IEEE Transactions on Biomedical Engineering最新文献

{"title":"A Multi-modality Fusion Model based on Dual-task Measurement for the Automatic Detection of Early-stage Cognitive Impairment.","authors":"Shuqiong Wu, Jiaqing Liu, Akos Godo, Fumio Okura, Manabu Ikeda, Shunsuke Sato, Maki Suzuki, Yuto Satake, Daiki Taomoto, Masahiro Hata, Yasushi Yagi","doi":"10.1109/TBME.2025.3582269","DOIUrl":"https://doi.org/10.1109/TBME.2025.3582269","url":null,"abstract":"<p><strong>Objective: </strong>The aim of this research is to develop a simple automated screening approach for earlystage cognitive impairment with high performance.</p><p><strong>Method: </strong>Our approach is based on the dual-task paradigm, where individuals perform two tasks simultaneously, typically a physical task combined with a cognitive task. In this study, we developed a dual-task system capable of collecting gait data, cognitive scores, and EEG (electroencephalography) signals within a single five-minute measurement. EEG data were recorded while the individual performs both gait and cognitive tasks simultaneously. To improve overall accuracy, we introduced a novel fusion algorithm with an innovative loss function to integrate gait, cognitive scores, and EEG modalities. In our fusion model, we employ cross-attention mechanisms to capture implicit relationships among the three modalities. Furthermore, our proposed loss function minimizes the overlap between different modalities to maximize their complementary contributions.</p><p><strong>Results: </strong>The experimental results validate the effectiveness of both the proposed fusion model and the new loss function. The proposed approach outperforms existing methods in nearly all conditions, achieving an overall performance of AUC: 0.9845, sensitivity: 0.9659, and specificity: 0.9535. Furthermore, compared with other methods, our approach demonstrates a relatively superior cross fold stability and sensitivity-specificity balance.</p><p><strong>Conclusion: </strong>This study presents an effective multi-modality fusion framework for early-stage cognitive impairment screening. The experimental results confirm the validity and robustness of the proposed algorithm.</p><p><strong>Significance: </strong>The proposed algorithm, supported by comprehensive analysis, facilitates early detection of cognitive impairment, ultimately contributing to the prevention and treatment of dementia.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144474999","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":"AI-based identification of head impact locations, speeds, and force based on head kinematics simulations.","authors":"Xianghao Zhan, Yuzhe Liu, Nicholas J Cecchi, Jessica Towns, Ashlyn A Callan, Olivier Gevaert, Michael M Zeineh, David B Camarillo","doi":"10.1109/TBME.2025.3581171","DOIUrl":"https://doi.org/10.1109/TBME.2025.3581171","url":null,"abstract":"<p><strong>Objective: </strong>With the development of wearable sensors, head kinematics data have become widely available. However, key impact information-such as impact direction, speed, and force-which is crucial for helmet development, is still not being directly measured. This study presents a deep learning model designed to accurately predict these head impact parameters from head kinematics during helmeted impacts.</p><p><strong>Methods: </strong>Leveraging a dataset of 16,000 simulated helmeted head impacts using the Riddell helmet finite element model, we implemented a Long Short-Term Memory (LSTM) network to process the head kinematics: linear accelerations and angular velocities.</p><p><strong>Results: </strong>In the simulated dataset, the models accurately predict the impact information describing impact direction, speed, and the impact force profile with $R^{2}$ exceeding 70% for all tasks. Further validation was conducted using an on-field dataset recorded by instrumented mouthguards and videos, consisting of 79 head impacts in which the impact location can be clearly identified. The deep learning model significantly outperformed existing methods, achieving a 79.7% accuracy in identifying impact locations, compared to lower accuracies with traditional methods (the highest accuracy of existing methods is 49.4%).</p><p><strong>Conclusion: </strong>The precision on simulations underscores the model's potential in enhancing helmet design and safety in sports by providing more accurate impact data. Future studies should test the models across various helmets and sports on large in vivo datasets to validate the accuracy of the models, employing techniques like transfer learning to broaden its effectiveness.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333025","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":"IEEE Transactions on Biomedical Engineering Information for Authors","authors":"","doi":"10.1109/TBME.2025.3572016","DOIUrl":"https://doi.org/10.1109/TBME.2025.3572016","url":null,"abstract":"","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 7","pages":"C3-C3"},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11044993","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144322989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Negative Impedance Converter Design to Enhance Capacitive Conduction Through a Neurostimulator Electrode Interface.","authors":"Ege Iseri, Manjunath Machnoor, Thanh D Nguyen, Constantine Sideris, Kimberly K Gokoffski, Gianluca Lazzi","doi":"10.1109/TBME.2025.3581537","DOIUrl":"https://doi.org/10.1109/TBME.2025.3581537","url":null,"abstract":"<p><strong>Objective: </strong>With the growing interest in electric field-induced neuromodulation for clinical applications, optimizing circuitry and stimulation parameters is crucial for effective therapy. Studies have shown successful neuroregeneration, neuroprotection, and neuronal activation in vitro when electric fields exceed a certain threshold. However, clinical translation remains challenging, as stimulation amplitudes are often constrained by patient tolerance. Strategies that enhance charge delivery per phase within safety limits can improve the efficacy of these techniques.