Intracranial Error Detection via Deep Learning
Martin Völker Graduate School of Robotics Albert-Ludwigs-University Freiburg, Germany Jiří Hammer Department of Neurology Motol University Hospital, Charles University Prague, Czech Republic Robin T. Schirrmeister Translational Neurotechnology Lab University Medical Center Freiburg Freiburg, Germany Joos Behncke Department of Computer Science Albert-Ludwigs-University Freiburg, Germany Lukas D.J. Fiederer Faculty of Biology Albert-Ludwigs-University Freiburg, Germany Andreas Schulze-Bonhage Epilepsy Center University Medical Center Freiburg Freiburg, Germany Petr Marusič Department of Neurology Motol University Hospital, Charles University Prague, Czech Republic Wolfram Burgard Department of Computer Science Albert-Ludwigs-University Freiburg, Germany Tonio Ball Translational Neurotechnology Lab University Medical Center Freiburg Freiburg, Germany
Abstract
Deep learning techniques have revolutionized the field of machine learning and were recently successfully applied to various classification problems in noninvasive electroencephalography (EEG). However, these methods were so far only rarely evaluated for use in intracranial EEG. We employed convolutional neural networks (CNNs) to classify and characterize the error-related brain response as measured in 24 intracranial EEG recordings. Decoding accuracies of CNNs were significantly higher than those of a regularized linear discriminant analysis. Using time-resolved deep decoding, it was possible to classify errors in various regions in the human brain, and further to decode errors over 200 ms before the actual erroneous button press, e.g., in the precentral gyrus. Moreover, deeper networks performed better than shallower networks in distinguishing correct from error trials in all-channel decoding. In single recordings, up to 100 % decoding accuracy was achieved. Visualization of the networks’ learned features indicated that multivariate decoding on an ensemble of channels yields related, albeit non-redundant information compared to single-channel decoding. In summary, here we show th
中文速览
大脑在犯错时会产生特定的神经信号，如果能准确识别这些信号，就能改进脑机接口等神经技术应用——而这项工作正是要用深度学习来破解植入式颅内脑电（intracranial EEG）中的错误相关脑响应。研究者对24段颅内脑电记录分别训练了多种卷积神经网络（CNN）架构，并与传统的正则化线性判别分析（rLDA）对比，发现CNN解码准确率显著更高，其中较深的网络（如34层残差网络ResNet）在多通道解码场景下优势尤为突出，部分单次记录甚至达到100%的解码准确率。更值得关注的是，通过滑动时间窗口分析，研究者发现在错误按键动作发生前200毫秒以上，前中央回等运动相关区域就已经出现可被解码的预测性活动，揭示了人脑错误处理网络从额叶到顶颞叶的时空动态传播规律。这项工作首次系统验证了深度学习在颅内脑电错误解码中的有效性，既为高精度脑机接口提供了新工具，也为绘制人脑错误处理的精细时空图谱开辟了新路径。
原文 arXiv:1805.01667;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1805.01667v3