Motor Imagery Tasks Research Articles

CONTRAST SENSITIVITY AND BRAIN NETWORK COMMUNITY STRUCTURE IN THE BRAIN NETWORKS AND MOBILITY STUDY

Abstract Contrast sensitivity (CS) is the ability to perceive differences in shades of light and dark, which is important for pattern recognition and depth perception. We have previously shown that impaired CS is associated with poor performance on the expanded short physical performance battery (eSPPB), and that performance on the eSPPB is associated with sensory motor cortex (SMC) connectivity at rest. We hypothesized that brain networks are important to the relationship of CS with eSPPB. Participants (n=192) were cognitively unimpaired older adults (mean age=76.5±4.7 years; 56.5% female, 9.4% black) with good visual acuity who completed CS testing. We applied graph theory to characterize the cross-sectional relationship of binocular CS to functional brain networks generated from fMRI both at rest and during a motor imagery (MI) task and determined the spatial patterns of SMC, visual (VIS) and default mode (DMN) network connectivity. Regression analyses were used to assess associations of CS with brain network connectivity without and with adjustment for sex and eSPPB. Lower CS (p=0.009) was significantly associated with degraded SMC connectivity at rest even in models adjusted for eSPPB and sex. Similarly, lower CS was significantly associated with degraded VIS and DMN connectivity during the MI task (all p< 0.005) when controlling for eSPPB and sex. These results indicate that low CS and poor eSPPB are both associated with connectivity in the SMC at rest and with VIS and DMN during MI in older adults. These findings may be important for understanding the relationship between age-related visual and mobility dysfunction.

Measuring neuronal avalanches to inform brain-computer interfaces

Large-scale interactions among multiple brain regions manifest as bursts of activations called neuronal avalanches, which reconfigure according to the task at hand and, hence, might constitute natural candidates to design brain-computer interfaces (BCIs). To test this hypothesis, we used source-reconstructed magneto/electroencephalography during resting state and a motor imagery task performed within a BCI protocol. To track the probability that an avalanche would spread across any two regions, we built an avalanche transition matrix (ATM) and demonstrated that the edges whose transition probabilities significantly differed between conditions hinged selectively on premotor regions in all subjects. Furthermore, we showed that the topology of the ATMs allows task-decoding above the current gold standard. Hence, our results suggest that neuronal avalanches might capture interpretable differences between tasks that can be used to inform brain-computer interfaces.

A multiscale feature fusion network based on attention mechanism for motor imagery EEG decoding

The decoding of motor imagery (MI) electroencephalogram (EEG) is an essential component of the brain–computer interface (BCI), which can help patients with motor impairment communicate directly with the outside world through assistive devices. The key to motor imagery electroencephalogram (MI-EEG) classification is to extract multiple temporal, spatial, and spectral features, to obtain more comprehensive and representative information. However, current deep learning methods must fully consider the depth of temporal features and multi-spectral knowledge in EEG and often ignore the temporal or spectrum dependence in MI-EEG. In addition, the lack of effective feature fusion methods can lead to information redundancy, which affects decoding performance. To solve the above problems, this paper proposes a novel MI-EEG decoding method, named multi-scale feature fusion network based on attention mechanism (MSFF-SENet). Firstly, the multi-scale spatio-temporal module (MS-STM) and the multi-scale temporal module (MSTM) extract spatial and high-dimensional temporal features from the original signal. Then, the power spectral density estimation (PSD) convolution module (PSD-Conv module) acquires the multi-spectral features of the MI-EEG signal. Secondly, the feature fusion module fuses spatio-temporal and multi-spectral features to generate integrated feature mappings and establish the dependencies between different features. Finally, we conducted a visual analysis of the results, explaining the neural activity patterns of various motor imagery tasks in different frequency ranges and revealing the potential relationship between body movement and changes related to brain activity. The experimental results show that the classification accuracy of this model in BCI Competition IV 2a (BCI IV 2a) and High Gamma (HGD) datasets is 85.37% and 96.60%, respectively, which is superior to the most advanced methods.