</p><p><strong>Approach: </strong>This paper presents a method to reduce the electrode-tissue interface time constant by incorporating a negative resistance circuit to lower the series resistance and an RC circuit to reduce the equivalent capacitance in a Thevenin model of the interface. By targeting the capacitive conduction phase with higher amplitudes, a voltage-controlled stimulator can deliver greater charge while remaining within tolerance limits. The proposed circuit models are validated in vivo by assessing the stimulation tolerance of rats at the optic nerve.</p><p><strong>Main results: </strong>The proposed circuits connected in series with a two-electrode stimulator effectively reduced the time constant of the current waveform, shifting the magnitude response toward higher frequencies in Bode analysis. In vivo experiments confirmed that animals tolerated, on average, 20% greater charge injection within the first 200 μs of a rectangular pulse-the interval where capacitive charge transfer dominates over faradaic processes.</p><p><strong>Significance: </strong>Enhancing voltage-controlled neurostimulators with external circuits is a promising approach to overcoming amplitude limitations in clinical neurostimulation. As electrotherapy requires aminimum electric field amplitude for efficacy, increasing patient tolerance can improve treatment success rates.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333024","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":"IEEE Transactions on Biomedical Engineering Handling Editors Information","authors":"","doi":"10.1109/TBME.2025.3572018","DOIUrl":"https://doi.org/10.1109/TBME.2025.3572018","url":null,"abstract":"","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 7","pages":"C4-C4"},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11044982","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144323229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In Vivo Classification of Oral Lesions Using Electrical Impedance Spectroscopy.","authors":"Sophie A Lloyd, Torri E Lee, Ethan K Murphy, Allaire F Doussan, Jacob P Thones, Darcy A Kerr, Joseph A Paydarfar, Ryan J Halter","doi":"10.1109/TBME.2025.3581465","DOIUrl":"https://doi.org/10.1109/TBME.2025.3581465","url":null,"abstract":"<p><strong>Objective: </strong>To evaluate a new non-invasive, handheld Electrical Impedance Spectroscopy (EIS) device for assessing oral lesions in real-life surgical scenarios.</p><p><strong>Methods: </strong>A custom-designed probe with a 33-electrode sensor array was used to collect impedance measurements across multiple frequencies (100 Hz - 100 kHz) from non-consecutive patients undergoing surgical resection of oral cancer. In vivo EIS measurements were recorded from lesion and healthy tissue surfaces before resection, with no clinical decisions based on impedance data.</p><p><strong>Results: </strong>The study included 26 participants (median [IQR] age, 64.3 [59 - 70] years; 11 (42%) female) with oral squamous cell carcinoma. Cancerous tissue was found to have significantly lower resistance and reactance than healthy tissue (p<0.0001). Tissue classification using the permittivity at 40 kHz showed the highest accuracy (88%) with an AUC of 0.88. Multiple impedance parameters achieved AUCs >0.85 for differentiating healthy from malignant tissue. Conclusion & Significance: The study indicates that EIS can effectively differentiate between healthy and cancerous oral mucosa through rapid, non-invasive intraoperative measurements. The data processing pipeline developed demonstrates success in maintaining high data quality amidst the external disturbances presented in intraoperative data collection.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333027","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":"From Frequency to Temporal: Three Simple Steps Achieve Lightweight High-Performance Motor Imagery Decoding.","authors":"Yuan Li, Diwei Su, Xiaonan Yang, Xiangcun Wang, Hongxi Zhao, Jiacai Zhang","doi":"10.1109/TBME.2025.3579528","DOIUrl":"https://doi.org/10.1109/TBME.2025.3579528","url":null,"abstract":"<p><strong>Objective: </strong>To address the challenges of high data noise and substantial model computational complexity in Electroencephalography (EEG)-based motor imagery decoding, this study aims to develop a decoding method with both high accuracy and low computational cost.</p><p><strong>Methods: </strong>First, frequency domain analysis was performed to reveal the frequency modeling patterns of deep learning models. Utilizing prior knowledge from brain science regarding the key frequency bands for motor imagery, we adjusted the convolution kernels and pooling sizes of EEGNet to focus on effective frequency bands. Subsequently, a residual network was introduced to preserve high-frequency detailed features. Finally, temporal convolution modules were used to deeply capture temporal dependencies, significantly enhancing feature discriminability.