IEEE Transactions on Biomedical Engineering最新文献

{"title":"Fast and Stable Neonatal Brain MR Imaging Using Integrated Learned Subspace Model and Deep Learning.","authors":"Ziwen Ke, Yue Guan, Tianyao Wang, Huixiang Zhuang, Zijun Cheng, Yunpeng Zhang, Jing-Ya Ren, Su-Zhen Dong, Yao Li","doi":"10.1109/TBME.2025.3541643","DOIUrl":"https://doi.org/10.1109/TBME.2025.3541643","url":null,"abstract":"<p><strong>Objective: </strong>To enable fast and stable neonatal brain MR imaging by integrating learned neonate-specific subspace model and model-driven deep learning.</p><p><strong>Methods: </strong>Fast data acquisition is critical for neonatal brain MRI, and deep learning has emerged as an effective tool to accelerate existing fast MRI methods by leveraging prior image information. However, deep learning often requires large amounts of training data to ensure stable image reconstruction, which is not currently available for neonatal MRI applications. In this work, we addressed this problem by utilizing a subspace model-assisted deep learning approach. Specifically, we used a subspace model to capture the spatial features of neonatal brain images. The learned neonate-specific subspace was then integrated with a deep network to reconstruct high-quality neonatal brain images from very sparse k-space data.</p><p><strong>Results: </strong>The effectiveness and robustness of the proposed method were validated using both the dHCP dataset and testing data from four independent medical centers, yielding very encouraging results. The stability of the proposed method has been confirmed with different perturbations, all showing remarkably stable reconstruction performance. The flexibility of the learned subspace was also shown when combined with other deep neural networks, yielding improved image reconstruction performance.</p><p><strong>Conclusion: </strong>Fast and stable neonatal brain MR imaging can be achieved using subspace-assisted deep learning with sparse sampling. With further development, the proposed method may improve the practical utility of MRI in neonatal imaging applications.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143614778","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 Novel NICU Sleep State Stratification: Multiperspective Features, Adaptive Feature Selection and Ensemble Model.","authors":"Muhammad Irfan, Abdulhamit Subasi, Zhenning Tang, Laishuan Wang, Yan Xu, Chen Chen, Tomi Westurlund, Wei Chen","doi":"10.1109/TBME.2025.3549584","DOIUrl":"https://doi.org/10.1109/TBME.2025.3549584","url":null,"abstract":"<p><p>The examination of sleep patterns in newborns, particularly premature infants, is crucial for understanding neonatal development. This study presents an automated multi-sleep state classification approach for infants in neonatal intensive care units (NICU) using multiperspective feature extraction methodologies and machine learning to assess their neurological and physical development. The datasets for this study were collected from Children's Hospital Fudan University, Shanghai and consist of electroencephalography (EEG) recordings from two datasets, one comprising 64 neonates and the other 19 neonates. The proposed study involves six major phases: data collection, data annotation, preprocessing, multi-perspective feature extraction, adaptive feature selection, and classification. During the preprocessing phase, noise reduction is achieved using the multi-scale principal component analysis (MSPCA) method. From each epoch of eight EEG channels, a diverse ensemble of 1,976 features is extracted. This extraction employs a combination of stationary wavelet transform (SWT), flexible analytical wavelet transform (FAWT), spectral features based on α, β, θ, and δ brain waves, and temporal features refined through adaptive feature algorithm. In terms of performance, the proposed approach demonstrates significant improvements over existing studies. Using a single EEG channel, the model achieves accuracy of 81.45% and a Kappa score of 71.75%. With four channels, these metrics increase to 83.71% accuracy and a 74.04% Kappa score. Furthermore, utilizing all eight channels, the mean accuracy reaches to 85.62%, and the Kappa score rises to 76.30%. To evaluate the model's effectiveness, a leave-one-subject-out cross-validation method is employed. This thorough analysis validates the reliability of the classification approach. This makes it a promising method for monitoring and assessing sleep patterns in neonates.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604640","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":"Design of Magnetic Actuated Capsule Robot for Liquid Sampling.","authors":"Shuo Zhang, Shaohui Song, Xinkai Yu, Shuang Song, Lihai Zhang","doi":"10.1109/TBME.2025.3550179","DOIUrl":"10.1109/TBME.2025.3550179","url":null,"abstract":"<p><strong>Objective: </strong>This study aims to introduce a biopsy capsule robot based on the negative pressure suction principle to achieve liquid sampling in the digestive tract.