搜索结果：IEEE journal of biomedical and health informatics

Focal Cortical Dysplasia (FCD) is a major cause of drug-resistant epilepsy both in children and adults. In most such cases, surgery is the most effective treatment unless other treatments, such as rehabilitation, are the most effective intervention; hence, it is important to have the correct identification of FCD in order to make a clinical decision. Magnetic resonance imaging (MRI) is a common technique of imaging FCD because it is painless and offers good resolution images. Nevertheless, MRI is still a big challenge in detecting the lesions of FCD. The lesions are diverse in size and shape, and their location andimagingfeatures are usually subtle and atypical. Therefore, the process of manual identification is not only time consuming but also very much relies on the knowledge of the epileptologist, which brings inconsistency in diagnosis. To overcome these difficulties, this research is de voted to the automated detection of FCD lesions (i.e., FCD type-II) with the help of the state-of-the-art deep-learning methods. An automatic slice selection architecture based on Gumbel-softmax hard thresholding is proposed, which selects the top k important slices in a 3D MRI volume. The selected slices are then passed to Efficient Channel Attention (ECA) enhanced pre-trained Convolutional Neural Networks(CNNs) of DenseNet201, VGG16 and VGG19. The proposed method can detect the changes in healthy brain tissue, FCD-II lesions and T1w features by comparing FCD II lesions and T1w features with healthy brain tissue us ing FCD-II, T1-weighted (T1w) and FLAIR MRI sequences. Amongthese models, ECA-DenseNet201 demonstrated the best performance in classification, achieving high accuracy (96.7% for FLAIR and 96.8% for T1w), precision (0.972 for FLAIR and 0.957 for T1W), and F1-score (0.953 for FLAIR and 0.967 for T1W) in distinguishing FCD-II slices from healthy brain slices.

Multidomain and multimodal identification of the walking gait-cycle states is important for detecting and monitoring locomotion disorders such as Parkinson's disease (PD). We propose a novel multizonal clustering and multi-level thresholding method based on analyzing multizonal plantar load distribution for generating a discrete gait-state time-interval (GSTI) signal to improve PD diagnosis accuracy and the effectiveness of rehabilitation through personalized strategies. Multidomain analysis of the GSTI signal shows a novel coupled I.Baryskievic-H.Li bio-oscillator interpreted as a GSTI-derived signal-level oscillatory signature that may be associated with a central nervous system (CNS)-related locomotor rhythm organization. The bio-oscillator consists of two interconnected oscillations with distinct resonant spectral peaks at specific natural frequencies and phase coupling (nonlinearity) between two frequency components. We propose a multidomain feature level of layered Integrative Body Intelligence (IBI) framework to identify lower and higher-order interactions between gait cycle states. The proposed multimodal data level of IBI involves the proposed acoustic and visual biofeedback based on a novel acoustic harmonic plantar pressure model and a 3D gait state portrait of the GSTI signal used for walking gait monitoring and personalized rehabilitation assessment in PD. Experiments on a publicly available PD plantar-insole dataset show that the Multilayer Perceptron (MLP) model based on the selected multidomain (time-interval, spectral, and bispectral) feature subset achieves classification accuracy (94.44%), and offers a trade-off between model complexity and performance for PD recognition. This result suggests that it is possible to accurately diagnose early-stage PD through merely testing patients' GSTI signal.

Brain-Computer Interface (BCI) technology holds great promise for enhancing human health and quality of life, with visual stimulus reconstruction from EEG signals being a key application. However, the complexity and noise of EEG data challenge existing reconstruction methods. To address these issues, we propose NeuroDecoder, an end-to-end multimodal guidance generation framework that produces high-quality images from EEG signals. The key innovation is the collaborative mitigation of EEG noise and cross-modal representation discrepancies through a noise-robust encoder, mask-based triple-contrastive alignment, and a fixed generative model. Specifically, NeuroDecoder consists of three integrated learning stages: 1) EEG Decoding, 2) Modality Alignment, and 3) Image Reconstruction. In the decoding stage, a novel visual decoding model extracts visually relevant features with superior classification accuracy. In the alignment stage, a mask-based triple contrastive learning strategy achieves efficient cross-modal alignment of EEG, text, image, and edge map embeddings into a unified space. In the generation stage, a new reconstruction pipeline feeds the aligned EEG embeddings into a pre-trained stable diffusion model, enabling high-quality visual stimulus reconstruction with enhanced semantic and structural fidelity, without fine-tuning the generative model. On three EEG datasets, NeuroDecoder achieved subject-dependent classification accuracies of 99.76%, 94.41%, and 56.67%, respectively; in the subject-independent setting, it performed near random on EEGCVPR40 but reached 91.61% and 37.63% on the other two. For image reconstruction, it obtained Fréchet Inception Distance of 62.84 and 63.12 on the first two datasets. Extensive experiments demonstrate that NeuroDecoder outperforms prior methods in both EEG classification accuracy and image reconstruction quality.

