IEEE Transactions on Biomedical Engineering最新文献

{"title":"Automated Electrorotation System for High-Throughput Dielectric Cell Characterization.","authors":"Samuele Moscato, Andrea Ballo, Pasquale Memmolo, Paolo Bonacci, Nicolo Musso, Maide Bucolo, Massimo Camarda","doi":"10.1109/TBME.2025.3617496","DOIUrl":"https://doi.org/10.1109/TBME.2025.3617496","url":null,"abstract":"<p><strong>Objective: </strong>This work presents ROT-QSG, a compact, automated, and user-friendly electrorotation system for label-free dielectric characterization of biological cells, enabling applications in disease diagnosis, drug discovery, and personalized medicine.</p><p><strong>Methods: </strong>The ROT-QSG system consists of three main components: (1) a custom electronic device-Quadrature Signal Generator (QSG); (2) a specifically designed electrorotation chip-ROT-chip; and (3) a dedicated image processing algorithm-Pixel Intensity (PxI)-which enables automatic, operator-independent extraction of cell rotation data. Electrorotation allows the dielectric characterization of cells by analyzing their rotational response to varying electric field frequencies, generating the rotation-frequency spectrum (ROT-spectrum). To ensure high consistency and repeatability, the entire experimental workflow-from signal generation to spectrum extraction-has been fully automated through a dedicated experimental control algorithm.</p><p><strong>Results: </strong>The system was validated by analyzing three immortalized cell lines (CaCo-2, CCD-841, and OPM2), from which ROT spectra and corresponding cell membrane capacitance values were successfully extracted.</p><p><strong>Conclusion: </strong>The comparative study revealed clear differences in membrane capacitance among the three cell types, confirming the system's capability to detect meaningful dielectric variations. The repeatability of measurements within each cell line and the observed distinct spectral differences between the cell lines demonstrate its sensitivity to variations in membrane morphology and structural organization.</p><p><strong>Significance: </strong>The system, designed with a strong focus on integration, automation, and ease of use in biological settings, has the potential to enhance dielectric characterization across a wide range of cell types, contributing to a deeper understanding of cellular functions and disease mechanisms.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238475","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":"Self-Supervised Contrastive Pre-Training for EEG-Based Recognition via Cross Device Representation Consistency.","authors":"Meihong Zhang, Shaokai Zhao, Liang Xie, Tiejun Liu, Dezhong Yao, Erwei Yin","doi":"10.1109/TBME.2025.3613730","DOIUrl":"https://doi.org/10.1109/TBME.2025.3613730","url":null,"abstract":"<p><p>Electroencephalography (EEG) has emerged as a powerful tool for modeling human brain states. However, the widespread adoption of EEG-based recognition systems is hindered by low signal-to-noise ratios and the scarcity of labeled data. While existing studies often tackle these challenges in isolation, we propose a novel Cross-Device Representation Consistency (CDRC) pretraining paradigm that addresses both issues simultaneously. CDRC leverages self-supervised signals derived from representation distances and is trained through contrastive estimation. Specifically, our approach employs a transformer based dual-branch single-view embedding prediction task, combining with a contrastive feature alignment module to extract robust and discriminative representations. We first evaluate the CDRC model on a low signal-to-noise ratio emotion classification task involving wearable dry electrodes. Furthermore, we extend CDRC to a multimodal fusion setting to address a cross-device vigilance regression task involving heterogeneous physiological modalities. Extensive experiments on the PaDWEED and SEED-VIG datasets demonstrate that CDRC achieves performance comparable to fully supervised methods and reaches the stat-of-the-art results of existing self-supervised methods, setting a new benchmark in this field. Notably, its strong performance on subject-independent tasks highlights its effectiveness in mitigating subject variability. These results underscore the potential of CDRC to significantly enhance the practicality and scalability of EEG-based recognition systems, marking a meaningful step toward real-world brain-computer interfaces.