Objective. The limited spatial resolution inherent in electroencephalography (EEG), a widely-adopted non-invasive neuroimaging technique, combined with the intrinsic complexity of performing unilateral lower-limb motor imagery (MI), restricts decoding accuracy. To address these challenges, we propose a paradigm based on action observation-guided rhythmic motor execution (AO-ME) and motor imagery (AO-MI), designed to simplify task demands and enhance decoding performance. Magnetoencephalography (MEG) serves as the data acquisition method, leveraging its superior spatiotemporal resolution. Approach. Spatiotemporal and spectral features were characterized at the sensor level, and source imaging techniques were employed to examine cortical activation patterns. Ensemble task-related component analysis (eTRCA) facilitated decoding of unilateral tasks. Main results. Robust lateralized neural responses were observed, exhibiting low-frequency phase-locked components that distinctly reflected the task frequency and its second harmonic within sensorimotor, parietal, and occipital cortices. Moreover, significant contralateral suppression of the sensorimotor rhythm was observed. Decoding accuracies reached 95.22% ± 4.75% for AO-ME and 88.66% ± 8.52% for AO-MI across twenty participants based on the phase-locked features. Significance. Collectively, our findings demonstrate that the AO-ME/MI paradigm elicits stable, distinguishable neural activity, highlighting its potential as an effective strategy for decoding unilateral lower-limb movements within brain-computer interface (BCI) applications.
The similarity of neural activity in finger movements poses challenges for accurate decoding using many non-invasive imaging techniques. Magnetoencephalography (MEG), with its relatively high spatial resolution, offers the potential to capture the underlying dynamic neural differences. In this study, we recorded MEG signals during single extension movements of the right-hand fingers, examining the time-varying cortical activation patterns across different frequency bands and their contribution to decoding finger movements. Our results demonstrate that signals below 8 Hz not only enable effective movement classification but also reveal millisecond-scale neural activation patterns in the sensorimotor cortex. Furthermore, incorporating the spatiotemporal dynamics of neural activity may enhance decoding performance for fine motor control. These findings highlight the value of integrating temporal, frequency, and spatial dimensions in studying motor neural activity and underscore MEG’s potential for broader applications in movement-related neurophysiology and brain–computer interface research.