ESI-GAL: EEG source imaging-based trajectory estimation for grasp and lift task

• Published in: Computers in biology and medicine Vol. 186; p. 109608
• Main Authors: Jain, Anant, Kumar, Lalan
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2025; Elsevier Limited
• Subjects: Adult; Biochips; Biomechanical Phenomena; Brain; Brain - physiology; Brain-Computer Interfaces; Brain–computer interface (BCI); Computer applications; Correlation coefficients; Decoders; Decoding; Deep Learning; EEG; Electroencephalography; Electroencephalography - methods; Feasibility studies; Female; Hand - physiology; Hand Strength - physiology; Human-computer interface; Humans; Implants; Inter-subject decoding; Internal Medicine; Kinematics; Male; Motor kinematics prediction (MKP); Motor skill learning; Neuroimaging; Other; Predictions; Prostheses; Prosthetics; Sensors; Signal Processing, Computer-Assisted; sLORETA; Source imaging; Time lag; Deep learning; Source imaging; Motor kinematics prediction (MKP); Inter-subject decoding; EEG; Electroencephalography; sLORETA; Brain–computer interface (BCI)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109608

Electroencephalogram (EEG) signals-based motor kinematics prediction (MKP) has been an active area of research to develop Brain–computer interface (BCI) systems such as exosuits, prostheses, and rehabilitation devices. However, EEG source imaging (ESI) based kinematics prediction is sparsely explored in the literature. In this study, pre-movement EEG features are utilized to predict three-dimensional (3D) hand kinematics for the grasp-and-lift motor task. A public dataset, WAY-EEG-GAL, is utilized for MKP analysis. In particular, sensor-domain (EEG data) and source-domain (ESI data) based features from the frontoparietal region are explored for MKP. Deep learning-based models are explored to achieve efficient kinematics decoding. Various time-lagged and window sizes are analyzed for hand kinematics prediction. Subsequently, intra-subject and inter-subject MKP analysis is performed to investigate the subject-specific and subject-independent motor-learning capabilities of the neural decoders. The Pearson correlation coefficient (PCC) is used as the performance metric for kinematics trajectory decoding. The rEEGNet neural decoder achieved the best performance with sensor-domain and source-domain features with the time lag and window size of 100ms and 450ms, respectively. The highest mean PCC values of 0.790, 0.795, and 0.637 are achieved using sensor-domain features, while 0.769, 0.777, and 0.647 are achieved using source-domain features in x, y, and z-directions, respectively. This study explores the feasibility of trajectory prediction using EEG sensor-domain and source-domain features for the grasp-and-lift task. Furthermore, inter-subject trajectory estimation is performed using the proposed deep learning decoder with EEG source domain features. •Sensor-domain and source-domain EEG features are explored for trajectory estimation.•The frontoparietal brain regions are utilized for spatial specific feature selection.•Proposed models are comprehensively evaluated across temporal EEG windows and lags.•rEEGNet model has the best decoding performance for MKP during grasp-and-lift task.•Inter-subject decoding is performed to demonstrate the subject adaptability.