IEEE Transactions on Biomedical Engineering最新文献

{"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":"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":"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}

{"title":"Entropy-Minimizing Active Sensing for Model-Based Anatomical Target Tracking.","authors":"E Erdem Tuna, Daniel A Herzka, M Cenk Cavusoglu","doi":"10.1109/TBME.2026.3726063","DOIUrl":"10.1109/TBME.2026.3726063","url":null,"abstract":"<p><strong>Objective: </strong>This study presents an active sensing framework for information-optimal, model-based tracking of de formable anatomy to track the three-dimensional (3D) surface of the heart ventricles using a time sequence of two-dimensional (2D) image slices.</p><p><strong>Methods: </strong>A low-order deformable model parameterizes the cardiac surface, while cardiac motion dynamics are modeled by a recursive adaptive filter and tracked using a particle filter. Measurements of the system state are obtained from a magnetic resonance imaging (MRI) system whose slice selection is governed by an entropy-minimizing active sensing method that chooses the sensing action maximizing expected information gain. Performance is compared with cases where the image slice is fixed or randomly selected. The framework operates on general 2D image streams and is validated on multi-slice cine MRI data to enable comparison against ground-truth slice locations. A variable temporal sampling strategy reduces computational load by executing tracking updates at intervals defined by a temporal sampling factor.</p><p><strong>Results: </strong>The active sensing-based tracking method captured left ventricular (LV) surface points-of-interest within 3 pixels of accuracy at a mean root-mean-square error (RMSE) of 2.93mm, right ventricular (RV) tracking was 4.27mm, for an overall mean RMSE of 3.25mm. For a downsampling factor of 4, the framework maintains an overall RMSE of 3.57mm, a modest degradation relative to fully sampled tracking.</p><p><strong>Conclusion: </strong>The proposed frame work enables a flexible trade-off between computational efficiency and tracking performance.</p><p><strong>Significance: </strong>This work demonstrates that information-driven measurement selection can enhance de formable anatomical tracking under sensing constraints.</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":"148792276","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":"A Bionic Pneumatic Shoulder Exosuit for Multi-DOF Assistance and Load-Bearing Augmentation in Rehabilitation.","authors":"Rongna Xu, Wenhao Yan, Songning Deng, Yi Hu, Hong Yang, Yu Pan, Shaoping Bai, Vincenzo Parenti Castelli, Hongliu Yu, Qiaoling Meng","doi":"10.1109/TBME.2026.3725930","DOIUrl":"10.1109/TBME.2026.3725930","url":null,"abstract":"<p><strong>Objective: </strong>The shoulder joint is pivotal for upper-limb kinematics, yet individuals with post-stroke hemiparesis often require external shoulder support because of impaired motor control, excessive gravitational loading, and the risk of glenohumeral complications. Existing rehabilitation exoskeletons still face challenges in combining compliant movement assistance with sufficient antigravity load support.</p><p><strong>Methods: </strong>This study proposes a Pneumatic Shoulder Exosuit (PSE) designed to provide compliant multi-DOF shoulder assistance and augment load-bearing capacity during rehabilitation. The dual functionality is enabled by two coupled pouch-based pneumatic actuator modalities configured into a bionic agonist/antagonist architecture. Device performance was evaluated through experiments with 10 healthy volunteers using kinematic assessment, standardized trajectory-tracking, and static overhead weight-holding tasks. In addition, 7 participants with post-stroke hemiparesis were enrolled to evaluate the feasibility and usability of the PSE during assisted shoulder tasks.</p><p><strong>Results: </strong>The experimental results showed that the PSE can provide gravity support with up to 24 Nm of torque. The device maintained the movement trajectory with a 96.5% similarity compared to unassisted. It also reduced agonist muscle activities (anterior, middle, and posterior deltoids and biceps brachii) by up to 65% with a 70% reduction in compensatory muscle (latissimus dorsi) activity, and a 45% reduction in peak lateral trunk tilt. The participants with post-stroke hemiparesis also provided positive feedback.</p><p><strong>Conclusion: </strong>These findings demonstrate that the PSE can combine load-bearing augmentation with kinematic transparency during shoulder assistance.</p><p><strong>Significance: </strong>The PSE suggests potential for compliant rehabilitation-oriented shoulder support in future clinical and home-based rehabilitation studies.