IEEE Transactions on Biomedical Engineering最新文献

{"title":"Analysis of the Impact of Hardware Front-End Limitations on Vagus Nerve Electroneurogram-Based Seizure Detection.","authors":"Sylvain Favresse, Antoine Nonclercq, Riem El Tahry, David Bol, Denis Flandre","doi":"10.1109/TBME.2026.3729285","DOIUrl":"https://doi.org/10.1109/TBME.2026.3729285","url":null,"abstract":"<p><strong>Objective: </strong>The detection of seizures from the vagus nerve electroneurogram (VENG) is an emerging application allowing minimally invasive closed-loop vagus nerve stimulation for the treatment of epilepsy. Several VENG-specific front-end designs were presented earlier, but their specifications were approximate or arbitrary, leading to inefficient or sub-optimal designs in an applicative context. In this work, we analyze how front-end design choices and non-idealities impact seizure detection performance. The sensitivity analysis leads to the presentation of potentially optimal front-end designs with low power consumption.</p><p><strong>Methods: </strong>This work uses experimental VENG data from 8 rats, a behavioral model of the front-end circuits, and a seizure detection algorithm based on template matching. The studied front-end limitations are intrinsic noise, common-mode rejection, dynamic range, quantization resolution, and oversampling rate, studied individually in a sensitivity analysis. Optimal designs are then proposed based on sensitivity results. The performance of the seizure detection algorithm is characterized by metrics that are least affected by the small dataset size.</p><p><strong>Results: </strong>Noise and dynamic range are the main factors impacting algorithm performance. An optimal front-end design with 3-μV_RMS noise, 6-bit quantization, and 2.1-μW power consumption is presented and achieves perfect seizure classification on the dataset.</p><p><strong>Conclusion: </strong>The presented analysis enables the optimization of front-end specifications and a significant reduction in power consumption.</p><p><strong>Significance: </strong>This work bridges the gap between the performance of a seizure detection algorithm and the circuit-level specifications for ultra-low-power integrated bio-interface design.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148864825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability and Agreement of CMAP Scan-Derived MUNE Algorithms in Healthy Individuals.","authors":"Tarun Arora, Mohammed Almokdad, Daniel M Sorensen, Agessandro Abrahao, Abir Alaamel, Halil C Alaydin, Martin Ballegaard, Evren Boran, Bulent Cengiz, Oystein Dunker, Carolina C Graffe, Mika A Kallio, Christian Krarup, Thomas Kroigard, Rocco Liguori, Tudor D Lupescu, Stuart Maitland, Jose M Matamala, Mihai Moldovan, Javier Moreno-Roco, Andreas C Themistocleous, Hilmi Uysal, Veria Vacchiano, Roger G Whittaker, Lorne Zinman, Hatice Tankisi, Kristian B Nilsen, Kelvin E Jones","doi":"10.1109/TBME.2026.3728251","DOIUrl":"https://doi.org/10.1109/TBME.2026.3728251","url":null,"abstract":"<p><strong>Objective: </strong>CMAP scan-based motor unit number estimation (MUNE) methods offer non-invasive, physiologically meaningful measures of motor unit integrity. This study evaluated and compared the test-retest measurement properties of three algorithms: STEPIX, CDIX, and StairFit, with comparison to previously published MScanFit values.</p><p><strong>Methods: </strong>MUNE was estimated from the abductor pollicis brevis (APB), abductor digiti minimi (ADM), and tibialis anterior (TA) muscles in 148 healthy adults recruited across 15 international sites. Relative reliability was assessed using intraclass correlation coefficient (ICC) and concordance correlation coefficient (CCC). Agreement was evaluated using Bland-Altman analysis and estimation statistics. Absolute measurement error was quantified using the standard error of measurement (SEM), SEM%, and smallest detectable changes (SDC). Sensitivity analyses were performed after excluding site- or participant-level data that exceeded quality control thresholds.</p><p><strong>Results: </strong>Across all muscles and algorithms, relative reliability was poor-to-moderate (ICC: 0.29-0.76), with SEM% values of 12-29%. CDIX demonstrated the lowest reliability and highest measurement error, while StairFit and STEPIX performed comparably. CMAP peak amplitude showed moderate-to-good relative reliability (ICC: 0.73-0.82) with SEM% values of 12-16%. Sensitivity analyses improved CMAP peak reliability, but produced only modest changes in MUNE measurement properties. Percent-change analyses indicated that visit-to-visit CMAP peak variability contributed to MUNE variability, but the strength of this association differed across algorithms.