Bioengineering最新文献

{"title":"Resting-State Activity Changes Induced by tDCS in MS Patients and Healthy Controls: A Simultaneous tDCS rs-fMRI Study.","authors":"Marco Muccio, Giuseppina Pilloni, Lillian Walton Masters, Peidong He, Lauren Krupp, Abhishek Datta, Marom Bikson, Leigh Charvet, Yulin Ge","doi":"10.3390/bioengineering12060672","DOIUrl":"10.3390/bioengineering12060672","url":null,"abstract":"<p><p>Transcranial direct current stimulation (tDCS) is a safe, well-tolerated method of non-invasively eliciting cortical neuromodulation. It has gained recent interest, especially for its positive clinical outcomes in neurodegenerative diseases such as multiple sclerosis (MS). However, its simultaneous (during tDCS) and cumulative effects (following repeated tDCS sessions) on the regional brain activity during rest need further investigation, especially in MS. This study aims to elucidate tDCS' underpinnings, alongside its therapeutic impact in MS patients, using concurrent tDCS-MRI methods. In total, 20 MS patients (age = 48 ± 12 years; 8 males) and 28 healthy controls (HCs; age = 36 ± 15 years; 12 males) were recruited. They participated in a tDCS-MRI session, during which resting-state functional MRI (rs-fMRI) was used to measure the levels of the fractional amplitude of low-frequency fluctuations (fALFFs), which is an index of regional neuronal activity, before and during left anodal dorsolateral prefrontal cortex (DLPFC) tDCS (2.0 mA for 15 min). MS patients were then asked to return for an identical tDCS-MRI visit (follow-up) after 20 identical at-home tDCS sessions. Simultaneous tDCS-induced changes in fALFF are seen across cortical and subcortical areas in both HC and MS patients, with some regions showing increased and others decreased brain activity. In HCs, fALFF increased in the right pre- and post-central gyrus whilst it decreased in subcortical regions. Conversely, MS patients initially displayed increases in more posterior cortical regions but decreases in the superior and temporal cortical regions. At follow-up, MS patients showed reversed patterns, emphasizing significant cumulative effects of tDCS treatment upon brain excitation. Such long-lasting changes are further supported by greater pre-tDCS fALFFs measured at follow-up compared to baseline, especially around the cuneus. The results were significant after correcting for multiple comparisons (p-FDR < 0.05). Our study shows that tDCS has both simultaneous and cumulative effects on neuronal activity measured with rs-fMRI, especially involving major brain areas distant from the site of stimulation, and it is responsible for fatigue and cognitive and motor skills.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189455/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finite Element Analysis of Biomechanical Assessment: Traditional Bilateral Pedicle Screw System vs. Novel Reverse Transdiscal Screw System for Lumbar Degenerative Disc Disease.","authors":"Utpal K Dhar, Kamran Aghayev, Hadi Sultan, Saahas Rajendran, Chi-Tay Tsai, Frank D Vrionis","doi":"10.3390/bioengineering12060671","DOIUrl":"10.3390/bioengineering12060671","url":null,"abstract":"<p><p>The traditional bilateral pedicle screw system has been used for the treatment of various lumbar spine conditions including advanced degenerative disc disease. However, there is an ongoing need to develop more effective and less invasive techniques. The purpose of this study was to compare the traditional bilateral pedicle screw system (BPSS) with the novel reverse transdiscal screw system (RTSS) for lumbar disc degenerative disease. A 3D solid lumbar L1-L5 spine model was developed and validated based on a human CT scan. Fusions were simulated at L3-L4. The first scenario comprised a transforaminal lumbar interbody cage in combination with the bilateral pedicle screw-rod system (BPSS-TLIF). In the second scenario, the same TLIF cage was combined with reverse L3-L4 transdiscal screws (RTSS-TLIF). Testing parameters included range of motion (ROM) in three orthogonal axes, hardware (cage and screw) stress, and shear load resistance. The ROM of the surgical model was reduced by approximately 90% compared to the intact model at the fused level. The RTSS model demonstrated less ROM compared to the BPSS model at the fused level for all loading conditions. Overall, the RTSS model exhibited lower stress on both screws and cage compared with the BPSS model in all biomechanical testing conditions. The RTSS model also exhibited higher anterior and posterior shear load resistance than the BPSS model. In conclusion, the RTSS model proved superior to the BPSS model in all respects. These findings indicate that the RTSS could serve as a feasible option for patients undergoing lumbar fusion, especially for adjacent segment disease, potentially enhancing surgical outcomes for disc degeneration.