System Derived Spatial-Temporal CNN for High-Density fNIRS BCI

An intuitive and generalisable approach to spatial-temporal feature extraction for high-density (HD) functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed, demonstrated here using Frequency-Domain (FD) fNIRS for motor-task classification. Enabled by the HD probe design, layered topographical maps of Oxy/deOxy Haemoglobin changes are used to train a 3D convolutional neural network (CNN), enabling simultaneous extraction of spatial and temporal features. The proposed spatial-temporal CNN is shown to effectively exploit the spatial relationships in HD fNIRS measurements to improve the classification of the functional haemodynamic response, achieving an average F1 score of 0.69 across seven subjects in a mixed subjects training scheme, and improving subject-independent classification as compared to a standard temporal CNN.

Automated summary

An intuitive and generalizable approach for spatial-temporal feature extraction in high-density functional Near-Infrared Spectroscopy (fNIRS) brain-computer interface (BCI) is proposed and demonstrated using Frequency-Domain (FD) fNIRS for motor-task classification. A 3D convolutional neural network (CNN) is trained with layered topographical maps of Oxy/deOxy Haemoglobin changes enabled by the HD probe design, allowing for simultaneous extraction of spatial and temporal features. The spatial-temporal CNN is shown to effectively capture the spatial relationships in HD fNIRS measurements, improving the classification of the functional haemodynamic response.