Unilateral movement decoding of upper and lower limbs using magnetoencephalography

Problem: The effectiveness of distinguishing unilateral lower limb motor execution (ME) or imagery (MI) based on electroencephalogram (EEG) is limited by its low spatial resolution, since the somatotopies of bilateral lower limbs are close to each other. Aim: This research focused on differentiating unilateral lower limb tasks using magnetoencephalography (MEG) signals. Methods: MEG signals were recorded during unilateral upper and lower limb movements. Channel selection and extraction of band power features were performed at both the conventional sensor level and the proposed source level, reconstructed using beamforming. The classification performance at both levels was compared. Results: The theta band changes exhibited the most significant differences and lateralization across tasks. Task-related features were more prominent at the source than at the sensor level. The classification results indicate that all methods achieved an average accuracy of over 98.33% in classifying the upper limb task. For the classification of lower limb tasks, the average accuracies achieved at the source level (96.97% and 95.86%) were significantly higher than those obtained at the sensor level (90.00% and 92.57%). Conclusion and Significance: Our results demonstrated the feasibility of MEG in classifying unilateral lower limb movements, providing a potentially effective method for brain-computer interfaces (BCIs) to enhance control commands. Furthermore, signal processing at the source level can effectively enhance inter-task differences to achieve higher classification performance. Meanwhile, the theta band is highly effective in movement classification and may play an important role in motor function.

Duke Scholars

Author Fan Wang Neurobiology