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238445","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":"Physics-guided Self-supervised Implicit Neural Representation For Accelerated $text{T}_{1rho }$ Mapping.","authors":"Yuanyuan Liu, Jinwen Xie, Jianhao Wu, Zhuo-Xu Cui, Qingyong Zhu, Jing Cheng, Haifeng Wang, Zhen Song, Dong Liang, Yanjie Zhu","doi":"10.1109/TBME.2025.3618476","DOIUrl":"https://doi.org/10.1109/TBME.2025.3618476","url":null,"abstract":"<p><p>Quantitative $text{T}_{1rho }$ mapping has shown promise in clinical and research studies. However, it suffers from long scan times. Deep learning-based techniques have been successfully applied in accelerated quantitative MR parameter mapping. However, most methods require fully-sampled training dataset, which is impractical in the clinic. In this study, a novel scan-specific self-supervised method based on the implicit neural representation is proposed to reconstruct $text{T}_{1rho }$-weighted images and generate $text{T}_{1rho }$ map from highly undersampled $k$-space data, which only takes spatiotemporal coordinates as the input. Specifically, the proposed method learns an implicit neural representation of the MR images guided by the physical model of $text{T}_{1rho }$ mapping and two explicit priors: the signal relaxation prior and the self-consistency of $k$-t space data prior. The proposed method was verified using both retrospective and prospective undersampled $k$-space data. Experiment results demonstrate that it achieves a high acceleration factor up to 14, and outperforms the state-of-the-art methods in terms of suppressing artifacts and achieving the lowest error.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145238447","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 Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications.","authors":"Tolga Cukur, Salman Uh Dar, Valiyeh A Nezhad, Yohan Jun, Tae Hyung Kim, Shohei Fujita, Berkin Bilgic","doi":"10.1109/TBME.2025.3617575","DOIUrl":"https://doi.org/10.1109/TBME.2025.3617575","url":null,"abstract":"<p><p>MRI is an indispensable clinical tool, offering a rich variety of tissue contrasts to support broad diagnostic and research applications. Protocols can incorporate multiple structural, functional, diffusion, spectroscopic, or relaxometry sequences to provide complementary information for differential diagnosis, and to capture multidimensional insights into tissue structure and composition. However, these capabilities come at the cost of prolonged scan times, which reduce patient throughput, increase susceptibility to motion artifacts, and may require trade-offs in image quality or diagnostic scope. Over the last two decades, advances in image reconstruction algorithms-alongside improvements in hardware and pulse sequence design-have made it possible to accelerate acquisitions while preserving diagnostic quality. Central to this progress is the ability to incorporate prior information to regularize the solutions to the reconstruction problem. In this tutorial, we overview the basics of MRI reconstruction and highlight state-of-the-art approaches, beginning with classical methods that rely on explicit hand-crafted priors, and then turning to deep learning methods that leverage a combination of learned and crafted priors to further push the performance envelope. We also explore the translational aspects and eventual clinical implications of these methods. We conclude by discussing future directions to address remaining challenges in MRI reconstruction. The tutorial is accompanied by a Python toolbox (https://github.com/tutorial-MRI-recon/tutorial) to demonstrate select methods discussed in the article.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145225448","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":"Multilevel Correlation-aware and Modal-aware Graph Convolutional Network for Diagnosing Neurodevelopmental Disorders.","authors":"Shijia Zuo, Yu Li, Yinbao Qi, Aiping Liu","doi":"10.1109/TBME.2025.3617348","DOIUrl":"https://doi.org/10.1109/TBME.2025.3617348","url":null,"abstract":"<p><strong>Objective: </strong>Graph-based methods using resting-state functional magnetic resonance imaging demonstrate strong capabilities in modeling brain networks. However, existing graph-based methods often overlook inter-graph relationships, limiting their ability to capture the intrinsic features shared across individuals. Additionally, their simplistic integration strategies may fail to take full advantage of multimodal information. To address these challenges, this paper proposes a Multilevel Correlation-aware and Modal-aware Graph Convolutional Network (MCM-GCN) for the reliable diagnosis of neurodevelopmental disorders.