</p><p><strong>Conclusion: </strong>CMAP scan MUNE methods showed limited test-retest measurement properties in healthy individuals. Variability reflected contributions from both CMAP acquisition and algorithm-based estimation.</p><p><strong>Significance: </strong>No algorithm consistently achieved the combined reliability, precision, and SDC values needed for tracking individual-level change under the conditions studied. Future studies should evaluate whether measurement properties improve in clinical populations with motor unit loss.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148840230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Guided Dual-View Pre-Training for Fracture-Healing Assessment on Orthogonal Radiographs.","authors":"Rui Hu, Jie Chen, Dillon C O'Neill, Istvan Gergely, Cooper R Parish, Sarah L Mostardo, Mubashir Jafry, Mingquan Lin, Roman M Natoli, Melissa A Kacena, Nian Wang","doi":"10.1109/TBME.2026.3728034","DOIUrl":"https://doi.org/10.1109/TBME.2026.3728034","url":null,"abstract":"<p><p>Radiographic fracture-healing assessment is subjective and time-consuming, and existing automated methods often underuse the complementary information in paired anteroposterior (AP) and lateral (LAT) radiographs. To address this limitation, we propose Dual-View Fracture Scoring (DV-FraS), a deep learning framework for automated cortex-level fracture-healing assessment from paired orthogonal radiographs. DV-FraS implements an automated end-to-end workflow that standardizes fracture localization, performs cross-guided orthogonal multi-view 2D representation learning, and predicts cortex-level modified radiographic union score for tibia (mRUST) from paired AP and LAT radiographs. In the representation-learning stage, a Dual-View Cross-Guided Masked Autoencoder (DC-MAE) reconstructs masked anatomical information across orthogonal views, encouraging view-consistent and complementary fracture representations. DV-FraS was evaluated using murine femur-fracture radiographs and a prospective human fracture cohort. On the murine held-out test set, it achieved a mean absolute error (MAE) of 0.042, Top-1 accuracy (Top-1 Acc.) of 97.07%, and an absolute-agreement intraclass correlation coefficient [ICC(A,1)] of 0.980. In human radiographs, DV-FraS achieved a mean absolute error of 0.192 and Top-1 Acc. of 89.47%, with statistically significant Top-1 Acc. gains over the leading dual-view competitors. Moreover, its predictions also preserved age-dependent longitudinal healing patterns. These findings suggest that DV-FraS provides an automated and clinically aligned framework that may improve the objectivity, consistency, and efficiency of radiographic fracture-healing assessment.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148827853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of Walking Body Center of Mass Velocity by Means of Microwave Radars and Deep Learning.","authors":"Paolo Brasiliano, Fabrizio Lorenzo Carcione, Gaspare Pavei, Emanuele Cardillo, Elena Bergamini","doi":"10.1109/TBME.2026.3727079","DOIUrl":"https://doi.org/10.1109/TBME.2026.3727079","url":null,"abstract":"<p><strong>Objective: </strong>This study introduces an innovative framework combining microwave Doppler radar networks with deep learning to estimate three-dimensional body center of mass (BCoM) velocity. We evaluated the system's ability to derive clinical gait-quality indices, aiming for a privacy-preserving alternative to laboratory-based motion capture.</p><p><strong>Methods: </strong>Sixty healthy adults performed treadmill walking at 2, 4, and 6 km/h, including a simulated hemiplegic gait. Three radars captured micro-Doppler spectrograms in anterior-posterior (AP), medio lateral (ML), and cranio-caudal (CC) directions. Recurrent neural networks, optimized via Bayesian techniques, estimated 3D BCoM velocities, which were validated against gold-standard motion capture. Three parameters were derived to assess gait smoothness (LDLJ), symmetry (iHR), and stability (RMS acceleration).</p><p><strong>Results: </strong>The system reconstructed BCoM velocity waveforms with high fidelity and minimal bias. In particular, LDLJ achieved remarkable accuracy in the AP and CC directions, with errors below 6.1%. While medio-lateral and acceleration-derived metrics (particularly RMS) proved more sensitive to estimation noise- peaking at 22.3% error during simulated hemiplegia-the framework successfully preserved key gait-quality patterns at the group level.