Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning
Robust and accurate decoding of hand kinematics from entire spiking activity using deep learning
复制标题
使用深度学习从整个扣球活动中稳健而准确地解码手部运动学
DOI：
10.1101/2020.05.07.083063
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Ahmadi N
中科院分区：
文献类型：
--
作者：
Ahmadi N
目的脑机接口(Brain-Machine Interfaces，BMI)试图通过使神经系统疾病患者能够直接用他们的思想控制外部设备来恢复他们失去的运动功能。这项工作旨在提高稳健性和解码精度，这是目前皮质内BMI临床翻译中的主要挑战。方法我们提出将整个尖峰活动(ESA)-可以通过一种简单、无阈值和自动化技术提取的尖峰活动的包络-作为输入信号。我们将ESA与基于深度学习的解码算法相结合，该算法采用准递归神经网络(QRNN)结构。我们综合评估了ESA驱动的QRNN解码器在从执行不同任务的三个非人类灵长类动物的初级运动皮质区长期记录的神经信号中解码手部运动学的性能。主要结果我们提出的方法获得了一致高于输入信号和解码算法的任何其他组合的解码性能。即使从原始信号中去除尖峰，当使用不同的通道数，并且使用较少的训练数据量时，它也可以保持高的译码性能。总体上，显著的结果显示出非常高的译码精度和长期的鲁棒性，这是非常理想的，因为这是BMI中一个尚未解决的挑战。
ObjectiveBrain–machine interfaces (BMIs) seek to restore lost motor functions in individuals with neurological disorders by enabling them to control external devices directly with their thoughts. This work aims to improve robustness and decoding accuracy that currently become major challenges in the clinical translation of intracortical BMIs.ApproachWe propose entire spiking activity (ESA)—an envelope of spiking activity that can be extracted by a simple, threshold-less, and automated technique—as the input signal. We couple ESA with deep learning-based decoding algorithm that uses quasi-recurrent neural network (QRNN) architecture. We evaluate comprehensively the performance of ESA-driven QRNN decoder for decoding hand kinematics from neural signals chronically recorded from the primary motor cortex area of three non-human primates performing different tasks.Main resultsOur proposed method yields consistently higher decoding performance than any other combinations of the input signal and decoding algorithm previously reported across long-term recording sessions. It can sustain high decoding performance even when removing spikes from the raw signals, when using the different number of channels, and when using a smaller amount of training data.SignificanceOverall results demonstrate exceptionally high decoding accuracy and chronic robustness, which is highly desirable given it is an unresolved challenge in BMIs.
登录
查看更多内容
DOI：
10.1109/tnsre.2016.2612001
发表时间：
2017-10
期刊：
IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society
影响因子：
--
作者：
Jackson A;Hall TM
通讯作者：
Hall TM
从灵长类动物原发性运动皮层中的高频局部田间电位中解码3-D覆盖范围并掌握了运动学。
DOI：
10.1109/tbme.2010.2047015
发表时间：
2010-07
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Zhuang J;Truccolo W;Vargas-Irwin C;Donoghue JP
通讯作者：
Donoghue JP
影响因子：
4.1
作者：
Ryu SI;Shenoy KV
通讯作者：
Shenoy KV
影响因子：
9.8
作者：
Brochier T;Zehl L;Hao Y;Duret M;Sprenger J;Denker M;Grün S;Riehle A
通讯作者：
Riehle A
影响因子：
2.5
作者：
Aggarwal, Vikram;Mollazadeh, Mohsen;Thakor, Nitish V.
通讯作者：
Thakor, Nitish V.