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189082/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Changepoint Detection-Based General Methodology for Robust Signal Processing: An Application to Understand Preeclampsia's Mechanisms.","authors":"Patricio Cumsille, Felipe Troncoso, Hermes Sandoval, Jesenia Acurio, Carlos Escudero","doi":"10.3390/bioengineering12060675","DOIUrl":"10.3390/bioengineering12060675","url":null,"abstract":"<p><p>Motivated by illuminating the underlying mechanisms of preeclampsia, we develop a changepoint detection-based general and versatile methodology that can be applied to any experimental model, effectively addressing the challenges of high uncertainty produced by experimental interventions, intrinsic high variability, and rapidly and abruptly varying time dynamics in perfusion signals. This methodology provides a systematic and reliable approach for robust perfusion signal analysis. The main innovation of our methodology is a highly efficient automatic data processing system consisting of modular programming components. These components include a signal processing tool for optimal segmentation of perfusion signals by isolating their \"genuine\" vascular response to experimental interventions, and a novel and suitable normalization to evaluate this response concerning an experimental reference state, typically basal or pre-intervention. In this way, we can identify anomalies in an experimental group compared to a control group by disaggregating noise during the transitions just after experimental interventions. We have successfully applied our general methodology to perfusion signals measured from a preeclampsia-like syndrome model developed by our research group. Our findings revealed impaired brain perfusion in offspring from preeclampsia, particularly dysfunctional brain perfusion signals with inadequate perfusion signal vasoreactivity to thermal physical stimuli. This general methodology represents a significant step towards a systematic, accurate, and reliable approach to robust perfusion signals analysis across various experimental settings with diverse intervention protocols.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189793/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144493977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Innovative Artificial Intelligence Classification Model for Non-Ischemic Cardiomyopathy Utilizing Cardiac Biomechanics Derived from Magnetic Resonance Imaging.","authors":"Liqiang Fu, Peifang Zhang, Liuquan Cheng, Peng Zhi, Jiayu Xu, Xiaolei Liu, Yang Zhang, Ziwen Xu, Kunlun He","doi":"10.3390/bioengineering12060670","DOIUrl":"10.3390/bioengineering12060670","url":null,"abstract":"<p><p>Significant challenges persist in diagnosing non-ischemic cardiomyopathies (NICMs) owing to early morphological overlap and subtle functional changes. While cardiac magnetic resonance (CMR) offers gold-standard structural assessment, current morphology-based AI models frequently overlook key biomechanical dysfunctions like diastolic/systolic abnormalities. To address this, we propose a dual-path hybrid deep learning framework based on CNN-LSTM and MLP, integrating anatomical features from cine CMR with biomechanical markers derived from intraventricular pressure gradients (IVPGs), significantly enhancing NICM subtype classification by capturing subtle biomechanical dysfunctions overlooked by traditional morphological models. Our dual-path architecture combines a CNN-LSTM encoder for cine CMR analysis and an MLP encoder for IVPG time-series data, followed by feature fusion and dense classification layers. Trained on a multicenter dataset of 1196 patients and externally validated on 137 patients from a distinct institution, the model achieved a superior performance (internal AUC: 0.974; external AUC: 0.962), outperforming ResNet50, VGG16, and radiomics-based SVM. Ablation studies confirmed IVPGs' significant contribution, while gradient saliency and gradient-weighted class activation mapping (Grad-CAM) visualizations proved the model pays attention to physiologically relevant cardiac regions and phases. The framework maintained robust generalizability across imaging protocols and institutions with minimal performance degradation. By synergizing biomechanical insights with deep learning, our approach offers an interpretable, data-efficient solution for early NICM detection and subtype differentiation, holding strong translational potential for clinical practice.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189867/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Miniaturized Implantable Telemetry Biosensor for the Long-Term Dual-Modality Monitoring of Core Temperature and Locomotor Activity.","authors":"Wendi Shi, Hao Huang, Xueting Sun, Qihui Jia, Yu Zhou, Maohua Zhu, Mingqiang Tian, Zhuofan Li, Zepeng Zhang, Tongfei A Wang, Lei Zhang","doi":"10.3390/bioengineering12060673","DOIUrl":"10.3390/bioengineering12060673","url":null,"abstract":"<p><p>Implantable telemetry biosensors have become powerful tools for continuous physiological monitoring with minimal animal perturbation. However, commercially available implants are relatively oversized for small animals such as mice and have limited transmission range, leading to concerns about animal welfare, experiment scenarios, and the reliability of the data. In this study, we designed a telemetry system that tracks the animals' body temperature and locomotor activity in real time. The implant integrates a temperature sensor with a 3-axis accelerometer and is capable of wirelessly transmitting data over a 40 m mesh network. The implant's temperature performance was evaluated in bench tests, showing a response rate of 0.2 °C/s, drift ≤ 0.03 °C within 31 days, and a standard deviation of 0.035 °C across three identically designed implants. Meanwhile, the in vivo implant's locomotion recordings showed strong agreement with computer vision analysis with a correlation coefficient of r = 0.95 (<i>p</i> < 0.001), and their body temperature recordings were aligned to differential states of rest, exercise, or post-exercise recovery. The results demonstrate stable and highly accurate performance over the 30-day implantation period. Its ability to minimize behavioral interference while enabling long-term continuous monitoring highlights its value in both biomedical and animal behavior research.