</p><p><strong>Methods: </strong>At the individual level, we design a correlation-driven feature generation module that incorporates a pooling layer with external graph attention to perceive inter-graph correlations, generating discriminative brain embeddings and identifying disease-related regions. At the population level, to deeply integrate multimodal and multi-atlas information, a multimodal-decoupled feature enhancement module learns unique and shared embeddings from brain graphs and phenotypic data and then fuses them adaptively with graph channel attention for reliable disease classification.</p><p><strong>Results: </strong>Extensive experiments on two public datasets for Autism Spectrum Disorder (ASD) and Attention Deficit Hyperactivity Disorder (ADHD) demonstrate that MCM-GCN outperforms other competing methods, with an accuracy of 92.88% for ASD and 76.55% for ADHD.</p><p><strong>Conclusion: </strong>The MCM-GCN framework integrates individual-level and population-level analyses, offering a comprehensive perspective for neurodevelopmental disorder diagnosis, significantly improving diagnostic accuracy while identifying key indicators.</p><p><strong>Significance: </strong>These findings highlight the potential of the MCM-GCN for imaging-assisted diagnosis of neurodevelopmental diseases, advancing interpretable deep learning in medical imaging analysis.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145212283","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 Integrated Rigid-Flexible Body Dynamic Approach to Computationally Efficient Musculoskeletal Modeling and Muscle Recruitment Simulation of the Lumbosacral Spine and Torso.","authors":"Siril Teja Dukkipati, Mark Driscoll","doi":"10.1109/TBME.2025.3617301","DOIUrl":"https://doi.org/10.1109/TBME.2025.3617301","url":null,"abstract":"<p><strong>Objective: </strong>In silico biomechanical models of the spine traditionally follow either rigid body dynamic (RBD) modeling (multibody modeling) or finite element (FE) modeling techniques. While RBD models lack robust representation for flexible tissues, FE models are computationally expensive. This study proposes an integrated rigid-flexible body dynamic (RFBD) architecture to address these limitations, and develops a full-torso human model, focusing spinal mechanical stability.</p><p><strong>Methods: </strong>The model consisted of L1-L5 lumbar vertebrae, pelvis, sacrum, a lumped thoracic spine with ribcage as rigid bodies, while the intervertebral discs (IVDs), abdominal cavity and thoracolumbar fascia (TLF) were modeled as deformable reduced-order flexible bodies. Spinal ligaments were represented as nonlinear tension-only springs, while the musculature was modeled as tension-only forces. Level-by-level spinal stiffness was validated under pure flexion moments up to 7.5 Nm against literature studies. The reduced-order implementation was also validated against an identical FE model. Spinal stability contribution of different tissues in flexion was systematically evaluated using six on-off cases.</p><p><strong>Results: </strong>Passive spine segmental stiffness profiles matched well with ex vivo and in silico comparators. The RFBD method demonstrated strong agreement with the FE solver, while significantly reducing computational demand. Stability analyses highlighted the role of intra-abdominal pressure in spinal unloading and generation of compressive loads along the spinal curvature through muscle recruitment.</p><p><strong>Conclusion: </strong>This parametric, fast-solving, high-fidelity spine simulation platform could be a useful biomechanical tool for spine researchers.</p><p><strong>Significance: </strong>A novel human torso model with integrated rigid and flexible bodies was presented in this study, providing insights into mechanical spine stability.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145212295","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":"Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulation.","authors":"Richard Lee Lai, Jen-Cheng Hou, I-Chun Chern, Kuo-Hsuan Hung, Yi-Ting Chen, Mandar Gogate, Tughrul Arslan, Amir Hussain, Chii-Wann Lin, Yu Tsao","doi":"10.1109/TBME.2025.3610284","DOIUrl":"https://doi.org/10.1109/TBME.2025.3610284","url":null,"abstract":"<p><strong>Objective: </strong>Individuals with hearing impairments face challenges in their ability to comprehend speech, particularly in noisy environments. This study explores the effectiveness of audio-visual speech enhancement (AVSE) in improving the intelligibility of vocoded speech in cochlear implant (CI) simulations.