</p><p><strong>Conclusion: </strong>Integrating radar technology with sequence learning effectively recovers complex BCoM dynamics. Despite inherent challenges in acceleration-based metrics, this approach captures nuanced gait characteristics that go beyond traditional spatiotemporal parameters, maintaining clinical relevance in a non-invasive format.</p><p><strong>Significance: </strong>This work represents a significant step toward unobtrusive, markerless gait monitoring. It offers a scalable, privacy-preserving solution for continuous assessment in clinical and home settings, bridging the gap between laboratory research and real-world applications.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inferring Causality in Aperiodic and Periodic Components of Brain and Cardiac Dynamics.","authors":"Vincenzo Catrambone, Beatrice Cairo, Vlasta Bari, Marco Ranucci, Alberto Porta, Gaetano Valenza","doi":"10.1109/TBME.2026.3727058","DOIUrl":"https://doi.org/10.1109/TBME.2026.3727058","url":null,"abstract":"<p><p>  Background: Aperiodic $1/f-$like neural activity is thought to reflect fundamental properties of population-level excitation-inhibition balance, yet no existing framework provides directional causal inference between this component and neuroautonomic dynamics. Current brain-heart models also lack formulations accounting for both aperiodic and oscillatory spectral components.</p><p><strong>Objectives: </strong>To develop a mathematical framework for directional causal inference between time-resolved aperiodic ($1/f-$like) electroencephalographic (EEG) components and heartbeat dynamics. We also aim to extend the same formalism to periodic narrow-band EEG oscillations.</p><p><strong>Methods: </strong>We introduce the directional causality for brain-heart interplay (DiCa-BHI) framework, a stochastic modelling approach in which each EEG spectral parameter is treated as a time-varying process governed by autoregressive dynamics with exogenous neuroautonomic inputs. Aperiodic exponent, offset, and oscillatory peak amplitudes are modelled within a parametric spectral representation, while heartbeat dynamics are characterized via an extended, stochastic integral pulse frequency modulation model. Directional causal coefficients are estimated using a Granger-predictive causal ARX formalism. Validation employed synchronized EEG-ECG recordings from 27 healthy adults undergoing supine rest, postural changes, and emotional video elicitation. Subject-specific estimations are performed and then compared across experimental conditions.</p><p><strong>Results: </strong>The aperiodic $1/f-$-like EEG component exhibited predominant bottom-up heart-to-brain causality, attenuated during orthostasis but strengthened during emotional stimulation across widespread cortical regions. Conversely, periodic narrowband components showed strong top-down brain-to-heart dominance, exceeding 90% for vagal and 70% for sympathovagal contributions.</p><p><strong>Conclusions: </strong>DiCa-BHI provides a novel methodological framework for directional causal inference in the $1/f-$ aperiodic component of neural activity and generalizes seamlessly to narrow-band oscillatory components.</p><p><strong>Significance: </strong>The framework advances mathematical modelling of the brain-heart axis and provides a quantitative tool for applications in cardiology, neurology, and psychophysiological research.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dual-Echo bSSFP for Rapid T2-Sensitive Quantitative Contrast Imaging at Ultra-Low Field.","authors":"Sheng Shen, Neha Koonjoo, Hester A Braaksma, Noah Mack, Hongwei Li, Matthew S Rosen","doi":"10.1109/TBME.2026.3727100","DOIUrl":"10.1109/TBME.2026.3727100","url":null,"abstract":"<p><strong>Objective: </strong>Rapid characterization of transverse-relaxation-sensitive MRI contrast is important for evaluating tissue-dependent signal behavior, but remains challenging in ultra-low-field (ULF) MRI because of limited signal-to-noise ratio (SNR) and acquisition-efficiency constraints. This study aims to develop a rapid, high-SNR, sequence-specific T2-sensitive quantitative contrast imaging method for ULF MRI.</p><p><strong>Methods: </strong>A balanced dual-echo steady-state (bDESS) sequence was developed to acquire two echoes at predefined echo times within each repetition of a balanced steady-state free precession acquisition. A logarithmic-ratio operator, based on a mono-exponential attenuation approximation, was used to derive a sequence-specific T2-sensitive contrast index, termed T2SDI, from the two echo magnitudes. The proposed method was implemented on a custom-built 6.5 mT MRI system and evaluated using numerical simulations, CuSO₄ phantom experiments, and in vivo brain imaging.