IEEE Transactions on Biomedical Engineering最新文献

{"title":"Deep Learning for EEG-Based Visual Classification and Reconstruction: Panorama, Trends, Challenges and Opportunities.","authors":"Wei Li, Penglu Zhao, Cheng Xu, Yingting Hou, Wenhao Jiang, Aiguo Song","doi":"10.1109/TBME.2025.3568282","DOIUrl":"https://doi.org/10.1109/TBME.2025.3568282","url":null,"abstract":"<p><p>Deep learning has significantly enhanced the research on the emerging issue of Electroencephalogram (EEG)-based visual classification and reconstruction, which has gained a growth of attention and concern recently. To promote the research progress, at this critical moment, a review work on the deep learning methodology for the issue becomes necessary and important. However, such a work seems absent in the literature. This paper provides the first review on EEG-based visual classification and reconstruction, whose contents can be categorized into the following four main parts: 1) comprehensively summarizing and systematically analyzing the representative deep learning methods from both feature encoding and decoding perspectives; 2) introducing the available benchmark datasets, describing the experimental paradigms, and displaying the method performances; 3) proposing the methodological essences and neuroscientific insights as well as the dynamic closed-loop interaction and promotion between them, which are potentially beneficial for technological innovations and academic progress; 4) discussing the potential challenges of current research and the prospective opportunities in future trends. We expect that this work can shed light on the technological directions and also enlighten the academic breakthroughs for the issue in the not-so-far future.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143985680","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 Quasi-Resonant System for High-Frequency Trans-Spinal Magnetic Stimulation (HF-TSMS).","authors":"Francesca Marturano, Don Straney, Micol Colella, Yin-Ching Iris Chen, Ilknur Ay, Giorgio Bonmassar","doi":"10.1109/TBME.2025.3568701","DOIUrl":"https://doi.org/10.1109/TBME.2025.3568701","url":null,"abstract":"<p><strong>Objective: </strong>We designed, developed, and tested a novel non-invasive system for high-frequency (HF) trans-spinal magnetic stimulation (TSMS).</p><p><strong>Methods: </strong>The system is based on a quasi-resonant pulse width modulation (PWM) design with customizable parameters, coupled with a custom figure-8 coil optimized for selective stimulation of spinal fibers. A key innovation is sequence-controlled zero current switching (SCZCS), which minimizes switching losses.</p><p><strong>Results: </strong>Through quasi-resonance, a capacitor bank canceled the coil inductance, enabling the generation of 10 kA current pulses with input voltages over three times lower than traditional magnetic stimulation methods. Preliminary rodent experiments, including electrophysiological recordings from the common peroneal nerve studies, demonstrated that the system's pulses reached the spinal cord. The HF-TSMS system operated safely, delivering HF stimulation without significant coil heating during experimental sessions.</p><p><strong>Conclusion: </strong>The proposed HF-TSMS system generated HF current pulses at lower cost, with reduced switching losses and higher efficiency.</p><p><strong>Significance: </strong>This system has the potential for integration into clinical practice as a safe and non-invasive treatment option for chronic pain management.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143963418","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":"Electrode Design for Internal Electric Field Delivery to Brain Tumors: Considering Electrical Power and Dynamic Field Shaping.","authors":"Erin Iredale, Lucas G Westerink, Abdulla Elsaleh, Vera Luo, Susanne Schmid, Matthew O Hebb, Terry M Peters, Eugene Wong","doi":"10.1109/TBME.2025.3567904","DOIUrl":"https://doi.org/10.1109/TBME.2025.3567904","url":null,"abstract":"<p><strong>Objective: </strong>Brain cancer treatment using low intensity electrotherapy techniques is gaining interest. Localized electric field delivery via an implanted array of electrodes, termed Intratumoral Modulation Therapy (IMT), was found efficacious against brain cancers preclinically. With prior IMT studies supporting the transition towards patient application, we consider optimizing the design of electrodes, such that power consumption is minimized while retaining tumor field coverage and field shaping capability.</p><p><strong>Methods: </strong>Cylindrical multi-contact electrodes were modelled with variable radius, spacing between contacts and contact length, and applied to spherical tumors ranging from 20-40 mm in diameter. Stimulation programming was optimized and the overall power analyzed for each design such that target coverage was maintained. To investigate the field shaping potential, designs were further optimized on 11 glioma patient MR images with irregular shaped tumors.</p><p><strong>Results: </strong>The IMT electrode parameters found to minimize power consumption were maximal electrode radius (0.8 mm) and minimal contact spacing (1 mm). Analysis of treatment plans on patient images found 4 mm contact length to minimize complexity (total number of contacts) while maintaining field shaping capability.