Objective. Detection of motor imagery of hand/arm has been extensively studied for stroke rehabilitation. This paper firstly investigates the detection of motor imagery of swallow (MI-SW) and motor imagery of tongue protrusion (MI-Ton) in an attempt to find a novel solution for post-stroke dysphagia rehabilitation.
Detection of MI-SW from a simple yet relevant modality such as MI-Ton is then investigated, motivated by the similar activation patterns between tongue movements and swallowing and less movements artifacts in performing tongue movements compared to swallowing. Approach. Novel features were extracted based on the coefficients of dual-tree complex wavelet transform to build multiple training models to detect MI-SW. The session-to-session classification accuracy was boosted by adaptively selecting the training model to maximize the ratio of between-classes distances versus within-class distances, using features of training and evaluation data. Main results. Our proposed method yielded an averaged cross-validation (CV) classification accuracies of 70.89% and 73.79% for MI-SW and MI-Ton based on 10 healthy subjects, which were significantly better than existing methods. In addition, averaged CV accuracies of 66.40% and 70.24% for MI-SW and MI-Ton were obtained for 1 stroke patient, demonstrating the detectability of MI-SW and MI-Ton from idle state. Furthermore, averaged session-to-session classification accuracies of 72.08% and 70% were achieved for 10 healthy subjects and 1 stroke patient using MI-Ton model. These results and the subject-wise strong correlations in classification accuracies between MI-SW and MI-Ton demonstrated the feasibility of detecting MI-SW from MI-Ton models.