Explainable cross-task adaptive transfer learning for motor imagery EEG classification

Objective. In the field of motor imagery (MI) electroencephalography (EEG)-based brain-computer interfaces, deep transfer learning (TL) has proven to be an effective tool for solving the problem of limited availability in subject-specific data for the training of robust deep learning (DL) models. Although considerable progress has been made in the cross-subject/session and cross-device scenarios, the more challenging problem of cross-task deep TL remains largely unexplored. Approach. We propose a novel explainable cross-task adaptive TL method for MI EEG decoding. Firstly, similarity analysis and data alignment are performed for EEG data of motor execution (ME) and MI tasks. Afterwards, the MI EEG decoding model is obtained via pre-training with extensive ME EEG data and fine-tuning with partial MI EEG data. Finally, expected gradient-based post-hoc explainability analysis is conducted for the visualization of important temporal-spatial features. Main results. Extensive experiments are conducted on one large ME EEG High-Gamma dataset and two large MI EEG datasets (openBMI and GIST). The best average classification accuracy of our method reaches 80.00% and 72.73% for OpenBMI and GIST respectively, which outperforms several state-of-the-art algorithms. In addition, the results of the explainability analysis further validate the correlation between ME and MI EEG data and the effectiveness of ME/MI cross-task adaptation. Significance. This paper confirms that the decoding of MI EEG can be well facilitated by pre-existing ME EEG data, which largely relaxes the constraint of training samples for MI EEG decoding and is important in a practical sense.

A Comparative Analysis of CNNs and RNNs for EEG-based Motor Imagery Classification in BCIs

EEG-based motor imagery (MI) classification plays a vital role in brain-computer interface systems (BCIs) to enable the control of external devices with the human brain. However, there is currently limited research focusing on the comparison between different machine learning models for this task. This research paper aims to present a comprehensive comparative analysis of two popular deep learning architectures, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for MI recognition with EEG data. The experiments utilised the EEG Motor Movement/Imagery Dataset v1.0.0 from PhysioNet, which contains EEG signals recorded during a variety of motor imagery tasks. The respective performances of the CNN and RNN architectures were subsequently evaluated and compared based on classification accuracy and computational efficiency. Various metrics and statistics, namely accuracy, precision, training speed, memory usage, etc., were used for assessment. The results revealed that CNN outperforms RNN in terms of accuracy, while RNN demonstrates superior computational efficiency. These findings potentially serve as a valuable guideline for researchers and practitioners in the field of BCIs, aiding them in selecting the most suitable neural network architecture for performing MI related tasks.

Fractal Dimension as a discriminative feature for high accuracy classification in motor imagery EEG-based brain-computer interface

Background and ObjectiveThe brain-computer interface (BCI) technology acquires human brain electrical signals, which can be effectively and successfully used to control external devices, potentially supporting subjects suffering from motor impairments in the interaction with the environment. To this aim, BCI systems must correctly decode and interpret neurophysiological signals reflecting the intention of the subjects to move. Therefore, the accurate classification of single events in motor tasks represents a fundamental challenge in ensuring efficient communication and control between users and BCIs. Movement-associated changes in electroencephalographic (EEG) sensorimotor rhythms, such as event-related desynchronization (ERD), are well-known features of discriminating motor tasks. Fractal dimension (FD) can be used to evaluate the complexity and self-similarity in brain signals, potentially providing complementary information to frequency-based signal features. MethodsIn the present work, we introduce FD as a novel feature for subject-independent event classification, and we test several machine learning (ML) models in behavioural tasks of motor imagery (MI) and motor execution (ME). ResultsOur results show that FD improves the classification accuracy of ML compared to ERD. Furthermore, unilateral hand movements have higher classification accuracy than bilateral movements in both MI and ME tasks. ConclusionsThese results provide further insights into subject-independent event classification in BCI systems and demonstrate the potential of FD as a discriminative feature for EEG signals.

The Influence of Resistance Training Experience on the Efficacy of Motor Imagery for Acutely Increasing Corticospinal Excitability.