</p><p><strong>Conclusion: </strong>In this study, electrodes were designed specifically for IMT that minimized power consumption while maintaining field coverage and shaping. This design was robust in its applicability to patient samples.</p><p><strong>Significance: </strong>Due to the complexity of dynamic IMT electric field delivery, the established planning system and the custom IMT hardware designed in this study are necessary precursors to human applications. With this work we are one step closer to treating patients with brain cancer.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144017803","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":"Machine learning methods to track dynamic facial function in facial palsy.","authors":"Akshita A Rao, Jacqueline J Greene, Todd P Coleman","doi":"10.1109/TBME.2025.3567984","DOIUrl":"https://doi.org/10.1109/TBME.2025.3567984","url":null,"abstract":"<p><strong>Objective: </strong>For patients with facial palsy, the wait for return of facial function and resulting vision risk from poor eye closure, difficulty speaking and eating from flaccid oral sphincter muscles, and psychological morbidity from the inability to smile or express emotions can be devastating. There are limited methods to assess ongoing facial nerve regeneration: clinicians rely on subjective descriptions, imprecise scales, and static photographs to evaluate facial functional recovery. We propose a more precise evaluation of dynamic facial function through video-based machine learning analysis to facilitate a better understanding of the sometimes subtle onset of facial nerve recovery and improve guidance for facial reanimation surgery.</p><p><strong>Methods: </strong>We present machine learning methods employing likelihood ratio tests, optimal transport theory, and Mahalanobis distances to: 1) assess the use of defined facial landmarks for binary classification of different facial palsy types; 2) identify regions of asymmetry and potential palsy during specific facial cues; and 3) quantify palsy severity and map it directly to widely used clinical scores, offering clinicians an objective way to assess facial nerve function.</p><p><strong>Results: </strong>Our results demonstrate that video analysis provides a significantly more accurate and detailed assessment of facial movements than previously reported.</p><p><strong>Conclusions: </strong>Our work allows for precise classification of facial palsy types, identification of asymmetric regions, and assessment of palsy severity.</p><p><strong>Significance: </strong>This project enables clinicians to have more accurate and timely information to make decisions for facial reanimation surgery, which will have drastic consequences on the quality of life for affected patients.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144002848","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":"Multi-Color Magnetic Particle Imaging Based on Superparamagnetic and Superferromagnetic Nanoparticles.","authors":"Lei Li, Chan Zhao, Jiesheng Tian, Qing Liu, Xin Feng, Jie Tian","doi":"10.1109/TBME.2025.3567127","DOIUrl":"https://doi.org/10.1109/TBME.2025.3567127","url":null,"abstract":"<p><strong>Objective: </strong>Magnetic Particle Imaging (MPI) is a tracer based biomedical imaging modality that enables quantitative visualization of magnetic nanoparticles (MNPs). Current MPI technology mainly focuses on single-channel imaging. In recent years, the multi-color MPI has emerged, allowing for the simultaneous imaging of multiple distinct tracers, significantly broadening MPI's application spectrum. For instance, multi-color MPI can concurrently visualize distinct cell types or molecular markers, facilitating the investigation of spatio-temporal interactions between cells or biomolecules. However, existing multi-color MPI techniques use different superparamagnetic MNPs for imaging. Their similar magnetization responses limit the imaging effect when there is a large particle signal difference.</p><p><strong>Methods: </strong>In this study, we propose a semi-periodic x-space method to use superparamagnetic and superferromagnetic particles for multi-color MPI. The method takes advantage of their distinct coercivity characteristics, allowing for robust multi-color imaging without requiring iterative solving or any additional prior information beyond coercivity.</p><p><strong>Results: </strong>We validate the feasibility and robustness of the proposed multi-color method under conditions of low signal-to-noise ratio (5 dB) and high signal intensity ratios (16:1) through simulation and in vitro experiments. Furthermore, we showcase the in vivo imaging capability using a mouse tumor model to simultaneously visualize superparamagnetic and superferromagnetic MNPs within the tumor.</p><p><strong>Conclusion: </strong>We propose a method that can effectively and robustly reconstruct superparamagnetic and superferromagnetic MNPs simultaneously in MPI. Its performance has been rigorously validated through comprehensive simulations and experiments.</p><p><strong>Significance: </strong>The proposed method successfully leverages the coercivity characteristics of superparamagnetic and superferromagnetic MNPs, improving the performance of multi-color MPI.