Search Results (8)

Background: The decoding of motor imagery electroencephalography (MI-EEG) is constrained by core issues including low signal-to-noise ratio (SNR) and cross-session as well as cross-subject domain shift, which seriously impedes the practical deployment of brain–computer interfaces (BCIs). Methods: To address these challenges, this paper proposes a novel end-to-end MI-EEG decoding method named BARN-DA. Two innovative modules, Band-Aware Channel Attention (BACA) and Multi-Scale Kernel Perception (MSKP), are designed: one enhances discriminative channel features by modeling channel information fused with frequency band feature representation, and the other captures complex data correlations via multi-scale parallel convolutions to improve the discriminability of the network’s feature extraction. Subsequently, the features are mapped onto the Riemannian manifold. For the source and target domain features residing on this manifold, a Riemannian Maximum Mean Discrepancy (R-MMD) loss is designed based on the log-Euclidean metric. This approach enables the effective embedding of Symmetric Positive Definite (SPD) matrices into the Reproducing Kernel Hilbert Space (RKHS), thereby reducing cross-domain discrepancies. Results: Experimental results on four public datasets demonstrate that the BARN-DA method achieves average cross-session classification accuracies of 84.65% ± 8.97% (BCIC IV 2a), 89.19% ± 7.69% (BCIC IV 2b), and 61.76% ± 12.68% (SHU), as well as average cross-subject classification accuracies of 65.49% ± 11.64% (BCIC IV 2a), 78.78% ± 8.44% (BCIC IV 2b), and 78.14% ± 14.41% (BCIC III 4a). Compared with state-of-the-art methods, BARN-DA obtains higher classification accuracy and stronger cross-session and cross-subject generalization ability. Conclusions: These results confirm that BARN-DA effectively alleviates low SNR and domain shift problems in MI-EEG decoding, providing an efficient technical solution for practical BCI systems. Full article

Motor imagery signal decoding is an important research direction in the field of brain–computer interfaces, which aim to judge the motor imagery state of an individual by analyzing electroencephalogram (EEG) signals. Deep learning technology has been gradually applied to EEG classification, which can automatically extract features. However, when processing complex EEG signals, the existing decoding models cannot effectively fuse features at different levels, resulting in limited classification performance. This study proposes a multi-scale spatiotemporal efficient feature fusion network (MS-TSEFNet), which learns the dynamic changes in EEG signals at different time scales through multi-scale convolution modules and combines the spatial attention mechanism to efficiently capture the spatial correlation between electrodes in EEG signals. In addition, the network adopts an efficient feature fusion strategy to deeply fuse features at different levels, thereby improving the expression ability of the model. In the task of motor imagery signal decoding, MS-TSEFNet shows higher accuracy and robustness. We use the public BCIC-IV2a, BCIC-IV2b and ECUST datasets for evaluation. The experimental results show that the average classification accuracy of MS-TSEFNet reaches 80.31%, 86.69% and 71.14%, respectively, which is better than the current state-of-the-art algorithms. We conducted an ablation experiment to further verify the effectiveness of the model. The experimental results showed that each module played an important role in improving the final performance. In particular, the combination of the multi-scale convolution module and the feature fusion module significantly improved the model’s ability to extract the spatiotemporal features of EEG signals. Full article

Transformer-based models have accelerated EEG motor imagery (MI) decoding by using self-attention to capture long-range temporal structures while complementing spatial inductive biases. This systematic survey of Scopus-indexed works from 2020 to 2025 indicates that reported advances are concentrated in offline, protocol-heterogeneous settings; inconsistent preprocessing, non-standard data splits, and sparse efficiency frequently reporting cloud claims of generalization and real-time suitability. Under session- and subject-aware evaluation on the BCIC IV 2a/2b dataset, typical performance clusters are in the high-80% range for binary MI and the mid-70% range for multi-class tasks with gains of roughly 5–10 percentage points achieved by strong hybrids (CNN/TCN–Transformer; hierarchical attention) rather than by extreme figures often driven by leakage-prone protocols. In parallel, transformer-driven denoising—particularly diffusion–transformer hybrids—yields strong signal-level metrics but remains weakly linked to task benefit; denoise → decode validation is rarely standardized despite being the most relevant proxy when artifact-free ground truth is unavailable. Three priorities emerge for translation: protocol discipline (fixed train/test partitions, transparent preprocessing, mandatory reporting of parameters, FLOPs, per-trial latency, and acquisition-to-feedback delay); task relevance (shared denoise → decode benchmarks for MI and related paradigms); and adaptivity at scale (self-supervised pretraining on heterogeneous EEG corpora and resource-aware co-optimization of preprocessing and hybrid transformer topologies). Evidence from subject-adjusting evolutionary pipelines that jointly tune preprocessing, attention depth, and CNN–Transformer fusion demonstrates reproducible inter-subject gains over established baselines under controlled protocols. Implementing these practices positions transformer-driven BCIs to move beyond inflated offline estimates toward reliable, real-time neurointerfaces with concrete clinical and assistive relevance. Full article

