Noninvasive neuroimaging and spatial filter transform enable ultra low delay motor imagery EEG decoding.

Objective. The brain-computer interface (BCI) system based on sensorimotor rhythm can convert the human spirit into instructions for machine control, and it is a new human-computer interaction system with broad applications. However, the spatial resolution of scalp electroencephalogram (EEG) is limited due to the presence of volume conduction effects. Therefore, it is very meaningful to explore intracranial activities in a noninvasive way and improve the spatial resolution of EEG. Meanwhile, low-delay decoding is an essential factor for the development of a real-time BCI system. Approach. In this paper, EEG conduction is modeled by using public head anatomical templates, and cortical EEG is obtained using dynamic parameter statistical mapping. To solve the problem of a large amount of computation caused by the increase in the number of channels, the filter bank common spatial pattern method is used to obtain a spatial filter kernel, which reduces the computational cost of feature extraction to a linear level. And the feature classification and selection of important features are completed using a neural network containing band-spatial-time domain self-attention mechanisms. Main results. The results show that the method proposed in this paper achieves high accuracy for the four types of motor imagery EEG classification tasks, with fairly low latency and high physiological interpretability. Significance. The proposed decoding framework facilitates the realization of low-latency human-computer interaction systems.