Brain fog has raised significant public health concerns as a common neurocognitive impairment in the post-COVID-19 condition, involving memory loss, poor concentration, and language difficulties. However, their neural mechanisms remain unclear, and objective resting-state fMRI-based diagnostic tools are still lacking. To address these challenges, we first recruited 72 patients who experienced persistent brain fog symptoms following COVID-19 infection, along with 68 post-COVID participants without brain fog (PC-noBF), and collected resting-state functional magnetic resonance imaging (rs-fMRI) data from all participants. The interpretable graph neural network model BrainGNN was employed to model and classify individual brain networks, utilizing functional connectivity graphs constructed from the Automated Anatomical Labeling (AAL) atlas. Using out-of-fold predictions from 5-fold cross-validation, BrainGNN achieved an accuracy of 75.71% (Bootstrap 95% CI: 68.57%-82.86%) and an area under the ROC curve (AUC) of 76.07% (Bootstrap 95% CI: 73.93%-88.48%). Furthermore, on an independent test set, BrainGNN outperformed traditional machine learning methods and other GNN models, achieving an accuracy of 82.14% and an AUC of 82.82% (classification threshold: 0.5). Moreover, the model identified several key brain regions-bilateral insula, bilateral Heschl's gyri, and the left superior temporal gyrus-as potential neurobiological markers. Notably, in post-hoc analyses, the ALFF and ReHo values of the left insula were significantly associated with scores related to language and memory symptoms. These findings collectively underscore the effectiveness and interpretability of the proposed approach in identifying functional markers of brain fog. This study not only demonstrates the potential of individual-level identification of brain fog using resting-state fMRI empowered by interpretable GNN, but also reveals its capacity to provide novel insights into the neurobiological mechanisms underlying COVID-19-related cognitive impairment.

B-lines are artifacts produced by the interaction of the ultrasound with the small air-liquid interface, which often serve as crucial biomarkers for evaluating lung pathology, such as the presence of liquid. However, due to the reverberation phenomenon, B-lines manifest as blurred, strip-like comet tails perpendicularly originating from the pleural line, making their automatic identification in speckle-noisy ultrasound images particularly challenging. This study proposes a Hough-based structure-aware detection framework, dubbed HSD, which leverages structural priors and the intrinsic relationship between the pleural line and B-lines to enhance B-line detection in ultrasound images. First, the proposed method adopts the shared encoder and two collaborative decoders to improve B-lines identification with the auxiliary pleural line detection, ensuring effective representation learning of linear structural features under inherent prior constraints. Specifically, one decoder incorporates Hough-based regression to reinforce the modeling of the global linear nature for B-line detection, alleviating the appearance influences of the fuzzy comet-tail. Simultaneously, another pathway enhances the exploration of the slender, curved morphology by integrating semantic context learning with linear heatmap regression, thereby facilitating the detection of the pleural line for calibration of B-lines. Second, we introduce a position-aware rectification module to ensure the consistency of the pleural line and its perpendicular alignment with B-lines. This post-processing module reduces the influence of ambiguous pixels, improving the robustness of B-line detection. Extensive experimental results on an in-house ultrasound dataset demonstrate the superiority of the proposed approach, which achieves a precision of 0.743, a recall of 0.953, and an F-measure of 0.837, substantially ahead of other methods, suggesting its potential for detecting pathological indicators in lung ultrasound.