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189742/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144493911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Hybrid Deep Learning Framework for Accurate Cell Segmentation in Whole Slide Images Using YOLOv11, StarDist, and SAM2.","authors":"Julius Bamwenda, Mehmet Siraç Özerdem, Orhan Ayyıldız, Veysı Akpolat","doi":"10.3390/bioengineering12060674","DOIUrl":"10.3390/bioengineering12060674","url":null,"abstract":"<p><p>Accurate segmentation of cellular structures in whole slide images (WSIs) is essential for quantitative analysis in computational pathology. However, the complexity and scale of WSIs present significant challenges for conventional segmentation methods. In this study, we propose a novel hybrid deep learning framework that integrates three complementary approaches, YOLOv11, StarDist, and Segment Anything Model v2 (SAM2), to achieve robust and precise cell segmentation. The proposed pipeline utilizes YOLOv11 as an object detector to localize regions of interest, generating bounding boxes or preliminary masks that are subsequently used either as prompts to guide SAM2 or to filter segmentation outputs. StarDist is employed to model cell and nuclear boundaries with high geometric precision using star-convex polygon representations, which are particularly effective in densely packed cellular regions. The framework was evaluated on a unique WSI dataset comprising 256 × 256 image tiles annotated with high-resolution cell-level masks. Quantitative evaluations using the Dice coefficient, intersection over union (IoU), F1-score, precision, and recall demonstrated that the proposed method significantly outperformed individual baseline models. The integration of object detection and prompt-based segmentation led to enhanced boundary accuracy, improved localization, and greater robustness across varied tissue types. This work contributes a scalable and modular solution for advancing automated histopathological image analysis.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144493907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamically Quantifying Vocal Fold Thickness: Effects of Medialization Implant Location on Glottal Shape and Phonation.","authors":"Charles Farbos de Luzan, Jacob Michaud-Dorko, Rebecca J Howell, Ephraim Gutmark, Liran Oren","doi":"10.3390/bioengineering12060667","DOIUrl":"10.3390/bioengineering12060667","url":null,"abstract":"<p><p>Unilateral vocal fold paralysis (UVFP) can lead to significant dysphonia. Medialization thyroplasty type 1 (TT1) is a common surgical intervention aiming at improving vocal quality by optimally positioning the paralyzed fold to generate the necessary vibrations for phonation. Implants are generally placed through the thyroid cartilage in a sedated patient and positioned either underneath the level of the vocal folds (infraglottal medialization or IM) or at the level of the vocal folds (glottal medialization or GM). Using high-speed three-dimensional digital image correlation (3D-DIC) in an ex vivo canine hemilarynx model, this study explores the impact of implant location, specifically IM versus GM on the pre-phonatory and dynamic vertical thickness, glottal divergence, flow rate (Q), and cepstral peak prominence (CPP) under varying adduction and subglottal pressure conditions. IM consistently increased glottal divergence and dynamic vertical thickness, particularly in under-adducted states (AL1), despite producing lower static thickness than GM. CPP remained unaffected by the implant condition, but Q decreased significantly with IM under AL1, indicating enhanced glottal resistance and closure. These findings suggest that IM may offer superior functional outcomes by restoring divergent glottal shaping and improving vibratory efficiency. This study also introduces a validated method for dynamically quantifying vocal fold thickness and emphasizes the importance of implant depth in medialization thyroplasty strategies.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189883/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Comprehensive Review of Unobtrusive Biosensing in Intelligent Vehicles: Sensors, Algorithms, and Integration Challenges.","authors":"Shiva Maleki Varnosfaderani, Mohd Rizwan Shaikh, Mohamad Forouzanfar","doi":"10.3390/bioengineering12060669","DOIUrl":"10.3390/bioengineering12060669","url":null,"abstract":"<p><p>Unobtrusive in-vehicle measurement and the monitoring of physiological signals have recently attracted researchers in industry and academia as an innovative approach that can provide valuable information about drivers' health and status. The main goal is to reduce the number of traffic accidents caused by driver errors by monitoring various physiological parameters and devising appropriate actions to alert the driver or to take control of the vehicle. The research on this topic is in its early stages. While there have been several publications on this topic and industrial prototypes made by car manufacturers, a comprehensive and critical review of the current trends and future directions is missing. This review examines the current research and findings in in-vehicle physiological monitoring and suggests future directions and potential uses. Various physiological sensors, their potential locations, and the results they produce are demonstrated. The main challenges of in-vehicle biosensing, including unobtrusive sensing, vehicle vibration and driver movement cancellation, and privacy management, are discussed, and possible solutions are presented. The paper also reviews the current in-vehicle biosensing prototypes built by car manufacturers and other researchers. The reviewed methods and presented directions provide valuable insights into robust and accurate biosensing within vehicles for researchers in the field.