</p><p><strong>Methods: </strong>The proposed capsule robot is designed with a magnetic spring configuration. By controlling the direction of an external magnetic field, the suction port can be aligned with the target sampling area. The sampling operation can then be achieved by increasing the external field to start the magnetic spring and a negative pressure can be generated to achieve the liquid sampling. Moreover, a locking mechanism is designed to prevent the magnetic spring from retracting, ensuring that the collected liquid is not squeezed out.</p><p><strong>Results: </strong>The capsule robot prototype has dimensions of 16.3mm × 24.4mm. Both phantom and in-vitro experiments have been carried out. Results showed that it can sample liquids with viscosities ranging from 0.7mPa s to 200mPa s and absorb up to 0.24ml liquid. Additionally, the sealing of the capsule also meets clinical requirements.</p><p><strong>Conclusion: </strong>The experimental results indicate that the designed capsule robot can satisfy the clinical requirements for liquid sampling within the digestive tract.</p><p><strong>Significance: </strong>This study has designed and developed a micro capsule robot in the digestive tract, which can achieve safe and efficient liquid sampling operations. The proposed robot can benefit the clinical diagnosis of digestive diseases, especially in the small intestine.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604641","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":"Human-Robot Shared Control for Osteotomy Procedure.","authors":"Elisa Iovene, Lorenzo Casadio, Junling Fu, Francesco Costa, Giancarlo Ferrigno, Elena De Momi","doi":"10.1109/TBME.2025.3549867","DOIUrl":"10.1109/TBME.2025.3549867","url":null,"abstract":"<p><p>Spinal intervention can benefit from advancements in robotic systems, particularly in the field of Human-Robot Interaction (HRI). Despite the promising potential of these technologies, their integration into spine surgeries remains relatively limited, comprising mainly only selected procedures. Meanwhile, complex and time-consuming procedures, such as osteotomy, continue to be performed manually, significantly impacting surgeon workload and stress. This paper introduces a robotic system to assist surgeons during the drilling of the vertebral body. The system aims to reduce surgeon workload, enhance surgical precision, and ultimately contribute to improved patient outcomes in spinal surgeries. The system integrates a pre-planning tool for establishing the desired angle of correction, a virtual fixture-based impedance control algorithm enabling the robot to assist the user in following pre-defined cutting trajectories while safeguarding surrounding structures, and a navigation tool for enhanced guidance during the procedure. The proposed system is composed by a 7 Degree-of-Freedom robotic manipulator equipped with a drilling system attached to its end-effector. System accuracy was validated on 5 vertebral phantoms, achieving a tracking error of mm and mm, a margin error of mm and mm, and an angular alignment error of and for the sagittal and coronal planes, respectively.Additionally, the system's performance was evaluated with real porcine bone, with results demonstrating similar precision and robustness under realistic mechanical properties. A user Study was conducted to evaluate whether the proposed system effectively enhanced user performance and alleviated the users' workload compared to a manual control strategy. The results demonstrated reduced deviation from the desired path (Trajectory Error) and fewer instances of the system exceeding predetermined restricted areas (Boundary Violation) when using the proposed system. Additionally, participants rated the proposed system as less mentally and physically demanding in comparison to the traditional control strategy.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143596874","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":"Robot-mediated asymmetric connection between humans can improve performance without increasing effort.","authors":"Alessia Noccaro, Silvia Buscaglione, Jonathan Eden, Xiaoxiao Cheng, Nicola Di Stefano, Gio-Vanni Di Pino, Etienne Burdet, Domenico Formica","doi":"10.1109/TBME.2025.3548884","DOIUrl":"10.1109/TBME.2025.3548884","url":null,"abstract":"<p><p>Whether working together to move a table or supporting a child learning to ride a bike, physically connected individuals exchange haptic information to improve motor performance. However, this improvement occurs at the cost of additional effort for the more skilled partner.</p><p><strong>Objective: </strong>Here, we hypothesize that an asymmetric connection, consisting of a stiffer link to the less skilled partner and a more compliant link to the more skilled partner, could improve task performance without additional effort in collaborative tasks.</p><p><strong>Methods: </strong>Through computational modelling, we first tested this hypothesis on simulated human dyads tracking a common target. Then we experimentally validated the approach on a three degree-offreedom tracking task using two commercial robots as individual interfaces.