Representation Learning for Motor Imagery Recognition with Deep Neural Network

Transferring a deep learning model from healthy subjects to stroke patients in a motor imagery brain-computer interface

Objective.Motor imagery (MI) brain-computer interfaces (BCIs) based on electroencephalogram (EEG) have been developed primarily for stroke rehabilitation, however, due to limited stroke data, current deep learning methods for cross-subject classification rely on healthy data. This study aims to assess the feasibility of applying MI-BCI models pre-trained using data from healthy individuals to detect MI in stroke patients.Approach.We introduce a new transfer learning approach where features from two-class MI data of healthy individuals are used to detect MI in stroke patients. We compare the results of the proposed method with those obtained from analyses within stroke data. Experiments were conducted using Deep ConvNet and state-of-the-art subject-specific machine learning MI classifiers, evaluated on OpenBMI two-class MI-EEG data from healthy subjects and two-class MI versus rest data from stroke patients.Main results.Results of our study indicate that through domain adaptation of a model pre-trained using healthy subjects' data, an average MI detection accuracy of 71.15% (±12.46%) can be achieved across 71 stroke patients. We demonstrate that the accuracy of the pre-trained model increased by 18.15% after transfer learning (p<0.001). Additionally, the proposed transfer learning method outperforms the subject-specific results achieved by Deep ConvNet and FBCSP, with significant enhancements of 7.64% (p<0.001) and 5.55% (p<0.001) in performance, respectively. Notably, the healthy-to-stroke transfer learning approach achieved similar performance to stroke-to-stroke transfer learning, with no significant difference (p>0.05). Explainable AI analyses using transfer models determined channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients.Significance.Transfer learning from healthy to stroke can enhance the clinical use of BCI algorithms by overcoming the challenge of insufficient clinical data for optimal training.

State-of-the-Art on Brain-Computer Interface Technology

This paper provides a comprehensive overview of the state-of-the-art in brain-computer interfaces (BCI). It begins by providing an introduction to BCIs, describing their main operation principles and most widely used platforms. The paper then examines the various components of a BCI system, such as hardware, software, and signal processing algorithms. Finally, it looks at current trends in research related to BCI use for medical, educational, and other purposes, as well as potential future applications of this technology. The paper concludes by highlighting some key challenges that still need to be addressed before widespread adoption can occur. By presenting an up-to-date assessment of the state-of-the-art in BCI technology, this paper will provide valuable insight into where this field is heading in terms of progress and innovation.

Time-Varying Effective Connectivity for Describing the Dynamic Brain Networks of Post-stroke Rehabilitation

Hemiplegia is a common motor dysfunction caused by a stroke. However, the dynamic network mechanism of brain processing information in post-stroke hemiplegic patients has not been revealed when performing motor imagery (MI) tasks. We acquire electroencephalography (EEG) data from healthy subjects and post-stroke hemiplegic patients and use the Fugl-Meyer assessment (FMA) to assess the degree of motor function damage in stroke patients. Time-varying MI networks are constructed using the adaptive directed transfer function (ADTF) method to explore the dynamic network mechanism of MI in post-stroke hemiplegic patients. Finally, correlation analysis has been conducted to study potential relationships between global efficiency and FMA scores. The performance of our proposed method has shown that the brain network pattern of stroke patients does not significantly change from laterality to bilateral symmetry when performing MI recognition. The main change is that the contralateral motor areas of the brain damage and the effective connection between the frontal lobe and the non-motor areas are enhanced, to compensate for motor dysfunction in stroke patients. We also find that there is a correlation between FMA scores and global efficiency. These findings help us better understand the dynamic brain network of patients with post-stroke when processing MI information. The network properties may provide a reliable biomarker for the objective evaluation of the functional rehabilitation diagnosis of stroke patients.