An FPGA-based, multi-channel, real-time, motion artifact detection technique for fNIRS/DOT systems

Functional Near-Infrared Spectroscopy (fNIRS) and its extension, Diffuse Optical Tomography (DOT), are emerging non-invasive neuroimaging techniques that measure brain activities by monitoring changes in blood oxygenation using near infrared light. However, motion artifacts from subject movements in fNIRS/DOT data could severely undermine data quality. Current solutions typically rely on offline methods executed on conventional computers in laboratories/hospitals, limiting real-time applications and flexibility in wider environments. To address these limitations, we present an FPGA-based multi-channel real-time motion artifact detection system. The proposed system, tested against an expert-annotated dataset, showcases encouraging overall performance, with a minimal delay of 2.75 ms across 12-channel raw fNIRS data, and boasts a sensitivity rate of 85.28% and accuracy of 87.06%. This efficiency is achieved using less than 10% of FPGA resources, underscoring that the proposed real-time processing system holds the potential to be scaled up to 3630 channels. These results indicate a promising avenue towards real-time motion artifact processing in large-size multi-channel fNIRS/DOT data. Our design lays the groundwork for its application in areas including wearable real-time functional brain imaging, brain-computer interfaces, human-robot interaction, and surgical monitoring.