Phonocardiogram (PCG) has increasingly been applied to out-of-hospital monitoring and home health management. Among these, Bone-Conduction PCG (BCPCG) has emerged as a promising solution for long-term wearable cardiac sound monitoring due to its superior noise resistance and privacy protection. However, its acquisition is susceptible to variations in textile thickness and contact pressure, exacerbating instability in critical event detection. To systematically evaluate these influencing mechanisms, this study quantifies the impact of varying textile thickness (0-5.92 mm) and pressure (0-15 N) combinations on BCPCG. First, an equivalent mass-damping-spring model was employed to assess the transmission dynamics qualitatively. Subsequently, rigorous experiments were designed to collect signals and compare key features, including S1/S2 localization accuracy, pseudo signal-to-noise ratio (PSNR), and spectral centroid (SC). The results demonstrate that BCPCG signals remain relatively stable within the 0-2 N range, exhibit slight degradation between 3-5 N, and experience a marked decline under high pressure (10-15 N), where the PSNR drops by nearly 50% and S1 localization accuracy decreases to 70.27%. This may stem from tissue tremors and amplified high-frequency noise under high pressure. Meanwhile, textile thickness at low pressures primarily affects high-frequency components without significantly impacting localization accuracy. Finally, a classification model based on Top-11 features identified contact pressure intervals (0-2 N, 3-5 N, 10-15 N), and the macro-averaged AUC reached 0.985. This study validates the feasibility of pressure-inverse inference using BCPCG features, providing theoretical and practical foundations for real-world applications.

Consumer health devices generate massive volumes of sensitive medical data requiring secure authentication mechanisms that accommodate the resource constraints of wearable sensors and portable diagnostic equipment. Traditional centralized authentication approaches in Internet of Medical Things (IoMT) environments suffer from single points of failure, privacy vulnerabilities, and scalability limitations when managing diverse health monitoring devices. This paper presents secure healthcare IoMT enhanced lightweight device authentication (SHIELD), a blockchain-based lightweight authentication framework designed for resource-constrained consumer health devices. The framework leverages blockchain's immutable and decentralized properties, combined with efficient elliptic curve cryptography, to ensure secure storage and verification of device identities while providing mutual authentication between health devices and medical data servers. Security analysis demonstrates that SHIELD satisfies twelve critical security properties, including decentralization, resistance to password guessing and replay attacks, perfect forward secrecy, and session key security. Performance evaluation reveals that SHIELD achieves computational efficiency at 9.837 milliseconds authentication latency, representing 31% improvement over previous best-performing schemes. The framework requires only 1384 bits of communication overhead and maintains minimal average delay times suitable for real-time health monitoring applications. Blockchain implementation analysis confirms practical deployment feasibility with 0.0356 MGas operational costs per authentication session.

The diagnosis of Sleep Apnea-Hypopnea Syndrome (SAHS) holds significant importance for assessing sleep quality and treating sleep disorders. However, the detection of hypopnea events has not been given due emphasis, and the precise delineation of event boundaries is not straightforward. In this work, we introduce a novel deep learning model for the precise detection of obstructive sleep apnea and hypopnea events. Respiration-related signals, processed through a sliding window, serve as inputs to the model. Initially, multi-scale features are extracted using the Dilated Pyramid Convolution module, followed by an adaptive refinement of these features using the Frequency Enhanced Attention module. Finally, the Contextual Representation Learning module captures the temporal dependencies within the features. The model was validated on two public datasets and one local dataset, achieving an accuracy of 84.4%, a precision of 66.3%, a recall of 84.5%, and an F1 score of 72.3% on the SHHS2 dataset. We have achieved an automatic detection of both obstructive sleep apnea and hypopnea events with a granularity of one second. Our method offers certain advantages over other approaches, with the potential to assist in clinical diagnosis and to enable home-based respiratory monitoring.

Freezing of gait (FOG), a debilitating symptom of Parkinson's disease, can manifest in three sub-types: shuffling, trembling, and akinesia, with occurrence and frequency varying across patients. While deep learning (DL) models show promise in FOG detection, their robustness and generalization across subtypes are limited by data scarcity and imbalances between FOG/non-FOG classes and among subtypes. To address this, we propose a subtype-aware FOG augmentation technique enabling training of DL models to perform consistently across subtypes. Specifically, we introduce Hierarchical Coarse-to-Fine conditional Generative Adversary Network (Hi-CF cGAN), a two-stage model that generates subtype-conditioned FOG-like ankle accelerations that are realistic and diverse, as verified through visualization, UMAPs, and Maximum Mean Discrepancy comparison against real signals. We evaluate its effective-ness by training CNNs for FOG detection with both general (subtype-stratified) and personalized (subtype-variant, based on patient-specific subtype composition) augmentation via Hi-CF cGAN, benchmarking against classical augmentations and baseline (no augmentation). Compared to baseline, general augmentation with Hi-CF cGAN effectively improves average detection rates of FOG, trembling FOG, and especially the previously overlooked minor subtypes, shuffling FOG (from 66.8% to 81.6%) and akinesia FOG (from 58.7% to 77.9%). These improvements exceed those of classical augmentations, demonstrating superior real-ism, richness, and adaptability of Hi-CF cGAN-generated data in addressing FOG/non-FOG and subtype imbalances. Personalized augmentation further enhances accuracy on targeted subtype(s) compared to general augmentation, highlighting its potential for tailored model optimization.