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143984446","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":"Volumetric medical image segmentation through dual self-distillation in U-shaped networks.","authors":"Soumyanil Banerjee, Nicholas Summerfield, Ming Dong, Carri Glide-Hurst","doi":"10.1109/TBME.2025.3566995","DOIUrl":"https://doi.org/10.1109/TBME.2025.3566995","url":null,"abstract":"<p><p>U-shaped networks and its variants have demonstrated exceptional results for medical image segmentation. In this paper, we propose a novel dual self-distillation (DSD) framework in U-shaped networks for volumetric medical image segmentation. DSD distills knowledge from the ground-truth segmentation labels to the decoder layers. Additionally, DSD also distills knowledge from the deepest decoder and encoder layer to the shallower decoder and encoder layers respectively of a single U-shaped network. DSD is a general training strategy that could be attached to the backbone architecture of any U-shaped network to further improve its segmentation performance. We attached DSD on several state-of-the-art U-shaped backbones, and extensive experiments on various public 3D medical image segmentation datasets (cardiac substructure, brain tumor and Hippocampus) demonstrated significant improvement over the same backbones without DSD. On average, after attaching DSD to the U-shaped backbones, we observed an increase of 2.82%, 4.53% and 1.3% in Dice similarity score, a decrease of 7.15 mm, 6.48 mm and 0.76 mm in the Hausdorff distance, for cardiac substructure, brain tumor and Hippocampus segmentation, respectively. These improvements were achieved with negligible increase in the number of trainable parameters and training time. Our proposed DSD framework also led to significant qualitative improvements for cardiac substructure, brain tumor and Hippocampus segmentation over the U-shaped backbones. The source code is publicly available at https://github.com/soumbane/DualSelfDistillation.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144019275","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":"Optoacousto-fluidics Based Optical Rotation Measure for Blood Glucose Sensing.","authors":"Swathi Padmanabhan, Sarikonda Aryan Shashank, Rajesh Srinivasan, Jaya Prakash","doi":"10.1109/TBME.2025.3566940","DOIUrl":"https://doi.org/10.1109/TBME.2025.3566940","url":null,"abstract":"<p><strong>Significance: </strong>Glucose sensing in deep tissue is challenging due to high light scattering and the optical properties of tissue constituents.</p><p><strong>Objective: </strong>We present a novel approach that integrates polarized light with optoacousto-fluidics based glucose sensing.</p><p><strong>Methods: </strong>A custom microfluidic chip mimicking blood vessel dimensions was developed to measure optical rotation via optoacoustic detection using polarized light (vertical and circular) at 1560 nm (near-infrared). The system reduces sample volume requirements while maintaining high sensitivity and accuracy. Experiments were performed using serum-like and human blood samples at a depth of 2 mm through whole blood. Flow dynamics was varied to assess their impact on measurement accuracy. Proof-of-concept studies included samples from diabetic and healthy volunteers.</p><p><strong>Results: </strong>Depth-resolved optoacoustic signals enabled accurate optical rotation quantification for glucose detection. Variations in flow velocity showed no significant effect, confirming system reliability under dynamic conditions. The system achieved a detection limit of 50 mg/dL in serum samples. Classification of diabetic and healthy samples reached an 88% prediction accuracy.</p><p><strong>Conclusion: </strong>This work demonstrates a low-volume, high-sensitivity method for glucose detection using polarized light and optoacousto-fluidics, with potential for real-time, non-invasive monitoring at tissue depths of 2-3 mm. It lays the foundation for advancing optical rotation-based glucose detection methodologies with significant implications for in-vivo sensing (at depths of 2-3 mm in skin).</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144010548","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":"Adaptive Cardiorespiratory Separation with Harmonic Models and Filters: The Case of Electrical Impedance Tomography.","authors":"Diogo F Silva, Thomas Muders, Sebastian Reinartz, Christian Putensen, Steffen Leonhardt","doi":"10.1109/TBME.2025.3566608","DOIUrl":"https://doi.org/10.1109/TBME.2025.3566608","url":null,"abstract":"<p><p>Cardiorespiratory monitoring methods are vital in clinical and personal healthcare contexts, continuously delivering comprehensive insights into patient health. Among them, electrical impedance tomography, a non-invasive imaging modality, uniquely enables spatially resolved, real-time monitoring of both cardiac and respiratory functions. However, separating cardiac and respiratory signals remains a challenge due to spectral and spatial overlap, heart-lung interactions and nonstationarity. Existing signal processing techniques face limitations in adaptiveness, harmonic overlap handling, and real-time feasibility, restricting their clinical adoption. This work introduces two novel adaptive model-based approaches derived from a harmonic framework inspired by source-filter theory: harmonic least-squares, a deterministic estimator; and harmonically-constrained filtering, which employs harmonic priors and noise covariance approximations towards optimal separation. These algorithms were systematically validated using extensive synthetic and real-world datasets across diverse clinical scenarios. Monte Carlo simulations with a dynamic synthesizer and machine learning surrogate models provided robust performance evaluations, with insights into algorithm behavior through accumulated local effect plots. The proposed methods demonstrated superior performance compared to state-of-the-art approaches and achieved real-time processing capability, making them promising for integration into medical devices. Despite these advancements, further improvements in noise modelling, performance guarantees, and processing efficiency remain potential areas for future development.