</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":"148792532","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":"Engineering a Timing-Accurate VR-EEG-Oculomotor Fusion System for Objective Assessment of Executive Function in ADHD.","authors":"Ting-Jhen Lin, R Vaitheeshwari, Shih-Ching Yeh, Chun-Chuan Chen, Yu-Jie Tsai, Eric Hsiao-Kuang Wu","doi":"10.1109/TBME.2026.3725610","DOIUrl":"10.1109/TBME.2026.3725610","url":null,"abstract":"<p><p>Objective, scalable assessment of executive function in Attention-Deficit/Hyperactivity Disorder (ADHD) is limited by subjective rating scales and single modality tests. We present a timing-characterized virtual-reality (VR) implementation of the Wisconsin Card Sorting Test (WCST) synchronized with EEG and oculomotor/cephalic sensing for objective ADHD assessment in children. Stimulus-onset timing was empirically validated with a dedicated photodiode measurement across screen locations and distractor conditions. One hundred and one children (7-15 years; 64 ADHD, 37 control) completed a tutorial and a WCST session with distraction and no-distraction blocks. Task performance, head rotation, eye movement, and EEG features including N2/P3 event related potentials (ERP) were extracted, and group and condition contrasts on the ERP time-courses were evaluated using non-parametric cluster-based permutation testing. Classification used eight machine learning algorithms and a deep neural network (DNN) under 5-fold cross-validation; the best early-fusion DNN (task performance + head rotation + eye movement + N2/P3) reached 83% accuracy, and the best ERP-only model reached 79% under distraction. Overall, a timing characterized VR-EEG oculomotor fusion system captures ADHD-related executive function differences through complementary multimodal integration, providing a scalable, objective adjunct to clinical ADHD screening with empirically quantified stimulus-timing performance.</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":"148792239","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":"Autonomous Patient-Specific Geometry-Aware Planning and Control Framework for Robotic Transcatheter Tricuspid Valve Intervention.","authors":"Haichuan Lin, Yiping Xie, Ziqi Wang, Yuen Chiu Ng, Qin-Yi Zhang, Weizhao Wang, Longyue Tan, Dong Chen, Pengcheng Zhang, Chen Chen, Xiao-Hu Zhou, Zeng-Guang Hou, Fei Pan, Shengtao Lin, Kent Chak-Yu So, Shuangyi Wang","doi":"10.1109/TBME.2026.3725663","DOIUrl":"10.1109/TBME.2026.3725663","url":null,"abstract":"<p><strong>Objective: </strong>Tricuspid regurgitation (TR) is the most prevalent yet historically neglected valvular disease. Transcatheter tricuspid valve interventions (TTVI), encompassing both repair and replacement, have emerged as less invasive alternatives, but their clinical scalability is hindered by the challenge of navigating a large-diameter catheter within the anatomically complex right atrium. This work aims to establish an autonomous and patient-specific planning-control framework that bridges preoperative imaging with intraoperative robotic navigation.</p><p><strong>Methods: </strong>Cardiac chambers were reconstructed from preoperative computed tomography (CT) segmentation. A singular value decomposition-based valve analysis was applied to automatically extract the tricuspid annulus and estimate its centerline. On this anatomical foundation, a geometry-aware path optimization method was developed, integrating signed distance fields (SDF) with Riemannian metrics to generate safe, smooth, and anatomically consistent delivery paths. During intraoperative navigation, a numerical Jacobian-based inverse kinematics controller guided the catheter tip autonomously along the preplanned path.</p><p><strong>Results: </strong>The framework was validated in a preclinical setting using fifteen real patient CT datasets with severe TR and three cardiac phantoms. The proposed method consistently produced anatomically valid paths and achieved accurate and robust catheter tip tracking, with millimeter-scale tracking errors across repeated phantom experiments.</p><p><strong>Conclusion: </strong>The integration of singular value decomposition-based anatomical analysis, geometry-aware path planning, and Jacobian-based control enables autonomous catheter navigation directly derived from patient-specific CT data.</p><p><strong>Significance: </strong>A framework was developed for TTVI to establish an end-to-end pipeline ranging from patient-specific CT analysis to autonomous catheter navigation, thereby reducing the burden on the operator and charting a course that provides a foundation for future translational development in robot-assisted structural cardiac interventions.