Diagnosis and prognosis of lung cancer via PET/CT imaging have long been major clinical concerns. However, existing multimodal approaches often focus on feature aggregation rather than cross-modal interactive collaboration, failing to capture the structural-metabolic correlations and multi-scale synergy essential for characterizing complex lesions. Therefore, this study proposes TriFuse-Net, a tri-branch PET/CT fusion pyramid network (FPN) enhanced by lesion-guided structural-metabolic attention (LSMA) to improve both diagnosis and prognosis prediction tasks. The model is composed of two identical unimodal branches (PET/CT) and one pyramid branch with an interacting channel and spatial attention. The pyramid structure enables bidirectional multiscale feature extraction and fusion, capturing both local details and global semantic information of lesions. Comprehensive experiments validated the model's superiority across three clinical tasks. TriFuse-Net achieved a C-index of 0.747 for progression-free survival (PFS) prediction, showing improvements of 14.7% and 11.0% over ResNet-CT and ResNet-PET, respectively. Additionally, the clinical-integrated model (TriFuse-Net-Cli) achieved AUCs of 0.947 for differentiating lung cancer from tuberculosis and 0.937 for identifying lymph-node metastasis. Ablation studies further confirmed the essential contributions of both FPN and LSMA. In summary, the proposed framework demonstrates that integrating multi-scale structural-metabolic relationships significantly enhances diagnosis and prognosis in lung cancer.

Instant messaging applications are an integral part of everyday life, facilitating communication in various settings, including work and healthcare. This systematic review aims to analyze the healthcare contexts in which these applications are most commonly used (i.e., work organization, education, communication among healthcare personnel, communication with patients), with a particular focus on privacy issues raised by the handling of sensitive data on these platforms and how, or if, these issues are addressed. Following a systematic literature review process conducted according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, the articles were examined with the goal of extracting the aforementioned information. The results reveal that the majority of studies (82.6%) adopt commercial solutions to improve communication in medical field, with most of them using WhatsApp as the primary communication channel. Although the studies acknowledge the privacy risks introduced by these applications, the description of how such risks are mitigated or addressed is rarely reported in detail; what is consistently highlighted instead is the practical lack of clarity in existing regulations about the pratical applicability.

Optimizing automated sepsis treatment policies using Reinforcement Learning (RL) has gained attention for improving quality of medical care and address physician shortages. However, in an offline setting, an RL agent cannot explore all possible treatment episodes, leading to an overestimation of Q-values for unexplored treatments. This causes a significant deviation from the physician's policy and results in the RL policy converging to a suboptimal policy. To address this problem, we propose Dyna-Based Discriminative Reinforcement Learning (DDRL), which aims to learn an optimal treatment policy that aligns with physician treatment policy. Our method utilizes both Electronic Medical Record (EMR) data and simulated treatment episodes to mitigate the limitations of restricted treatment exploration. Additionally, by leveraging a Discriminator, we suppress the Q-values of out-of-distribution treatments, preventing overestimation and reducing deviation from the physician treatment policies. The method was evaluated using data from Ajou University Hospital and Asan Medical Center. The expected return of the DDRL policy was 7.29 for Asan Medical Center and 4.55 for Ajou University Hospital, outperforming the Conservative Q-Learning (CQL) method by 3.4% and 5.6%, and surpassing the physician's policy by 18.7% and 8.3% respectively. The cosine similarity between DDRL and physician policies was 81.68% for Asan Medical Center and 90.90% for Ajou University Hospital, which is 0.73% and 26.11% higher, respectively, than the CQL method.