</p><p><strong>Results: </strong>Numerical simulations showed that T2SDI exhibited a monotonic and approximately linear dependence on T2 under controlled field-inhomogeneity conditions. Phantom experiments confirmed that bDESS-derived T2SDI increased with CPMG-measured reference T2 and showed higher SNR than dual-echo SPGR. The method was further demonstrated in vivo by generating T2SDI maps of the human brain.</p><p><strong>Conclusion: </strong>This study presents a sequence-specific, index-based method for rapid T2-sensitive quantitative contrast imaging in ULF MRI.</p><p><strong>Significance: </strong>The proposed dual-echo bSSFP/bDESS method provides a high-SNR and time-efficient strategy for sequence-specific T2-sensitive contrast characterization at ultra-low field.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparing Ankle Dorsiflexion-Only, Hip Flexion-Only, and Combined Hip-Ankle Assistance During Simulated Foot Drop Gait.","authors":"Junhyeong Kwon, Donghyun Lee, Hyunsu Choi, Wonhee Lee, Junyoung Moon, Giuk Lee","doi":"10.1109/TBME.2026.3726470","DOIUrl":"https://doi.org/10.1109/TBME.2026.3726470","url":null,"abstract":"<p><strong>Objective: </strong>This study experimentally evaluated whether coordinated multi-joint assistance within a single-limb soft exosuit produces broader swing-phase kinematic modulation than isolated ankle or hip assistance under a foot-drop-like perturbation.</p><p><strong>Methods: </strong>Ten healthy male adults walked on a treadmill at 4.0 km/h with a 2-kg distal mass on the dorsum of the foot to simulate a unilateral foot-drop clearance challenge. Four conditions were tested: loaded walking without assistance (LW), hip-only (HIP), ankle-only (ANK), and combined hip-ankle (MULTI) assistance delivered via a unilateral cable-driven exosuit. Three-dimensional marker trajectories were recorded using motion capture. Foot-clearance metrics and sagittal-plane hip, knee, and ankle kinematics were analyzed using repeated-measures ANOVA and statistical parametric mapping (SPM).</p><p><strong>Results: </strong>Compared with LW, both ANK and MULTI produced significant increases in maximum toe height and minimum toe clearance during mid-swing, and both exceeded HIP in minimum toe clearance. MULTI additionally produced a significant increase in foot contact angle at initial contact relative to LW. MULTI did not further increase minimum toe clearance or contact angle over ANK, but uniquely induced significant late-swing alterations in both hip and ankle sagittal kinematics; knee kinematics were unaffected by any condition.</p><p><strong>Conclusion: </strong>Coordinated multi-joint assistance yielded broader swing-phase kinematic modulation than isolated joint assistance, with its distinctive contribution lying in simultaneous proximal and distal control rather than further peak-clearance gains.</p><p><strong>Significance: </strong>These findings provide biomechanical evidence supporting multi-joint soft exosuit strategies for swing-phase foot clearance in foot-drop-like gait, while clinical translation remains to be established.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiple-Classifier Binary Convolutional Siamese Networks for Code-Modulated Visual Evoked Potential Classification.","authors":"Kiran Nair, Hubert Cecotti","doi":"10.1109/TBME.2026.3726071","DOIUrl":"https://doi.org/10.1109/TBME.2026.3726071","url":null,"abstract":"<p><strong>Objective: </strong>Non-invasive Brain-Computer Interfaces (BCIs) based on Code-Modulated Visual Evoked Potentials (c-VEPs) using electroencephalography (EEG) signals require robust classification algorithms. It is unclear whether the best approach is to use a similarity measure or to follow a discriminant method.</p><p><strong>Methods: </strong>We propose a multiple-classifier binary convolutional Siamese (MCBCS) network for single-trial c-VEP decoding, in which the multi-class recognition problem is decomposed into a set of class-specific binary similarity-learning tasks. The proposed MCBCS framework is systematically compared against a single multi-class Siamese network, convolutional neural networks for 63-bit m-sequence reconstruction and direct classification, and conventional correlation-based and canonical correlation analysis approaches. The study also investigates distance-based decoding strategies and the effect of temporal data augmentation with small to medium time shifts.</p><p><strong>Results: </strong>Experimental results on EEG data from 13 subjects demonstrate that the MCBCS architecture consistently outperforms other tested methods under within-subject evaluation, with a mean single-trial accuracy of 96.89%. However, the MCBCS approach achieves 96.17% under a leave-one-subject-out protocol, while EEGNet achieves 96.79%. Finally, the Wasserstein Distance (WD$_{1}$) achieved the highest accuracy (93.88%) among the distance metrics.