Osaka University, Institute for Advanced Co-Creation Studies, 2-2 Yamadaoka, Suita, Osaka 565-0871, Japan.
J Neural Eng. 2020 Jun 2;17(3):036009. doi: 10.1088/1741-2552/ab8910.
Brain-computer interfaces (BCIs) using electrocorticographic (ECoG) signals have been developed to restore the communication function of severely paralyzed patients. However, the limited amount of information derived from ECoG signals hinders their clinical applications. We aimed to develop a method to decode ECoG signals using spatiotemporal patterns characterizing movement types to increase the amount of information gained from these signals.
Previous studies have demonstrated that motor information could be decoded using powers of specific frequency bands of the ECoG signals estimated by fast Fourier transform (FFT) or wavelet analysis. However, because FFT is evaluated for each channel, the temporal and spatial patterns among channels are difficult to evaluate. Here, we used dynamic mode decomposition (DMD) to evaluate the spatiotemporal pattern of ECoG signals and evaluated the accuracy of motor decoding with the DMD modes. We used ECoG signals during three types of hand movements, which were recorded from 11 patients implanted with subdural electrodes. From the signals at the time of the movements, the modes and powers were evaluated by DMD and FFT and were decoded using support vector machine. We used the Grassmann kernel to evaluate the distance between modes estimated by DMD (DMD mode). In addition, we decoded the DMD modes, in which the phase components were shuffled, to compare the classification accuracy.
The decoding accuracy using DMD modes was significantly better than that using FFT powers. The accuracy significantly decreased when the phases of the DMD mode were shuffled. Among the frequency bands, the DMD mode at approximately 100 Hz demonstrated the highest classification accuracy.
DMD successfully captured the spatiotemporal patterns characterizing the movement types and contributed to improving the decoding accuracy. This method can be applied to improve BCIs to help severely paralyzed patients communicate.
脑-机接口（BCI）利用脑电（ECoG）信号已经被开发出来，以恢复严重瘫痪患者的沟通功能。然而，从 ECoG 信号中获得的信息量有限，限制了它们的临床应用。我们的目的是开发一种使用运动类型特征的时空模式来解码 ECoG 信号的方法，以增加从这些信号中获得的信息量。
先前的研究表明，运动信息可以使用由快速傅里叶变换（FFT）或小波分析估计的 ECoG 信号的特定频带的功率来解码。然而，由于 FFT 是针对每个通道进行评估的，因此通道之间的时间和空间模式很难评估。在这里，我们使用动态模式分解（DMD）来评估 ECoG 信号的时空模式，并使用 DMD 模式评估运动解码的准确性。我们使用了 11 名植入硬膜下电极的患者在进行三种手部运动时的 ECoG 信号。从运动时的信号中，通过 DMD 评估模式和功率，并使用支持向量机进行解码。我们使用 Grassmann 核来评估 DMD 估计的模式之间的距离（DMD 模式）。此外，我们还解码了相位分量被打乱的 DMD 模式，以比较分类精度。
使用 DMD 模式的解码精度明显优于使用 FFT 功率的解码精度。当 DMD 模式的相位被打乱时，精度显著降低。在频带中，约 100 Hz 的 DMD 模式表现出最高的分类精度。
DMD 成功地捕捉到了运动类型特征的时空模式，有助于提高解码精度。这种方法可以应用于改善 BCI，以帮助严重瘫痪的患者进行交流。