Accurate prediction of protein-ligand interactions is essential for drug discovery, supporting critical stages from lead optimization to therapeutic development. Many existing methods depend on high-resolution protein-ligand complex structures, which limits scalability and reduces robustness in structure-limited settings. To address these challenges, we introduce Multi-Combinatorial Knowledge Distillation (MCKD), a sequence-based framework that predicts protein-ligand interactions without requiring explicit three-dimensional structures at inference time. MCKD represents proteins and ligands as two-dimensional molecular graphs derived from their sequences and physicochemical properties, enabling effective learning from readily available inputs. To incorporate structural knowledge beyond sequence information, MCKD employs a hybrid distillation strategy that combines cross-modal distillation from a structure-based teacher with self-distillation to improve representation consistency across layers. To model protein-ligand interactions explicitly, MCKD integrates a bilinear attention network that captures residue-atom level associations and supports both binding affinity regression and binary interaction classification. Evaluations on multiple public benchmark datasets show that MCKD consistently outperforms existing sequence-based methods and achieves performance comparable to structure-based approaches. The model also generalizes well to unseen proteins and novel ligand scaffolds, while providing interpretable insights into key molecular interaction regions. These results suggest that MCKD offers a scalable and effective solution for protein-ligand interaction prediction, particularly for structure-free and data-limited drug discovery applications.

Investigating the public experience of urgent care facilities is essential for promoting community healthcare development. Traditional survey methods often fall short due to limited scope, time, and spatial coverage. Crowdsourcing through online reviews or social media offers a valuable approach to gaining such insights. With recent advancements in large language models (LLMs), extracting nuanced perceptions from reviews has become feasible. This study collects Google Maps reviews across the DMV and Florida areas and conducts prompt engineering with the GPT model to analyze the aspect-based sentiment of urgent care. We first analyze the geospatial patterns of various aspects, including interpersonal factors, operational efficiency, technical quality, finances, and facilities. Next, we determine Census Block Group (CBG)-level characteristics underpinning differences in public perception, including population density, median income, GINI Index, rent-to-income ratio, household below poverty rate, no insurance rate, and unemployment rate. Our results show that interpersonal factors and operational efficiency emerge as the strongest determinants of patient satisfaction in urgent care, while technical quality, finances, and facilities show no significant independent effects when adjusted for in multivariate models. Among socioeconomic and demographic factors, only population density demonstrates a significant but modest association with patient ratings, while the remaining factors exhibit no significant correlations. Overall, this study highlights the potential of crowdsourcing to uncover the key factors that matter to residents and provide valuable insights for stakeholders to improve public satisfaction with urgent care.

Electrocardiography (ECG) is a fundamental tool for diagnosing cardiovascular diseases, yet the scarcity of large-scale annotated data limits the applicability of supervised learning approaches. While self-supervised learning (SSL) has shown promise for ECG representation learning, existing methods often suffer from semantic distortion, insufficient spatial modeling, and a lack of integration with medical knowledge. To address these challenges, we propose GATE (Graph-And-Text Exchange), a novel multimodal SSL framework that enhances the quality of the representation of ECG through cross-modal exchange between graph-structured data and clinical ECG reports. GATE employs a spatiotemporal graph encoder to capture fine-grained intra- and inter-lead dependencies, and introduces a lexical knowledge-embedded codebook to enhance the semantic representation of clinical reports, facilitating effective graph-text alignment. During inference, GATE integrates a large language model with a domain-specific knowledge base to generate semantically enriched disease descriptions, enabling robust zero-shot classification. Extensive experiments on three real-world ECG datasets demonstrate that GATE outperforms state-of-the-art self-supervised and multimodal baselines under both low-resource and zero-shot settings. Notably, GATE achieves competitive performance even when trained on only 1% of labeled data, highlighting its strong generalization and clinical potential.

Food image localization and recognition on edge devices is a core task in food computing, enabling convenient dietary monitoring and efficient health management. However, food localization and recognition presents significant challenges due to inherent intra-class variability, inter-class similarity, and non-rigid characteristics. To address these challenges, we propose YOLO-Multi Feature Fusion, a novel multi-feature fusion model for food image localization and recognition. Building upon the YOLOv5 framework, YOLO-Multi Feature Fusion integrates several key components: the Ghost Bottleneck from the lightweight GhostNet, a newly designed Multi-Scale Feature Bottleneck, a Bidirectional Vision Transformer, and an Information Cross-Exchange module. These modules enable the model to comprehensively capture and fuse complex feature information from food images while simultaneously reducing both model parameters and computational load. Extensive evaluations on benchmark datasets (UEC Food100, UEC Food256, and ZSFooD) demonstrate that YOLO-Multi Feature Fusion outperforms existing lightweight detectors. Compared to YOLOv5, YOLO-Multi Feature Fusion achieves mAP improvements of 3.0%, 3.0%, and 0.3% on these datasets, respectively, with parameter reductions of 5.7M, 4.7M, and 4.9M, and computational load reductions of 44.6 GFLOPs, 42.0 GFLOPs, and 42.0 GFLOPs. The source code will be released upon the formal publication of the paper.