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143993346","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":"Noise propagation and MP-PCA image denoising for high-resolution quantitative R₂^*, T₂^*, and magnetic susceptibility mapping (QSM).","authors":"Liad Doniza, Mitchel Lee, Tamar Blumenfeld-Katzir, Moran Artzi, Dafna Ben-Bashat, Orna Aizenstein, Dvir Radunsky, Fenella Kirkham, George Thomas, Rimona S Weil, Karin Shmueli, Noam Ben-Eliezer","doi":"10.1109/TBME.2025.3566561","DOIUrl":"https://doi.org/10.1109/TBME.2025.3566561","url":null,"abstract":"<p><p>: Quantitative Susceptibility Mapping (QSM) measures magnetic susceptibility of tissues, aiding in the detection of pathologies like traumatic brain injury, cerebral microbleeds, Parkinson's disease, and multiple sclerosis, through analysis of variations in substances such as iron and calcium. Despite its clinical value, using high-resolution QSM (voxel sizes < 1 mm3) reduces signal-to-noise ratio (SNR), which compromises diagnostic quality.</p><p><strong>Methods: </strong>Denoising of T₂^* -weighted (T₂^*) data was implemented using Marchenko-Pastur Principal Component Analysis (MP-PCA), allowing to enhance the quality of R₂^*, T₂^*, and QSM maps. Proof of concept of the denoising technique was demonstrated on a numerical phantom, healthy subjects, and patients with brain metastases and sickle cell anemia.</p><p><strong>Results: </strong>Effective and robust denoising was observed across different scan settings, offering higher SNR and improved accuracy. Noise propagation was analyzed between T₂^*w, R₂^*, and T₂^* values, revealing augmentation of noise in T₂^*w compared to R₂^* values.</p><p><strong>Conclusions: </strong>The use of MP-PCA denoising allows the collection of high resolution (∼0.5 mm3) QSM data at clinical scan times, without compromising SNR.</p><p><strong>Significance: </strong>The presented pipeline could enhance the diagnosis of various neurological diseases by providing higher-definition mapping of small vessels and of variations in iron or calcium.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143989392","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":"Analysis and Characterization of Capacitive Links for Biomedical Data Telemetry.","authors":"A N M Shahriyar Hossain, Pedram Mohseni, Hossein Miri Lavasani","doi":"10.1109/TBME.2025.3566667","DOIUrl":"https://doi.org/10.1109/TBME.2025.3566667","url":null,"abstract":"<p><p>: This paper presents a comprehensive analysis and characterization of capacitive wireless links, specifically designed for applications demanding high data throughput.</p><p><strong>Methods: </strong>The research delves into the various challenges associated with achieving high data-rates in tuned capacitive links, by first introducing the concept of bandwidthconstrained capacitive channel and its equivalent electrical model, followed by theoretical analysis of the link and the corresponding channel transfer function. Moreover, the impact of channel characteristics, noise and modulation scheme on the signal integrity is investigated, highlighting the limitations on the data throughput and proposing solutions to ensure high data throughput while maintaining an efficient power transfer. Ex vivo testing and computer simulations are performed to validate the theoretical models, assessing the performance of capacitive links at 7 MHz.</p><p><strong>Results: </strong>Extensive simulations and ex vivo measurements done on a capacitive link tuned for operation at 7 MHz, which results in highest reported data rate of 15 Mbps in a capacitive link, reveal consistent findings throughout the study. The theoretical predictions favoring phase-based modulations for high data throughput and energy efficient communications with high reliability is confirmed through ex vivo measurements.</p><p><strong>Conclusions: </strong>The paper concludes with recommendations for the choice of modulation in bandwidthconstrained capacitive channels based on the desired power and data transfer requirements.</p><p><strong>Significance: </strong>This research advances the biomedical telemetry by demonstrating the potential of capacitive links to meet the demanding requirements of highspeed data transmission in medical applications, paving the way for improved patient monitoring and therapeutic interventions.</p>","PeriodicalId":13245,"journal":{"name":"IEEE Transactions on Biomedical Engineering","volume":"PP ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143965192","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}