</p><p><strong>Methods: </strong>We propose a speech enhancement framework called Self-Supervised Learning-based AVSE (SSL-AVSE), which uses visual cues such as lip and mouth movements along with corresponding speech. Features are extracted using the AV-HuBERT model and refined through a bidirectional LSTM. Experiments were conducted using the Taiwan Mandarin speech with video (TMSV) dataset.</p><p><strong>Results: </strong>Objective evaluations showed improvements in PESQ from 1.43 to 1.67 and in STOI from 0.70 to 0.74. NCM scores increased by up to 87.2% over the noisy baseline. Subjective listening tests further demonstrated maximum gains of 45.2% in speech quality and 51.9% in word intelligibility.</p><p><strong>Conclusion: </strong>SSL-AVSE consistently outperforms AOSE and conventional AVSE baselines. Listening tests with statistically significant results confirm its effectiveness. In addition to its strong performance, SSL-AVSE demonstrates cross-lingual generalization: although it was pretrained on English data, it performs effectively on Mandarin speech. This finding highlights the robustness of the features extracted by a pretrained foundation model and their applicability across languages.</p><p><strong>Significance: </strong>To the best of our knowledge, no prior work has explored the application of AVSE to CI simulations. This study provides the first evidence that incorporating visual information can significantly improve the intelligibility of vocoded speech in CI scenarios.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145212333","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":"Effect of nearby Metals on Electro-Quasistatic Human Body Communication.","authors":"Samyadip Sarkar, Arunashish Datta, David Yang, Mayukh Nath, Shovan Maity, Shreyas Sen","doi":"10.1109/TBME.2025.3616233","DOIUrl":"https://doi.org/10.1109/TBME.2025.3616233","url":null,"abstract":"<p><p>In recent decades, Human Body Communication (HBC) has emerged as a promising alternative to traditional radio wave communication, utilizing the body's conductive properties for low-power connectivity among wearables. This method harnesses the human body as an energy-efficient channel for data transmission within the Electro-Quasistatic (EQS) frequency range, paving the way for advancements in Human-Machine Interaction (HMI). While previous research has noted the role of parasitic return paths in capacitive EQS-HBC, the influence of surrounding metallic objects on these paths-critical for EQS wireless signaling-has not been thoroughly investigated. This paper addresses this gap through a structured approach, analyzing how various conducting objects, ranging from non-grounded (floating) and grounded metals to enclosed metallic environments such as elevators and cars, affect the performance of the body-communication channel. We present a theoretical framework supported by Finite Element Method (FEM)-based simulations and experiments with wearable devices. Our findings reveal that metallic objects within $sim$20 cm of the devices can reduce transmission loss by $sim$10 dB. When the device's ground connects to a grounded metallic object, channel gain can increase by at least 20 dB. Additionally, the contact area during touch-based interactions with grounded metals depicts contact impedance-dependent high-pass channel characteristics. The proximity to metallic objects enhances variability within a critical distance, with grounded metals having an overall higher impact than floating ones. These insights are crucial for improving the reliability of body-centric communication links, thereby supporting applications in healthcare, consumer electronics, defense, and industrial sectors.