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189504/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144493979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biomechanical Design and Validation of a Novel Elliptical Sleeve Pedicle Screw for Enhanced Spinal Fixation Stability.","authors":"Ting-Shuo Hsu, Chang-Jung Chiang, Hsuan-Wen Wang, Yu-San Chen, Chun-Li Lin","doi":"10.3390/bioengineering12060668","DOIUrl":"10.3390/bioengineering12060668","url":null,"abstract":"<p><p>This study aimed to develop a novel modular pedicle screw system incorporating an elliptical sleeve to conform the pedicle's elliptical cross-section and enhance fixation strength with mechanical stability. The biomechanical evaluation was conducted based on fundamental mechanics principles, followed by a finite element (FE) analysis to assess stress distribution under compressive and torsional loads. Subsequently, mechanical testing was performed to evaluate static and fatigue bending performance and in vitro biomechanical fatigue in porcine vertebrae by pull-out testing after 5000 and 100,000 cycles to assess fixation stability. The FE analysis demonstrated that the elliptical sleeve design improved bending resistance by 1.21× and torsional resistance by 1.91× compared to conventional cylindrical screws. Mechanical testing revealed greater bending/torsion stiffness and fatigue resistance, with the elliptical sleeve screw withstanding 5 million cycles at 235.4 N, compared to 175.46 N for cylindrical screws. Biomechanical pull-out testing further confirmed significantly higher retention strength after 100,000 cycles (1229.75 N vs. 867.83 N, <i>p</i> = 0.0101), whereas cylindrical screws failed prematurely at 10,663 cycles due to excessive displacement (>2 mm). The elliptical sleeve pedicle screw system demonstrated enhanced fixation strength, reduced micromotion, and superior fatigue resistance, making it a promising alternative to conventional pedicle screws for improving long-term spinal fixation stability.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12190103/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144493991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ResST-SEUNet++: Deep Model for Accurate Segmentation of Left Ventricle and Myocardium in Magnetic Resonance Imaging (MRI) Images.","authors":"Abduljabbar S Ba Mahel, Mehdhar S A M Al-Gaashani, Fahad Mushabbab G Alotaibi, Reem Ibrahim Alkanhel","doi":"10.3390/bioengineering12060665","DOIUrl":"10.3390/bioengineering12060665","url":null,"abstract":"<p><p>The highly precise and trustworthy segmentation of the left ventricle (LV) and myocardium is critical for diagnosing and treating cardiovascular disorders, which includes persistent microvascular obstruction (MVO) as well as myocardial infarction (MI) diseases. This process improves diagnostic accuracy and optimizes the planning and implementation of therapeutic interventions, ultimately improving the quality of care and patient prognosis. Limitations of earlier investigations include neglecting the complex image pre-processing required to accurately delineate areas of the LV and myocardium (Myo) in MRI and the absence of a substantial, high-quality dataset. Thus, this paper presents a comprehensive end-to-end framework, which includes contrast-limited adaptive histogram equalization (CLAHE) and bilateral filtering methods for image pre-processing and the development and implementation of a proposed deep model for left ventricular and myocardium segmentation. This study utilizes the EMIDEC database for the training and assessment of the model, allowing for a detailed comparative analysis with six state-of-the-art (SOTA) segmentation models. This approach provides a high accuracy and reliability for the segmentation that is crucial for the diagnosis and treatment of cardiovascular disorders. The achievements of the proposed model are demonstrated by high average values of segmentation rates, such as an Intersection over Union (IoU) of 93.73%, Recall of 96.54%, Dice coefficient of 96.70%, Precision of 96.86%, and F1-score of 96.70%. To verify the generalization capability, we assessed our suggested model on five supplementary databases, which substantiates its exceptional efficiency and adaptability in a diverse environment. The presented findings demonstrate that the proposed deep model surpasses current methods, offering more a precise and resilient segmentation of cardiac structures.</p>","PeriodicalId":8874,"journal":{"name":"Bioengineering","volume":"12 6","pages":""},"PeriodicalIF":3.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12189363/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144494068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}