</p><p><strong>Results: </strong>The simulation and experimental results confirm that using an asymmetric connection stiffness can improve joint performance without requiring additional effort from either partner compared to their solo effort.</p><p><strong>Conclusion: </strong>This suggests that the training of motor skills with a proficient partner may be enhanced through the use of robot-mediated asymmetric haptic connections.</p><p><strong>Significance: </strong>This approach may benefit joint tasks between individuals with clearly different motor abilities, such as a violin teacher demonstrating bowing techniques or a physical therapist assisting a patient during rehabilitation.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575654","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":"High-Resolution Whole-Brain Diffusion Tensor Imaging Exploiting Rapid Single-Slab 3D EPI Strategy.","authors":"Hyunkyung Maeng, HyungGoo R Kim, Roh Eul Yoo, Jaeseok Park","doi":"10.1109/TBME.2025.3541686","DOIUrl":"10.1109/TBME.2025.3541686","url":null,"abstract":"<p><strong>Objective: </strong>The purpose of this work is to investigate the feasibility of high-resolution whole-brain diffusion tensor imaging (DTI) using a rapid single-slab 3D pseudo-random EPI encoding strategy with physical constraints.</p><p><strong>Methods: </strong>A spin-echo-based diffusion-weighted imaging was modified to incorporate both single-slab 3D segmented EPI for high-resolution diffusion imaging and unsegmented EPI with short readouts for segment-specific motion-induced phase navigation. A physically constrained, segment-wise grouped phase encoding strategy is introduced, yielding a rapid, pseudo-random traversal of $k$ -space with smooth signal transition in local neighborhood even in the presence of magnetic field inhomogeneities. Numerical simulations and in vivo studies were performed to validate the feasibility of the proposed method for high-resolution whole-brain DTI.</p><p><strong>Results: </strong>The proposed method exhibits a robust point spread function (PSF) even in the presence of magnetic field inhomogeneities and produces a clear depiction of DTI parameter maps from highly incomplete measurements (reduction factor = 5.5). Furthermore, the proposed method outperforms the conventional 2D single-shot EPI and the conventional simultaneous multislice EPI due to its robust PSF, high encoding efficiency, and high signal gain.</p><p><strong>Conclusion: </strong>We successfully demonstrated the rapid single-slab 3D pseudo-random EPI encoding strategy with physical constraints, which makes it possible to achieve high-resolution (1.0mm$^{3}$) single-slab 3D DTI roughly in 14 minutes without apparent artifacts and noise.</p><p><strong>Significance: </strong>This is the first work that prospectively demonstrates a rapid, physically constrained pseudo-random EPI strategy for high-resolution single-slab whole-brain DTI.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575652","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":"Unobtrusive Sleep Health Assessment Using Impulse Radar: A Pilot Study in Older People.","authors":"Maowen Yin, Charalambos Hadjipanayi, Kiran K G Ravindran, Alan Bannon, Adrien Rapeaux, Ciro Della Monica, Tor Sverre Lande, Derk-Jan Dijk, Timothy Constandinou","doi":"10.1109/TBME.2025.3548780","DOIUrl":"https://doi.org/10.1109/TBME.2025.3548780","url":null,"abstract":"<p><strong>Objective: </strong>Ultra-wideband (UWB) radar technology has emerged as a promising alternative for creating portable and cost-effective in-home monitoring devices. Although there exists good evidence supporting its effectiveness in sleep monitoring, previous studies predominantly focus on younger, healthy participants. This research evaluates the applicability of commercial impulse UWB radar for sleep monitoring in older people and people with neurodegenerative disorders (NDDs).</p><p><strong>Methods: </strong>47 older people (mean age: 71.2 6.5, 18 with prodromal or mild Alzheimer's disease) participated in our overnight sleep trial with polysomnography (PSG) and UWB radar monitoring. Data processing based on multivariate empirical mode decomposition (MEMD) was employed to reconstruct cardiopulmonary activity and limb movements from radar signals. 29 features were extracted from the radar signals, and sleep stages were classified using a sequence-to-sequence neural network. Additionally, a cross-entropy-based approach was used to quantify uncertainties in the radar classification model and provide confidence in the classification.</p><p><strong>Results: </strong>The UWB radar system demonstrated high accuracy in detecting body movements, reconstructing respiratory patterns, and monitoring heart rate. For sleep stage classification, the results showed a Kappa coefficient of 0.63 and an average accuracy of 74.4% across wake, REM sleep, light sleep (N1 + N2), and deep sleep (N3) categories.</p><p><strong>Conclusion: </strong>The proposed method reliably monitors physiological changes during sleep, which suggests its potential as a cost-effective alternative to traditional sleep monitoring devices.