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145206256","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":"Cardiac Microanatomy Imaging Using Forward-viewing Optical Coherence Tomography Endoscope.","authors":"David L Vasquez, Franziska Einmuller, Ines Latka, Kanchan Kulkarni, Nestor Pallares-Lupon, Marion Constantin, James Marchant, Virginie Loyer, Stephane Bloquet, Dounia El Hamrani, Jerome Naulin, Wolfgang Drexler, Jurgen Popp, Angelika Unterhuber, Marco Andreana, Richard D Walton, Iwan W Schie","doi":"10.1109/TBME.2025.3616493","DOIUrl":"https://doi.org/10.1109/TBME.2025.3616493","url":null,"abstract":"<p><strong>Objective: </strong>Due to limitations in current imaging technologies detecting subtle cardiac microstructural changes that can lead to sudden cardiac death is a significant clinical challenge. To address this problem, we developed a forward-viewing optical coherence tomography (OCT) endoscope for the detection of relevant cardiac microstructures in the subendocardium, including Purkinje fibers, scar tissue, surviving myocytes, and adipose tissue.</p><p><strong>Methods: </strong>An endoscopic probe based on the scanning fiber principle was developed for OCT measurements in contact. The probe was evaluated in freshly excised ovine hearts exhibiting chronic myocardial infarction. Relevant regions within the cardiac chamber were measured, and distinctive microstructures were identified, characterized, and subsequently corroborated using Masson's trichrome staining. The volumetric imaging data were used to train a convolutional neural network (CNN) to detect Purkinje fibers, enabling the reconstruction of their 3D morphology.</p><p><strong>Results: </strong>We were able to distinguish between healthy myocardium, fibrotic remodeling, and critical elements of the cardiac conduction system. Our findings demonstrate the capability of this technology to provide detailed images of cardiac microstructures in large mammal hearts.</p><p><strong>Conclusion: </strong>A novel application of forward-viewing endoscopic OCT in cardiology is demonstrated by visualizing cardiac microstructures within the subendocardium at depths accessible by optical imaging modalities.</p><p><strong>Significance: </strong>By enhancing visualization at the cellular level, this method may contribute to a better understanding of cardiac physiology and pathology, potentially extending future diagnostic and therapeutic strategies.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145206313","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 Noise-Robust Model-Based Approach to T-Wave Amplitude Measurement and Alternans Detection.","authors":"Zuzana Koscova, Amit Shah, Ali Bahrami Rad, Qiao Li, Gari D Clifford, Reza Sameni","doi":"10.1109/TBME.2025.3616055","DOIUrl":"https://doi.org/10.1109/TBME.2025.3616055","url":null,"abstract":"<p><strong>Objective: </strong>T-wave alternans (TWA) is a potential marker for sudden cardiac death, but its reliable analysis is often constrained to noise-free environments, limiting its utility in real-world settings. We explore model-based T-wave estimation to mitigate the impact of noise on TWA level.</p><p><strong>Methods: </strong>Detection was performed using a previous surrogate-based method as a benchmark and a new method based on a Markov model state transition matrix (STM). These were combined with a Modified Moving Average (MMA) method and polynomial T-wave modeling to enhance noise robustness. Methods were tested across a wide range of signal-to-noise ratios (SNRs), from -5 to 30 dB, and different noise types: baseline wander (BW), muscle artifacts (MA), electrode movement (EM), and respiratory modulation. Synthetic ECGs with known TWA levels were used: 0 $bm mu$V for TWA-free and 30-72 $bm mu$V for TWA-present signals.</p><p><strong>Results: </strong>T-wave modeling improved estimation accuracy under noisy conditions. With EM noise at SNRs of -5 and 5 dB, mean absolute error (MAE) dropped from 62 to 49 $bm mu$V and 27 to 25 $bm mu$V, respectively (Mann-Whitney-U test, $bm {p < 0.05}$) with modeling applied. Similar improvements were seen with MA noise: MAE dropped from 100 to 70 $bm mu$V and 26 to 23 $bm mu$V. In detection, the STM method achieved an F1-score of 0.92, outperforming the surrogate-based method (F1 = 0.81), though both struggled under EM noise at -5 dB. Importantly, beyond SNR, detection performance depended on the number of beats analyzed.</p><p><strong>Conclusion: </strong>These findings show that combining model-based estimation with STM detection significantly improves TWA analysis under noise, supporting its application in ambulatory and wearable ECG monitoring.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.5,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145199180","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}