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792520","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":"Textile-Integrated Magnetoinductive Waveguides for Low-Complexity, Single-Channel Quantitative Estimation of Isometric Elbow Torque.","authors":"Samuel J Coogle, Brian Prejean, Asimina Kiourti","doi":"10.1109/TBME.2026.3725220","DOIUrl":"10.1109/TBME.2026.3725220","url":null,"abstract":"<p><strong>Objective: </strong>Wearable monitoring of isometric elbow torque is of great interest for rehabilitation monitoring and muscular disease management, yet remains limited by obtrusiveness, drift, and complexity. We present a wearable sensor that measures transient circumferential deformation of the mid-upper arm as a low-complexity bio-signal for joint torque monitoring.</p><p><strong>Methods: </strong>The proposed sensor operates on the basis of magnetoinductive waveguide principles. Participants (n=20) completed three sets of three contractions with sensor replacement between sets. A two-stage analysis extracted contraction-level calibration slopes and characterized variability using a three-level nested mixed effects model. Systematic bias was assessed and leave-one-out cross validation quantified prediction error at the subject, set, and contraction levels.</p><p><strong>Results: </strong>The sensor data had a strong, linear relationship with elbow torque (mean $R^{2}=0.925pm 0.063$) across the test population. Within-contraction modeling error was $2.5;Nm$ (5.9%); leave-one-out calibration grouped by set, subject, and population increased error to $5.84;Nm$ (14.0%), $7.70;Nm$ (18.4%), and $9.76;Nm$ (23.4%), respectively, with an opposite trend in calibration burden. No systematic bias was detected across set and contraction order, nor with respect to anthropometric data, supporting the sensor's generalizability.</p><p><strong>Conclusion: </strong>The herein described magnetoinductive waveguide sensor provides a strong, linear predictor of isometric elbow torque with calibration variability emerging primarily due to inter-subject differences that warrant further study. Extension to complex contractions remains critical for future work.</p><p><strong>Significance: </strong>The single-channel, low-complexity, textile-integrated modality enabled by transient circumferential deformation sensing creates a promising path towards monitoring of at-home rehabilitation and muscular disease management.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792245","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":"Patient-Specific Non-Invasive Epileptogenic Zone Localization via High-Resolution Time-Frequency Representations and CNN Deep Learning.","authors":"Yalin Wang, Wenbin Yuan, Yaqing Liu, Yao Guo, Yuanfeng Zhou, Wei Chen, Yanming Han, Tiancheng Wang, Bin Hu","doi":"10.1109/TBME.2026.3724147","DOIUrl":"10.1109/TBME.2026.3724147","url":null,"abstract":"<p><p>Stereoelectroencephalography (SEEG)-guided radiofrequency thermocoagulation is the mainstream treatment for drug-resistant epilepsy (DRE), yet non-invasive patient-specific localization of potential epileptogenic zone (EZ) prior to SEEG electrode implantation remains a critical unmet clinical need, hindered by limited automation, suboptimal accuracy, and poor cross-patient generalizability. To address these gaps, we developed an automated non-invasive EZ localization framework that integrates scalp EEG source imaging, high-resolution time-frequency analysis, and deep learning. This multicenter retrospective study included 97 seizure episodes from 37 surgically confirmed DRE patients with Engel Class I post-operative seizure freedom. Three time-frequency spectrograms were generated based on the source-reconstructed signal, and fed into four deep learning architectures (ResNet, VGG, DenseNet, Swin Transformer) for channel-level EZ binary classification with patient-level leave one-out cross-validation to validate personalized localization for unseen patients. The ResNet18-Superlet combination achieved optimal performance (accuracy = 81.15% ± 4.83%, AUC = 84.82% ± 5.27%) in the adult cohort, with robust generalization to pediatric and mixed cohorts, significantly outperforming conventional high-frequency oscillation (HFO)-based methods. This framework enables accurate personalized pre-surgical EZ map ping to optimize SEEG implantation planning, with open-source code available at https://github.com/wyl1994/Source-code-for Patient-Specific-Non-Invasive-Epileptogenic-Zone-Localization to ensure reproducibility and clinical translation.