</p><p><strong>Results: </strong>Experiments were conducted on the BCI Competition IV 2a and 2b datasets. Our method achieved average classification accuracies of 86.23% and 86.75% respectively, surpassing advanced models like EEG-Conformer and EEG-TransNet. Meanwhile, the Multiply-accumulate operations (MACs) were 27.16M, a reduction of over 50% compared to the comparison models, and the Forward/Backward Pass Size was 14.33MB.</p><p><strong>Conclusion: </strong>By integrating prior knowledge from brain science with deep learning techniques-specifically frequency domain analysis, residual networks, and temporal convolutions-it is possible to effectively improve the accuracy of EEG motor imagery decoding while substantially reducing model computational complexity.</p><p><strong>Significance: </strong>This paper employs the simplest and most fundamental techniques in its design, highlighting the critical role of brain science knowledge in model development. The proposed method demonstrates broad application potential.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333026","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":"IEEE Engineering in Medicine and Biology Society Publication Information","authors":"","doi":"10.1109/TBME.2025.3571974","DOIUrl":"https://doi.org/10.1109/TBME.2025.3571974","url":null,"abstract":"","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"72 7","pages":"C2-C2"},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11044977","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144323079","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rapid 3D Saturation Transfer Imaging for Simultaneous Phosphocreatine and Glycogen Mapping in Human Muscle.","authors":"Xi Xu, Xinran Chen, Yuanyuan Liu, Chongxue Bie, Hao Wu, Siqi Cai, Sen Jia, Lin Chen, Dong Liang, Hairong Zheng, Yang Zhou, Yanjie Zhu","doi":"10.1109/TBME.2025.3581341","DOIUrl":"https://doi.org/10.1109/TBME.2025.3581341","url":null,"abstract":"<p><strong>Objective: </strong>Phosphocreatine (PCr) and glycogen are key metabolites underpinning the skeletal muscle contractions. Simultaneous 3D imaging of these metabolites is valuable for understanding heterogeneous energetic events. While saturation transfer (ST) MRI can detect metabolites, 3D ST acquisition generally requires long scan times. We developed a rapid, high-resolution 3D scanning scheme for simultaneous quantification of PCr and glycogen.</p><p><strong>Methods: </strong>A 3D sequence was implemented on a 5 T MR scanner, using a continuous-wave saturation pulse and golden-angle stack-of-stars readouts. A patch-based low-rank algorithm was incorporated to reduce scan time. The sensitivity of sequence to concentration variations was validated in phantom experiments, and metabolite distribution was assessed in vivo. Furthermore, exercise protocols were employed to investigate metabolic heterogeneity.</p><p><strong>Results: </strong>The optimized acquisition strategy reduced the scan time to 26.7% of full sampling. Phantom studies showed a linear correlation between contrast signals and metabolite concentrations, in-vivo studies demonstrated uniform PCr and glycogen distribution across slices. Post-exercise, PCr and glycogen depletion was clearly observed.</p><p><strong>Conclusion and significance: </strong>The 3D rapid ST imaging framework achieves 100 mm coverage of skeletal muscle in 11.2 minutes, showing the potential to monitor muscle physiological processes.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144333028","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":"Camera-based Bipedal Plantar Pulse Transit Time Difference Measurement for Lower Limb Arterial Stenosis Detection.","authors":"Zhiyuan Xu, Shuhan Yi, Yukai Huang, Dongmin Huang, Zi Luo, Ningbo Zhao, Wenjin Wang","doi":"10.1109/TBME.2025.3580446","DOIUrl":"https://doi.org/10.1109/TBME.2025.3580446","url":null,"abstract":"<p><p>Peripheral arterial disease (PAD) can lead to severe foot problems, including claudication and amputation in extreme cases. Currently, clinical diagnosis primarily relies on costly and cumbersome methods like spectral Doppler ultrasound and Ankle-Brachial index (ABI). This highlights the urgent need for a low-cost and convenient screening approach. The lower extremity arterial stenosis caused by PAD leads to a delay in pulse wave transmission from the heart to the feet. This study proposes a novel PAD screening method, the bipedal plantar pulse transit time difference (PTTD), calculated as the time difference between photoplethysmographic (PPG) signals extracted from RGB videos of the feet. A simulation experiment was conducted on 19 healthy adult subjects, in which five different vascular obstruction conditions (i.e., PAD degrees) were simulated by applying varying pressures to the calf. The experimental results show that PTTD achieved 90.53% accuracy in PAD-simulation detection and 80.00% in five-class PAD-simulation grading, offering improvements of 10.53% and 28.42% over the baseline perfusion index (PI)-based detection and grading models, respectively. Additionally, we collected plantar video recordings from 10 PAD patients at the Department of Ultrasound in a hospital, demonstrating the feasibility in real clinical settings. This indicates that PTTD measured between bipedal plantars exhibits high sensitivity to vascular obstruction and holds promise as an efficient tool for PAD screening.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144325537","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}