Editing Brain–computer interface (section)

==== Electrocorticography ====
[[Electrocorticography]] (ECoG) measures brain electrical activity from beneath the skull in a way similar to non-invasive electroencephalography, using electrodes embedded in a thin plastic pad placed above the cortex, beneath the [[dura mater]].<ref>{{cite book | last1=Serruya | first1=Mijail | last2=Donoghue | first2=John | chapter = Chapter III: Design Principles of a Neuromotor Prosthetic Device | title = Neuroprosthetics: Theory and Practice | veditors = Horch KW, Dhillon GS | publisher = Imperial College Press | year=2004 |pages=1158–1196 | doi=10.1142/9789812561763_0040 | archive-url=https://web.archive.org/web/20050404155139/http://donoghue.neuro.brown.edu/pubs/2003-SerruyaDonoghue-Chap3-preprint.pdf | archive-date=4 April 2005 |chapter-url=http://donoghue.neuro.brown.edu/pubs/2003-SerruyaDonoghue-Chap3-preprint.pdf}}</ref> ECoG technologies were first trialled in humans in 2004 by Eric Leuthardt and Daniel Moran from [[Washington University in St. Louis]]. In a later trial, the researchers enabled a teenage boy to play [[Space Invaders]].<ref>{{cite web | url = http://news-info.wustl.edu/news/page/normal/7800.html | title = Teenager moves video icons just by imagination | work = Press release | publisher = Washington University in St Louis | date = 9 October 2006 }}</ref> This research indicates that control is rapid, requires minimal training, balancing signal fidelity and level of invasiveness.{{refn|group=note|These electrodes had not been implanted in the patient with the intention of developing a BCI. The patient had had severe [[epilepsy]] and the electrodes were temporarily implanted to help his physicians localize seizure foci; the BCI researchers simply took advantage of this.<ref>{{cite journal | vauthors = Schalk G, Miller KJ, Anderson NR, Wilson JA, Smyth MD, Ojemann JG, Moran DW, Wolpaw JR, Leuthardt EC | display-authors = 6 | title = Two-dimensional movement control using electrocorticographic signals in humans | journal = Journal of Neural Engineering | volume = 5 | issue = 1 | pages = 75–84 | date = March 2008 | pmid = 18310813 | pmc = 2744037 | doi = 10.1088/1741-2560/5/1/008 | bibcode = 2008JNEng...5...75S }}</ref>}}

Signals can be either subdural or epidural, but are not taken from within the brain [[parenchyma]]. Patients are required to have invasive monitoring for localization and resection of an epileptogenic focus.{{Citation needed|date=May 2024}}

ECoG offers higher spatial resolution, better signal-to-noise ratio, wider frequency range, and less training requirements than scalp-recorded EEG, and at the same time has lower technical difficulty, lower clinical risk, and may have superior long-term stability than intracortical single-neuron recording.<ref>{{cite journal | vauthors = Nicolas-Alonso LF, Gomez-Gil J | title = Brain computer interfaces, a review | journal = Sensors | volume = 12 | issue = 2 | pages = 1211–1279 | date = 2012-01-31 | pmid = 22438708 | pmc = 3304110 | doi = 10.3390/s120201211 | bibcode = 2012Senso..12.1211N | doi-access = free }}</ref> This feature profile and evidence of the high level of control with minimal training requirements shows potential for real world application for people with motor disabilities.<ref name=Mondeofuse>{{cite news | vauthors = Yanagisawa T |title=Electrocorticographic Control of Prosthetic Arm in Paralyzed Patients |doi=10.1002/ana.22613 |quote= ECoG- Based BCI has advantage in signal and durability that are absolutely necessary for clinical application|work=[[American Neurological Association]] |year= 2011 |volume=71 |issue=3 |pages=353–361 }}</ref><ref name=TelepathicCommVowel>{{cite news | vauthors = Pei X |title=Decoding Vowels and Consonants in Spoken and Imagined Words Using Electrocorticographic Signals in Humans |pmid=21750369 |quote= Justin Williams, a biomedical engineer at the university, has already transformed the ECoG implant into a micro device that can be installed with a minimum of fuss. It has been tested in animals for a long period of time – the micro ECoG stays in place and doesn't seem to negatively affect the immune system.|work=J Neural Eng 046028th ser. 8.4 |year=2011 }}</ref> 

[[Edward Chang (neurosurgeon)|Edward Chang]] and Joseph Makin from [[UCSF Medical Center|UCSF]] reported that ECoG signals could be used to decode speech from epilepsy patients implanted with high-density ECoG arrays over the peri-Sylvian cortices.<ref>{{cite book | vauthors = Makin JG, Moses DA, Chang EF | title = Brain-Computer Interface Research | veditors = Guger C, Allison BZ, Gunduz A | chapter = Speech Decoding as Machine Translation|date=2021 |pages=23–33 |series=SpringerBriefs in Electrical and Computer Engineering|place=Cham|publisher=Springer International Publishing |language=en |doi=10.1007/978-3-030-79287-9_3 |isbn=978-3-030-79287-9 | s2cid = 239756345 }}</ref><ref>{{cite journal | vauthors = Makin JG, Moses DA, Chang EF | title = Machine translation of cortical activity to text with an encoder-decoder framework | journal = Nature Neuroscience | volume = 23 | issue = 4 | pages = 575–582 | date = April 2020 | pmid = 32231340 | doi = 10.1038/s41593-020-0608-8 | pmc = 10560395 | s2cid = 214704481 }}</ref> They reported word error rates of 3% (a marked improvement from prior efforts) utilizing an encoder-decoder [[neural network]], which translated ECoG data into one of fifty sentences composed of 250 unique words.{{cn|date=April 2025}}