, [31][32][33] and precise and non-destructive neuron excitation/stimulation. [34] In the initial stage, this technology will focus on the repair of fundamental brain reflection; for example, it will help patients with cerebral infarction and Alzheimer's disease regain their body balance and self-care ability.…”

Section: Conclusion and Perspectivementioning

confidence: 99%

Electronic Neurons for a New Learning Paradigm

Wang

Shi

et al. 2023

Adv Healthcare Materials

View full text Add to dashboard Cite

Learning is the cornerstone of the growth and development of human beings. However, traditional learning methods are insufficient to meet the explosive growth of knowledge and information. Repeated training accounts for a large proportion of learning time, which significantly limits the improvement of learning efficiency. Inspired by cloud storage technology, electronic neurons (E‐neuron) with functions similar to neurons in the brain are proposed. Implanted E‐neurons can form new patterns of neural activity in circuits, including both E‐neurons and biological neurons, which can transfer knowledge from electronic cloud devices to human beings without training. Herein, the feasibility of this concept is preliminarily demonstrated. Fiber neural electrodes (FNEs) made of poly(3,4‐ethylene dioxythiophene) (PEDOT) modified carbon nanotubes (CNTs) are used to form both dendrites and axons of E‐neuron. After the implantation of an E‐neuron in a mouse's brain, an electrical neural connection is created between the mitral cell and dorsolateral periaqueductal gray (dlPAG). A piece of knowledge similar to “The red light stops; the green light is all right.” is then passed on to the mouse.

show abstract

Generalizable spelling using a speech neuroprosthesis in an individual with severe limb and vocal paralysis

Cited by 73 publications

References 47 publications

Decoding single and paired phonemes using 7T functional MRI

Decoding single and paired phonemes using 7T functional MRI

Use of Invasive Brain-Computer Interfaces in Pediatric Neurosurgery: Technical and Ethical Considerations

Electronic Neurons for a New Learning Paradigm

Contact Info

Product

Resources

About