</p><p><strong>Significance: </strong>The findings underscore the viability of UWB radar as a nonintrusive, forward-looking sleep assessment tool that could significantly benefit care for older people and people with neurodegenerative disorders.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143572946","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":"mmWave Radar for Sit-to-Stand Analysis: A Comparative Study with Wearables and Kinect.","authors":"Shuting Hu, Peggy Ackun, Xiang Zhang, Siyang Cao, Jennifer Barton Barton, Melvin G Hector, Mindy J Fain, Nima Toosizadeh","doi":"10.1109/TBME.2025.3548092","DOIUrl":"https://doi.org/10.1109/TBME.2025.3548092","url":null,"abstract":"<p><p>This study investigates a novel approach for analyzing Sit-to-Stand (STS) movements using millimeterwave (mmWave) radar technology, aiming to develop a noncontact, privacy-preserving, and all-day operational solution for healthcare applications. A 60GHz mmWave radar system was employed to collect radar point cloud data from 45 participants performing STS motions. Using a deep learning-based pose estimation model and Inverse Kinematics (IK), we calculated joint angles, segmented STS motions, and extracted clinically relevant features for fall risk assessment. The extracted features were compared with those obtained from Kinect and wearable sensors. While Kinect provided a reference for motion capture, we acknowledge its limitations compared to the gold-standard VICON system, which is planned for future validation. The results demonstrated that mmWave radar effectively captures general motion patterns and large joint movements (e.g., trunk), though challenges remain for more finegrained motion analysis. This study highlights the unique advantages and limitations of mmWave radar and other sensors, emphasizing the potential of integrated sensor technologies to enhance the accuracy and reliability of motion analysis in clinical and biomedical research. Future work will expand the scope to more complex movements and incorporate high-precision motion capture systems to further validate the findings.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143566940","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":"Acoustic Tweezers for Microscopy of Living Organisms.","authors":"K Sadeghian Esfahani, B Neff, A Roy, M Barekatain, E S Kim","doi":"10.1109/TBME.2025.3548557","DOIUrl":"10.1109/TBME.2025.3548557","url":null,"abstract":"<p><strong>Objective: </strong>Studying zebrafish embryos' growth through imaging them in their natural growth environment may reveal what has not been possible through the current imaging technique which uses mechanically-confining and nutrient-limiting gel, like agarose. This paper presents, for the first time, the imaging of live zebrafish embryos in their natural environment over 20 hours through acoustic tweezers capable of contactless trapping and precise manipulation via trapping without standing waves. The tweezers is shown to trap and hold a zebrafish embryo in its growth medium from 17 hours post fertilization (hpf) to 37 hpf under a Light-Sheet microscope for imaging. The continuous trapping and imaging reveal organ development, such as the tail, eyes, ears, and pigmentation. The method is safe, as evidenced by natural development, heartbeats, and tail movement.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143566938","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":"Deep Learning-Based Saturation Compensation for High Dynamic Range Multispectral Fluorescence Lifetime Imaging.","authors":"Hyeong Soo Nam, Dong Oh Kang, Jeongmoo Han, Jin Won Kim, Hongki Yoo","doi":"10.1109/TBME.2025.3548297","DOIUrl":"https://doi.org/10.1109/TBME.2025.3548297","url":null,"abstract":"<p><p>In multispectral fluorescence lifetime imaging (FLIm), achieving consistent imaging quality across all spectral channels is crucial for accurately identifying a wide range of fluorophores. However, these essential measurements are frequently compromised by saturation artifacts due to the inherently limited dynamic range of detection systems. To address this issue, we present SatCompFLImNet, a deep learning-based network specifically designed to correct saturation artifacts in multispectral FLIm, facilitating high dynamic range applications. Leveraging generative adversarial networks, SatCompFLImNet effectively compensates for saturated fluorescence signals, ensuring accurate lifetime measurements across various levels of saturation. Extensively validated with simulated and real-world data, SatCompFLImNet demonstrates remarkable capability in correcting saturation artifacts, improving signal-to-noise ratios, and maintaining fidelity of lifetime measurements. By enabling reliable fluorescence lifetime measurements under a variety of saturation conditions, SatCompFLImNet paves the way for improved diagnostic tools and a deeper understanding of biological processes, making it a pivotal advancement for research and clinical diagnostics in tissue characterization and disease pathogenesis.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143566939","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}