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792285","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":"Towards Wearable High-Density MEG: A Compact, Low-Power, and Scalable OPM-MEG System with Automated Control.","authors":"Kaiyan He, Rui Yang, Congcong Li, Yuyao Cai, Hao Cheng, Zeyu Jin, Dongxu Li, Fufu Zheng, Pingchuan Zou, Bingjiang Lyu, Jia-Hong Gao","doi":"10.1109/TBME.2026.3724753","DOIUrl":"10.1109/TBME.2026.3724753","url":null,"abstract":"<p><strong>Objective/background: </strong>Optically pumped magnetometer-based magnetoencephalography (OPM-MEG) is advancing toward wearable and high-density sensor configurations, posing significant engineering challenges in miniaturization, thermal management, and scalable integration. Here, we present a high-performance wearable OPM-MEG system that addresses these challenges.</p><p><strong>Methods: </strong>The system was developed through a system-level co-design of the sensor head and electronic control units (ECUs) with a fully automated control workflow. To reduce thermal dissipation and lower scalp temperature, we implemented a thermally optimized suspended vapor-cell module.</p><p><strong>Results: </strong>This design achieves a miniaturized sensor head (12 × 16.5 × 22.5 mm3) and ECU footprint (34 × 28 mm2), with a total per-sensor power consumption of 3.5 W (0.7 W allocated to the sensor head). Crucially, the sensor maintains high sensitivity required for detecting ultraweak brain magnetic fields, exhibiting single-axis sensitivity < 7 fT/$sqrt$ Hz and dual-axis sensitivity < 10 fT/$sqrt$ Hz, with a bandwidth of 130 Hz. Inter-sensor crosstalk and intra-sensor cross-axis projection error (CAPE) are suppressed to lower than 2%, addressing the critical challenge of signal interference in high-density sensor arrays. Phantom experiments demonstrate accurate source localization with a mean error of  1 mm, while human recordings provide further validation of stable and high-fidelity performance in wearable OPM-MEG settings.</p><p><strong>Conclusion: </strong>Collectively, this work establishes a scalable, instrument-level framework for the design, automated operation, and quantitative end-to-end evaluation of high-density wearable OPM-MEG systems.</p><p><strong>Significance: </strong>This work provides a scalable foundation for high-density wearable OPM-MEG, enabling mobile brain measurements for brain-computer interfaces, cognitive neuroscience, and future translational clinical neuroimaging applications.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148792328","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":"Analyzing Frequency-Space-Time EEG Signatures via Interpretable Neural Networks: A Simulation Study.","authors":"Davide Borra, Elisa Magosso","doi":"10.1109/TBME.2026.3723565","DOIUrl":"10.1109/TBME.2026.3723565","url":null,"abstract":"<p><strong>Objective: </strong>Event-related EEG activity is widely investigated to characterize brain functions. Traditional analyses rely on heavy pre-processing and strong a priori assumptions, which limit reproducibility and may obscure task-relevant neural activity. This study aims to validate an interpretable convolutional neural network (CNN) capable of highlighting frequency-, spatial-, and temporal-domain EEG signatures in an automatic, data-driven, and end-to-end manner.</p><p><strong>Methods: </strong>We simulated single-trial EEG with imposed spatio-temporal or spectral-spatio-temporal modulations in two paradigms: a visual oddball task and a motor task (200 participants and 200k trials overall). An interpretable CNN was applied to each cognitive task at the single-participant level. CNN-derived spectral, spatial, and temporal signatures were compared with ground-truth signatures known from the simulation by computing localization errors and accuracies.</p><p><strong>Results: </strong>Network features reproduced the modulations imposed in the simulations. The network localized neural signatures with high accuracy: average spectral, spatial, and temporal localization accuracies reached up to 85.3%, 97.8%, and 97.1% across tasks, respectively (top-1 prediction). The corresponding average localization errors were well within established EEG resolution limits (down to 0.95 Hz spectral, 5.7 mm spatial, and 30 ms temporal errors).</p><p><strong>Conclusion: </strong>The interpretable CNN accurately recovered task-relevant EEG signatures across domains, thereby supporting the validity of a CNN-based EEG analysis.</p><p><strong>Significance: </strong>This study provides a ground-truth-based quantitative validation of the multi-domain features learned in interpretable CNNs for EEG analysis, establishing a meaningful reference for trustworthy deep-learning tools that can enhance participant-specific EEG interpretation. These individualized tools could enhance our comprehension of brain functions in both healthy participants and patients.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2026-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148760314","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}