Stroke is a neurological condition that often results in long-term motor deficits. Given the high prevalence of motor impairments worldwide, there is a critical need to explore innovative neurorehabilitation strategies that aim to enhance the quality of life of patients. One promising approach involves brain–computer interface (BCI) systems controlled by electroencephalographic (EEG) signals elicited when a subject performs motor imagery (MI), which is the mental simulation of movement without actual execution. Such systems have shown potential for facilitating motor recovery by promoting neuroplastic mechanisms. Controlling BCI systems based on MI-EEG signals involves the following sequential stages: recording the raw signal, preprocessing, feature extraction and selection, and classification. Each of these stages can be executed using several techniques and numerous parameter combinations. In this study, we searched for the combination of feature extraction technique, time window, frequency range, and classifier that could provide the best classification accuracy for the BCI Competition 2008 IV 2a benchmark dataset (BCI-C), characterized by EEG-MI data of different limbs (four classes, of which three were used in this work), and the NeuroSCP EEG-MI dataset, a custom experimental protocol developed in our laboratory, consisting of EEG recordings of different movements with the same limb (three classes—right dominant arm). The mean classification accuracy for BCI-C was 76%. When the subjects were evaluated individually, the best-case classification accuracy was 94% and the worst case was 54%. For the NeuroSCP dataset, the average classification result was 53%. The individual subject’s evaluation best-case was 71% and the worst case was 35%, which is close to the chance level (33%). These results indicate that techniques commonly applied to classify different limb MI based on EEG features cannot perform well when classifying different MI tasks with the same limb. Therefore, we propose other techniques, such as EEG functional connectivity, as a feature that could be tested in future works to classify different MI tasks of the same limb. Full article

Brain–computer interfaces, where motor imagery electroencephalography (EEG) signals are transformed into control commands, offer a promising solution for enhancing the standard of living for disabled individuals. However, the performance of EEG classification has been limited in most studies due to a lack of attention to the complementary information inherent at different temporal scales. Additionally, significant inter-subject variability in sensitivity to biological motion poses another critical challenge in achieving accurate EEG classification in a subject-dependent manner. To address these challenges, we propose a novel machine learning framework combining multi-scale feature fusion, which captures global and local spatial information from different-sized EEG segmentations, and adaptive Lasso-based feature selection, a mechanism for adaptively retaining informative subject-dependent features and discarding irrelevant ones. Experimental results on multiple public benchmark datasets revealed substantial improvements in EEG classification, achieving rates of 81.36%, 75.90%, and 68.30% for the BCIC-IV-2a, SMR-BCI, and OpenBMI datasets, respectively. These results not only surpassed existing methodologies but also underscored the effectiveness of our approach in overcoming specific challenges in EEG classification. Ablation studies further confirmed the efficacy of both the multi-scale feature analysis and adaptive selection mechanisms. This framework marks a significant advancement in the decoding of motor imagery EEG signals, positioning it for practical applications in real-world BCIs. Full article

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain–computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding. Full article

Breast cancer is considered one of the deadliest diseases in women. Due to the risk and threat it poses, the world has agreed to hold a breast cancer awareness day in October, encouraging women to perform mammogram inspections. This inspection may prevent breast-cancer-related deaths or reduce the death rate. The identification and classification of breast cancer are challenging tasks. The most commonly known procedure of breast cancer detection is performed by using mammographic images. Recently implemented algorithms suffer from generating accuracy below expectations, and their computational complexity is high. To resolve these issues, this paper proposes a fully automated biomedical diagnosis system of breast cancer using an AlexNet, a type of Convolutional Neural Network (CNN), and multiple classifiers to identify and classify breast cancer. This system utilizes a neuro-fuzzy method, a segmentation algorithm, and various classifiers to reach a higher accuracy than other systems have achieved. Numerous features are extracted to detect and categorize breast cancer. Three datasets from Kaggle were tested to validate the proposed system. The performance evaluation is performed with quantitative and qualitative accuracy, precision, recall, specificity, and F-score. In addition, a comparative assessment is performed between the proposed system and some works of literature. This assessment shows that the presented algorithm provides better classification results and outperforms other systems in all parameters. Its average accuracy is over 98.6%, while other metrics are more than 98%. This research indicates that this approach can be applied to assist doctors in diagnosing breast cancer correctly. Full article

There is accumulating evidence that breast cancer may arise from mutated mammary stem/progenitor cells which have been termed breast cancer-initiating cells (BCIC). BCIC identified in clinical specimens based on membrane phenotype (CD44⁺/CD24^−/low and/or CD133⁺ expression) or enzymatic activity of aldehyde dehydrogenase 1 (ALDH1⁺), have been demonstrated to have stem/progenitor cell properties, and are tumorigenic when injected in immunocompromized mice at very low concentrations. BCIC have also been isolated and in vitro propagated as non-adherent spheres of undifferentiated cells, and stem cell patterns have been recognized even in cancer cell lines. Recent findings indicate that aberrant regulation of self renewal is central to cancer stem cell biology. Alterations in genes involved in self-renewal pathways, such as Wnt, Notch, sonic hedgehog, PTEN and BMI, proved to play a role in breast cancer progression. Hence, targeting key elements mediating the self renewal of BCIC represents an attractive option, with a solid rationale, clearly identifiable molecular targets, and adequate knowledge of the involved pathways. Possible concerns are related to the poor knowledge of tolerance and efficacy of inhibiting self-renewal mechanisms, because the latter are key pathways for a variety of biological functions and it is unknown whether their interference would kill BCIC or simply temporarily stop them. Thus, efforts to develop BCIC-targeted therapies should not only be focused on interfering on self-renewal, but could seek to identify additional molecular targets, like those involved in regulating EMT-related pathways, in reversing the MDR phenotype, in inducing differentiation and controlling cell survival pathways. Full article