Both motor imagery and resistance-training enhance motor function and corticospinal excitability. We tested the hypothesis that young participants with significant resistance-training experience would show heightened corticospinal excitability during a single session of motor imagery training. Fifty-six participants (mean ± SD age = 22 ± 2 years) were divided into resistance-trained and untrained groups. Forty-one upper-body resistance trained (21 males, 20 females; mean ± SD relative one repetition maximum bench press = 0.922 ± 0.317 kg/kg) and 15 untrained (4 males, 11 females; mean ± SD relative one repetition maximum bench press = 0.566 ± 0.175 kg/kg) participants visited the laboratory on three separate occasions. The first visit served as the familiarization session. During visits 2 and 3, participants engaged in a hand/wrist motor imagery protocol or rested quietly (control condition) in a randomized order. Before and after the interventions, single-pulse transcranial magnetic stimulation (TMS) over the motor cortex was used to measure resting motor-evoked potential amplitude of the first dorsal interosseous muscle. Our main finding was that motor imagery acutely increased corticospinal excitability by ~64% (marginal means pre = 784.1 µV, post = 1246.6 µV; p < 0.001, d = 0.487). However, there was no evidence that the increase in corticospinal excitability was influenced by resistance-training experience. We suspect that our results may have been influenced by the specific nature of the motor imagery task. Our findings have important implications for motor imagery prescription and suggest that motor imagery training may be equally beneficial for both resistance-trained and untrained populations. This study was prospectively registered at ClinicalTrials.gov (Identifier: NCT03889548).

Lower limb rehabilitation exoskeleton using brain–computer interface based on multiband filtering with classifier fusion

AbstractIn this study, we propose two adaptive frameworks based on evolutionary algorithms for improving the accuracy of motor imagery (MI) task classification. In an MI task, each participant has a different reaction time delay. In this study, the reaction delay was used as a parameter. Specifically, the time point after the reaction delay was defined as the starting point (SP) when MI began. Various classification and optimization algorithms were employed. The methods include the use of a fixed and dynamic SP for each individual, a genetic algorithm, particle swarm optimization (PSO), spatial filter tuning, the use of common spatial patterns, linear discriminant analysis, bagged decision trees, convolutional neural network (CNN), and long short‐term memory (LSTM). Moreover, a dynamic optimization method for multiband filtering (MBF) method for the subbands of EEG signals was developed that improved accuracy by 5.4%. Combining MBF with bagged decision trees with PSO‐optimized parameters achieved the highest accuracy of 82.3%. Moreover, after optimization by PSO, the CNN‐LSTM method achieved a classification accuracy of 81.4% for 1‐s signals, shorter than those in other studies. The method enables the use of EEG signals to control an exoskeleton for patient rehabilitation.

BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery

Brain–computer interfaces (BCIs) based on motor imagery (MI) enable the disabled to interact with the world through brain signals. To meet demands of real-time, stable, and diverse interactions, it is crucial to develop lightweight networks that can accurately and reliably decode multi-class MI tasks. In this paper, we introduce BrainGridNet, a convolutional neural network (CNN) framework that integrates two intersecting depthwise CNN branches with 3D electroencephalography (EEG) data to decode a five-class MI task. The BrainGridNet attains competitive results in both the time and frequency domains, with superior performance in the frequency domain. As a result, an accuracy of 80.26 percent and a kappa value of 0.753 are achieved by BrainGridNet, surpassing the state-of-the-art (SOTA) model. Additionally, BrainGridNet shows optimal computational efficiency, excels in decoding the most challenging subject, and maintains robust accuracy despite the random loss of 16 electrode signals. Finally, the visualizations demonstrate that BrainGridNet learns discriminative features and identifies critical brain regions and frequency bands corresponding to each MI class. The convergence of BrainGridNet’s strong feature extraction capability, high decoding accuracy, steady decoding efficacy, and low computational costs renders it an appealing choice for facilitating the development of BCIs.

Self-Supervised EEG Representation Learning with Contrastive Predictive Coding for Post-Stroke Patients.

Stroke patients are prone to fatigue during the EEG acquisition procedure, and experiments have high requirements on cognition and physical limitations of subjects. Therefore, how to learn effective feature representation is very important. Deep learning networks have been widely used in motor imagery (MI) based brain-computer interface (BCI). This paper proposes a contrast predictive coding (CPC) framework based on the modified s-transform (MST) to generate MST-CPC feature representations. MST is used to acquire the temporal-frequency feature to improve the decoding performance for MI task recognition. EEG2Image is used to convert multi-channel one-dimensional EEG into two-dimensional EEG topography. High-level feature representations are generated by CPC which consists of an encoder and autoregressive model. Finally, the effectiveness of generated features is verified by the k-means clustering algorithm. It can be found that our model generates features with high efficiency and a good clustering effect. After classification performance evaluation, the average classification accuracy of MI tasks is 89% based on 40 subjects. The proposed method can obtain effective feature representations and improve the performance of MI-BCI systems. By comparing several self-supervised methods on the public dataset, it can be concluded that the MST-CPC model has the highest average accuracy. This is a breakthrough in the combination of self-supervised learning and image processing of EEG signals. It is helpful to provide effective rehabilitation training for stroke patients to promote motor function recovery.

