Control of a Visual Keyboard Using an Electrocorticographic Brain-Computer Interface
Control of a Visual Keyboard Using an Electrocorticographic Brain-Computer Interface
复制标题
DOI：
10.1177/1545968310382425
复制
发表时间：
2011-05-01
影响因子：
4.2
通讯作者：
Shih, Jerry J.
中科院分区：
文献类型：
--
作者：
Krusienski, Dean J.;Shih, Jerry J.
Objective.脑机接口（BCI）是使严重残疾的人能够使用他们的脑电波与他们的环境进行交流和互动的设备。大多数研究人类脑机接口的研究都使用头皮脑电图作为电信号的来源，并集中在假肢或屏幕上的计算机光标的运动控制上。作者假设，与头皮EEG相比，使用直接从皮层表面获得的大脑信号将更有效地控制交流/拼写任务。方法.共有6名难治性癫痫患者接受了皮质电图（ECOG）信号控制视觉键盘的能力测试。在P300视觉任务范例期间收集的ECOG数据被预处理并用于训练线性分类器以随后预测预期的目标字母。结果该分类器能够预测预期的目标字符或接近100%的准确性，使用少于15个刺激序列中的5个测试的6人。来自语言皮层外电极的ECOG数据有助于分类器，并使参与者能够在视觉键盘上写下单词。结论.这是一个新的发现，因为以前的侵入性脑机接口研究只使用来自运动皮层的信号来控制计算机光标或假体设备。这些结果表明，来自覆盖语言皮层和语言皮层外部的电极的ECOG信号可以可靠地控制视觉键盘，以在没有语音或肢体运动的情况下生成语言输出。
Objective. Brain-computer interfaces (BCIs) are devices that enable severely disabled people to communicate and interact with their environments using their brain waves. Most studies investigating BCI in humans have used scalp EEG as the source of electrical signals and focused on motor control of prostheses or computer cursors on a screen. The authors hypothesize that the use of brain signals obtained directly from the cortical surface will more effectively control a communication/ spelling task compared to scalp EEG. Methods. A total of 6 patients with medically intractable epilepsy were tested for the ability to control a visual keyboard using electrocorticographic (ECOG) signals. ECOG data collected during a P300 visual task paradigm were preprocessed and used to train a linear classifier to subsequently predict the intended target letters. Results. The classifier was able to predict the intended target character at or near 100% accuracy using fewer than 15 stimulation sequences in 5 of the 6 people tested. ECOG data from electrodes outside the language cortex contributed to the classifier and enabled participants to write words on a visual keyboard. Conclusions. This is a novel finding because previous invasive BCI research in humans used signals exclusively from the motor cortex to control a computer cursor or prosthetic device. These results demonstrate that ECOG signals from electrodes both overlying and outside the language cortex can reliably control a visual keyboard to generate language output without voice or limb movements.