The tumor immune microenvironment (TIME) in non-small cell lung cancer (NSCLC) histopathology contains morphological and molecular characteristics predictive of immunotherapy response. Computational quantification of TIME characteristics, such as cell detection and tissue segmentation, can support biomarker development. However, currently available digital pathology datasets of NSCLC for the development of cell detection or tissue segmentation algorithms are limited in scope, lack annotations of clinically prevalent metastatic sites, and forgo molecular information such as PD-L1 immunohistochemistry (IHC). To fill this gap, we introduce the 'IGNITE data toolkit', a multi-stain, multi-centric, and multi-scanner dataset of annotated NSCLC digital pathology images. We publicly release 887 fully annotated regions of interest from 155 patients across three complementary tasks: (i) multi-class semantic segmentation of tissue compartments in H&E-stained slides, with 16 classes spanning primary and metastatic NSCLC, (ii) IHC nuclei detection, and (iii) PD-L1 positive tumor cell detection in PD-L1 IHC slides. To the best of our knowledge, this is the first public NSCLC dataset with manual annotations of H&E in metastatic sites and PD-L1 IHC.

Liver fibrosis staging (LFS) informs treatment decisions and prognostic assessment in liver disease. Multiparametric MRI enables non-invasive, quantitative characterization of fibrosis-related tissue changes across the whole liver. Although deep-learning-based MRI analysis has advanced automated LFS, two bottlenecks remain: (i) etiology- and tissue-level heterogeneities reduce feature consistency across patients and liver regions; (ii) the lack of explicit modeling of inter-regional and inter-biomarker interactions biases models toward isolated imaging cues, leading to spurious correlations and limited generalizability. Here, we introduce a deep heterogeneity profiling framework with graph-informed disentangled interaction learning (HP-DIL) to enable accurate and interpretable LFS. HP-DIL first performs a biologically inspired, unsupervised subregion discovery stage, which fuses multiparametric MRI signals, spatial-texture coherence, and anatomical priors to construct subject-level graphs for heterogeneity profiling while preserving hepatic morphology. Within each subject, identified subregions are encoded as graph nodes carrying spatial coordinates, geometry, and multiparametric MRI attributes, forming a spatial-semantic interaction graph. A global-local graph transformer subsequently captures higher-order interactions among node-level representations within the constructed graph. Based on causal inference principles, we introduce a disentangled interaction mechanism (DIM) that decouples representative node-level features from whole-graph embeddings. An information-theoretic optimization is adopted to preserve disease-relevant signals while mitigating spurious correlations. Experiments on two external test cohorts from three external multi-vendor centers demonstrate that HP-DIL achieves competitive accuracy and cross-center generalizability. Moreover, we clarify the imaging relevance of the subregions identified by HP-DIL, with qualitative analysis showing close agreement between DIM-highlighted regions and radiological assessment. These findings support HP-DIL's potential for reliable clinical deployment in non-invasive LFS.

Decoding motor intentions from noninvasive brain recordings remains a longstanding challenge in neural engineering, particularly in advancing brain-computer interfaces (BCIs) for motor assistance and rehabilitation. The traditional motor imagery (MI) paradigm faces limitations due to ill-defined mental tasks and the variability of the induced sensorimotor rhythm (SMR) features. Studies involving large-scale subject cohorts have reported that conventional MI-BCI achieves only around 70 75% accuracy in binary classification, with an inefficiency rate of 35%-50%. Here, we introduce a rhythmic MI paradigm which can induce steady-state movement-related rhythms (SSMRR). A comprehensive evaluation involving 65 BCI-naïve participants was conducted to investigate whether rhythmic MI with SSMRR features can enhance MI-BCI's performance. Our results demonstrate a 4 class online decoding accuracy of 78.88%±14.80% and a binary offline decoding accuracy of nearly 90%, with an inefficiency rate below 10%, marking a substantial improvement over conventional MI-BCI. Offline evaluations also show the potential of rhythmic MI for cross-subject generalization. Furthermore, we show that the proposed rhythmic MI tasks can help participants better modulate SMR, reducing the SMR inefficiency rate from 50.77% to 23.08%. Lastly, we validate phase consistency as a neurophysiological predictor of SSMRR-based decoding, offering insights for further refining mental tasks and improving decoding algorithms. Overall, our findings demonstrate that rhythmic MI can facilitate a noninvasive BCI with high decoding accuracy and low inefficiency rate, unlocking new possibilities for human machine interaction and clinical applications such as neurorehabilitation.