One-Dimensional Convolutional Multi-branch Fusion Network for EEG-Based Motor Imagery Classification

The Brain-Computer Interface (BCI) system based on motor imagery (MI) is a hot research topic nowadays, which can control external devices through the brain and has a wide range of applications in rehabilitation, gaming, and entertainment. Due to the non-smooth, non-linear, and low signal-to-noise ratio of the MI EEG signal, it is challenging to accurately decode the MI task intention. A new end-to-end deep learning method is proposed to decode raw MI EEG signals without preprocessing, such as filtering and feature reinforcement. The 1D convolution is used to learn the time-frequency features in MI signals, and a four-branch fusion network is used as the main body to add a 1D CNN-AE block and 1D SE-block to enhance the algorithm's performance. Experiments on two publicly available datasets demonstrate that our proposed algorithm outperforms the current state-of-the-art methods. It achieves 86.11% and 89.51% on the BCI Competition IV-2a and the BCI Competition IV-2b datasets, respectively, and a 6.9% improvement in the generalizability test. The proposed data enhancement method can effectively alleviate the overfitting of the algorithm and improve the decoding performance. Further analysis shows that 1D convolution can effectively extract the features associated with the MI task.

Diagnosis and Prognosis in Disorders of Consciousness: An Active Paradigm fMRI Study

Diagnoses in patients with disorders of consciousness are prone to misdiagnosis; thus, research has sought approaches to increase reliability, for instance, with functional MRI. By applying a motor imagery task, patients showing covert command following despite the absence of behavioural signs of awareness can be identified as being in a cognitive motor dissociation. This study seeks to determine the proportion of patients, with unresponsive wakefulness syndrome and minimally conscious state, who display covert command following. Moreover, the prognostic value of the improved diagnosis and different methodical approaches to analyse the functional MRI data were evaluated. 73 disorder of consciousness patients (35 unresponsive, 35 minimally conscious, and three already recovered) underwent weekly standardized behavioural assessments with the coma-recovery scale—revised and one functional MRI examination comparing their brain activations in the supplementary motor area between phases of imaging playing tennis and rest. 27 healthy controls served as a control group. The data was evaluated using different region-of-interest analyses (one- and two-tailed small-volume correction and region-of-interest exploration approaches) and a whole-brain analysis. Based on the one-tailed small volume correction data, seven patients, all of nontraumatic aetiology, showed covert command following. The one-tailed region-of-interest exploration identified three additional responders. 10 patients showed significantly more activation during rest than during the imagery paradigm (negative responders). 40% of patients (minimally conscious patients being three times more likely) showed significant activations in the whole brain analysis. Besides, no significant further associations were found between covert command following and clinical parameters. The analyses showed that the tennis paradigm could identify patients with cognitive motor dissociation with a nontraumatic aetiology, but our data failed to show any short-term prognostic validity. The relevance of negative responders and activated regions outside of the region of interest should be further investigated.

Variance characteristic preserving common spatial pattern for motor imagery BCI.

The common spatial patterns (CSP) algorithm is the most popular technique for extracting electroencephalogram (EEG) features in motor imagery based brain-computer interface (BCI) systems. CSP algorithm embeds the dimensionality of multichannel EEG data to extract features of motor imagery tasks. Most previous studies focused on the optimization of the time domain and the spectrum domain of EEG signal to improve the effectiveness of CSP, whereas ignoring the constraint on the projected feature space. This study proposed a variance characteristic preserving CSP (VPCSP) that is modified by a regularization item based on graph theory. Specifically, we calculated the loss of abnormalities of the projected data while preserving the variance characteristic locally. Then the loss could be rewritten as a matrix with the introduction of the Laplace matrix, which turned it into a generalized eigenvalue problem equivalent to CSP. This study evaluated the proposed method on two public EEG datasets from the BCI competition. The modified method could extract robust and distinguishable features that provided higher classification performance. Experimental results showed that the proposed regularization improved the effectiveness of CSP significantly and achieved superior performance compared with reported modified CSP algorithms significantly. The classification accuracy of the proposed method achieved 87.88 %, 90.07 %, and 76.06 % on public dataset IV part I, III part IVa and the self-collected dataset, respectively. Comparative experiments are conducted on two public datasets and one self-collected dataset. Results showed that the proposed method outperformed the reported algorithm. The proposed method can extract robust features to increase the performance of BCI systems. And the proposal still has expandability. These results show that our proposal is a promising candidate for the performance improvement of MI-BCI.