</p><p><strong>Conclusion: </strong>The multiple-classifier convolutional binary Siamese network achieved the highest overall performance.</p><p><strong>Significance: </strong>The results highlight the effectiveness of class-specific similarity learning for robust compared to direct discriminant approaches.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable AI Framework for 3D Vision-Based Classification of Adhesive Capsulitis Severity.","authors":"S K Konki, K W Lee, Y J Jeong, A Lee, J H Kim, S U Le","doi":"10.1109/TBME.2026.3726500","DOIUrl":"https://doi.org/10.1109/TBME.2026.3726500","url":null,"abstract":"<p><p>Adhesive capsulitis (AC) is a musculoskeletal disorder that causes significant shoulder pain and stiffness. However, timely assessment of severity is often hindered by labor-intensive clinical procedures and relies largely on subjective judgment. In this study, we propose an explainable AI system for automated classification of AC severity using a single Azure Kinect 3D depth camera. Marker less 3D skeletal data were collected from 221 participants while they performed key shoulder movements, including abduction, flexion, and internal/external rotation. The proposed framework integrates a Temporal Convolutional Network (TCN) to model local temporal structure and cycle-to-cycle variation, followed by Transformer encoders to capture global contextual relationships across movement cycles. In addition, attention-based Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (BiLSTM), and Gated Recurrent Unit (GRU) networks were implemented as deep sequential baselines. For abduction, flexion, and external rotation, all architectures achieved test accuracies of 0.88-0.92 and macro-F1 scores ≥ 0.84. Notably, for internal rotation, the best-performing model (Attention-GRU) achieved an accuracy of 0.81 and macro-F1 of 0.77. Attention weights and SHAP analysis provided complementary interpretability, highlighting discriminative kinematic patterns between healthy and AC groups. The proposed system demonstrates the feasibility of automated AC severity stratification and supports clinician-facing reporting for rehabilitation-oriented assessment.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Auditory BCI System Based on Stimulus-Related Semantic Backgrounds for Consciousness Detection.","authors":"Fei Wang, Jiajun Zhang, Xiaochun Yang, Jiahui Pan, Haiyun Huang, Yanbin He","doi":"10.1109/TBME.2026.3718066","DOIUrl":"https://doi.org/10.1109/TBME.2026.3718066","url":null,"abstract":"<p><p>Brain-computer interfaces (BCIs) hold significant promise in medical applications, particularly for detecting consciousness in patients with disorders of consciousness (DoC). However, conventional BCIs often rely on visual stimuli, which limits their accessibility for visually impaired patients. To expand the applicability of BCIs to a wider range of patients, this study introduces an advanced auditory BCI system. The system incorporates an auditory paradigm utilizing stimulus-related semantic backgrounds and an improved EEG-Inception prototype network with ECA (ECAEI-ProNet). To validate the effectiveness of the proposed system, Experiment 1 was conducted to compare it against three control conditions: Condition 1, which included related backgrounds and stimuli; Condition 2, which included unrelated backgrounds and stimuli; and Condition 3, which presented no background. The results demonstrated that utilizing stimulus-related semantic backgrounds significantly improved BCI classification performance while eliciting event-related potentials (ERP) patterns associated with semantic consistency in subjects. Additionally, the two improvements made to the ECAEI-ProNet model, building upon EEG-Inception, enhanced the model's classification performance. Our proposed paradigm and classification model achieved online accuracies of 88.8$pm$ 9.1%. To evaluate the clinical feasibility of the proposed BCI system, we applied it to 17 patients with DoC in Experiment 2. Results indicated that seven patients achieved online accuracy significantly above the chance level ($>$64%). Among them, the three highest-performing patients (P3, P5, and P12) showed improvements in both CRS-R scores and clinical diagnosis at the three-month follow-up. These findings suggest that the proposed auditory BCI system may offer preliminary information relevant to residual consciousness-related processing in some patients with DoC.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}