Hybrid optimization assisted channel selection of EEG for deep learning model-based classification of motor imagery task.

To design and develop an approach named HC+SMA-SSA scheme for classifying motor imagery task. The offered model employs a new method for classifying motor imagery task. Initially, down sampling is deployed to pre-process the incoming signal. Subsequently, "Modified Stockwell Transform (ST) and common spatial pattern (CSP) based features are extracted". Then, optimal channel selection is made by a novel hybrid optimization model named as Spider Monkey Assisted SSA (SMA-SSA). Here, "Long Short Term Memory (LSTM) and Bidirectional Gated Recurrent Unit (BI-GRU)" models are used for final classification, whose outcomes are averaged at the end. At last, the improvement of SMA-SSA based model is proven over different metrics. A superior sensitivity of 0.939 is noted for HC+SMA-SSA that was higher over HC with no optimization and proposed with traditional ST. The proposed method achieved effective classification performance in terms of performance measures.

Motor Imagery EEG Classification Based on a Weighted Multi-branch Structure Suitable for Multisubject Data.

Electroencephalogram (EEG) signal recognition based on deep learning technology requires the support of sufficient data. However, training data scarcity usually occurs in subject-specific motor imagery tasks unless multisubject data can be used to enlarge training data. Unfortunately, because of the large discrepancies between data distributions from different subjects, model performance could only be improved marginally or even worsened by simply training on multisubject data. This paper proposes a novel weighted multi-branch (WMB) structure for handling multisubject data to solve the problem, in which each branch is responsible for fitting a pair of source-target subject data and adaptive weights are used to integrate all branches or select branches with the largest weights to make the final decision. The proposed WMB structure was applied to six well-known deep learning models (EEGNet, Shallow ConvNet, Deep ConvNet, ResNet, MSFBCNN, and EEG_TCNet) and comprehensive experiments were conducted on EEG datasets BCICIV-2a, BCICIV-2b, high gamma dataset (HGD) and two supplementary datasets. Superior results against the state-of-the-art models have demonstrated the efficacy of the proposed method in subject-specific motor imagery EEG classification. For example, the proposed WMB_EEGNet achieved classification accuracies of 84.14%, 90.23%, and 97.81% on BCICIV-2a, BCICIV-2b and HGD, respectively. It is clear that the proposed WMB structure is capable to make good use of multisubject data with large distribution discrepancies for subject-specific EEG classification.

49 Cerebral hemodynamic during motor imagery of self-feeding with chopsticks: Differences between dominant and nondominant hand

Objective:Motor imagery is defined as a dynamic state during which a subject mentally simulates a given action without overt movements. Our aim was to use near-infrared spectroscopy to investigate differences in cerebral hemodynamic during motor imagery of self-feeding with chopsticks using the dominant or non-dominant hand.Participants and Methods:Twenty healthy right-handed people participated in this study. The motor imagery task involved eating sliced cucumber pickles using chopsticks with the dominant (right) or non-dominant (left) hand. Activation of regions of interest (pre-supplementary motor area, supplementary motor area, pre-motor area, pre-frontal cortex, and sensorimotor cortex was assessed.Results:Motor imagery vividness of the dominant hand tended to be significantly higher than that of the non-dominant hand. The time of peak oxygenated hemoglobin was significantly earlier in the right pre-frontal cortex than in the supplementary motor area and left pre-motor area. Hemodynamic correlations were detected in more regions of interest during dominant-hand motor imagery than during non-dominant-hand motor imagery.Conclusions:Hemodynamic might be affected by differences in motor imagery vividness caused by variations in motor manipulation.

A novel approach of decoding four-class motor imagery tasks via wavelet transform and 1DCNN-BiLSTM

A novel approach of decoding four-class motor imagery tasks via wavelet transform and 1DCNN-BiLSTM

Recognition of motor intentions from EEGs of the same upper limb by signal traceability and Riemannian geometry features.

The electroencephalographic (EEG) based on the motor imagery task is derived from the physiological electrical signal caused by the autonomous activity of the brain. Its weak potential difference changes make it easy to be overwhelmed by noise, and the EEG acquisition method has a natural limitation of low spatial resolution. These have brought significant obstacles to high-precision recognition, especially the recognition of the motion intention of the same upper limb. This research proposes a method that combines signal traceability and Riemannian geometric features to identify six motor intentions of the same upper limb, including grasping/holding of the palm, flexion/extension of the elbow, and abduction/adduction of the shoulder. First, the EEG data of electrodes irrelevant to the task were screened out by low-resolution brain electromagnetic tomography. Subsequently, tangential spatial features are extracted by the Riemannian geometry framework in the covariance matrix estimated from the reconstructed EEG signals. The learned Riemannian geometric features are used for pattern recognition by a support vector machine with a linear kernel function. The average accuracy of the six classifications on the data set of 15 participants is 22.47%, the accuracy is 19.34% without signal traceability, the accuracy is 18.07% when the features are the filter bank common spatial pattern (FBCSP), and the accuracy is 16.7% without signal traceability and characterized by FBCSP. The results show that the proposed method can significantly improve the accuracy of intent recognition. In addressing the issue of temporal variability in EEG data for active Brain-Machine Interfaces, our method achieved an average standard deviation of 2.98 through model transfer on different days' data.

More implicit and more explicit motor imagery tasks for exploring the mental representation of hands and feet in action.

The mental representation of the body in action can be explored using motor imagery (MI) tasks. MI tasks can be allocated along a continuum going from more implicit to more explicit tasks, where the discriminant is the degree of action monitoring required to solve the tasks (which is the awareness of using the mental representation of our own body to monitor our motor imagery). Tasks based on laterality judgments, such as the Hand Laterality Task (HLT) and the Foot Laterality Task (FLT), provide an example of more implicit tasks (i.e., less action monitoring is required). While, an example of a more explicit task is the Mental Motor Chronometry task (MMC) for hands and feet, where individuals are asked to perform or imagine performing movements with their limbs (i.e., more action monitoring is required). In our study, we directly compared hands and feet at all these tasks for the first time, as these body districts have different physical features as well as functions. Fifty-five participants were asked to complete an online version of the HLT and FLT (more implicit measure), and an online version of the MMC task for hands and feet (more explicit measure). The mental representation of hands and feet in action differed only when the degree of action monitoring decreased (HLT ≠ FLT); we observed the presence of biomechanical constraints only for hands. Differently, when the degree of action monitoring increased hands and feet did not show any difference (MMC hands = MMC feet). Our results show the presence of a difference in the mental representation of hands and feet in action that specifically depends on the degree of action monitoring.

Effects of visual-electrotactile stimulation feedback on brain functional connectivity during motor imagery practice

The use of neurofeedback is an important aspect of effective motor rehabilitation as it offers real-time sensory information to promote neuroplasticity. However, there is still limited knowledge about how the brain’s functional networks reorganize in response to such feedback. To address this gap, this study investigates the reorganization of the brain network during motor imagery tasks when subject to visual stimulation or visual-electrotactile stimulation feedback. This study can provide healthcare professionals with a deeper understanding of the changes in the brain network and help develop successful treatment approaches for brain–computer interface-based motor rehabilitation applications. We examine individual edges, nodes, and the entire network, and use the minimum spanning tree algorithm to construct a brain network representation using a functional connectivity matrix. Furthermore, graph analysis is used to detect significant features in the brain network that might arise in response to the feedback. Additionally, we investigate the power distribution of brain activation patterns using power spectral analysis and evaluate the motor imagery performance based on the classification accuracy. The results showed that the visual and visual-electrotactile stimulation feedback induced subject-specific changes in brain activation patterns and network reorganization in the alpha band. Thus, the visual-electrotactile stimulation feedback significantly improved the integration of information flow between brain regions associated with motor-related commands and higher-level cognitive functions, while reducing cognitive workload in the sensory areas of the brain and promoting positive emotions. Despite these promising results, neither neurofeedback modality resulted in a significant improvement in classification accuracy, compared with the absence of feedback. These findings indicate that multimodal neurofeedback can modulate imagery-mediated rehabilitation by enhancing motor-cognitive communication and reducing cognitive effort. In future interventions, incorporating this technique to ease cognitive demands for participants could be crucial for maintaining their motivation to engage in rehabilitation.