Biomedical Engineering and Computational Biology最新文献

{"title":"RunicNet: Leveraging CNNs With Attention Mechanisms for Cervical Cancer Cell Classification.","authors":"Erin Beate Bjørkeli, Morteza Esmaeili","doi":"10.1177/11795972251351815","DOIUrl":"10.1177/11795972251351815","url":null,"abstract":"<p><strong>Introduction: </strong>Early detection through routine screening methods, such as the Papanicolaou (Pap) test, is crucial for reducing cervical cancer mortality. However, the Pap smear method faces challenges including subjective interpretation, significant variability in diagnostic confidence, and high susceptibility to human errors-leading to both false negatives (missed abnormalities) and false positives (unnecessary follow-up procedures). Providing a first opinion could improve the screening examination pipeline and greatly aid the specialist's confidence in reporting. Artificial intelligence (AI)-based approaches have shown promise in automating cell classification, reducing human error, and identifying subtle abnormalities that may be missed by experts.</p><p><strong>Methods: </strong>In this study, we present RunicNet, a CNN-based architecture with attention mechanisms designed to classify Pap smear cell images. RunicNet integrates attention mechanisms such as High-Frequency Attention Blocks-enhanced Residual Blocks for improved feature extraction, Pixel Attention for computational efficiency, and a Gated-Dconv Feed-Forward Network to refine image representation. The model was trained on a dataset of 85 080 cell images, employing data augmentation and class balancing techniques to address dataset imbalances.</p><p><strong>Results: </strong>Evaluated on a separate testing dataset, RunicNet achieved a weighted F1-score of 0.78, significantly outperforming baseline models such as ResNet-18 (F1-score of 0.53) and a fully connected CNN (F1-score of 0.66).</p><p><strong>Discussion: </strong>The findings support the potential of attention-based CNN models like RunicNet to significantly improve the accuracy and efficiency of cervical cancer screening. Integrating such AI systems into clinical workflows may enhance early detection and reduce diagnostic variability in Pap smear analysis.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251351815"},"PeriodicalIF":2.3,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12271656/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144676052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Numerical Systematic Review and Meta-Analysis of Diagnosing the Vibration Modes of the Cylindrical Shell in the MRI Machine.","authors":"Hamidreza Mortazavy Beni, Fatemeh Aghaei, Ashkan Heydarian, Fatemeh Yekta Asaei, Hosein Samaram","doi":"10.1177/11795972251353069","DOIUrl":"10.1177/11795972251353069","url":null,"abstract":"<p><p>Magnetic Resonance Imaging (MRI) is a non-invasive imaging method that utilizes radio waves and magnetic fields. This study focuses on reducing the acoustic noise produced inside the cylindrical shell of the scanner, where the patient is located. Vibration modes are generated by eddy currents in the cylindrical shell induced by gradient magnetic fields. Additionally, the scanner wall is typically joined to the gradient spiral cylinder, causing vibrations to be transmitted to the wall and thereby producing extra sound waves. The present study investigates methods for mitigating noise from the scanner wall and reducing the transmission noise from the spiral gradient cylinder. Numerical methods and practical solutions for lowering acoustic noise in MRI gradient coils are explored. A 20 mm uniform absorber is demonstrated as an effective design for significantly reducing acoustic noise in the frequency range 0 to 3 kHz. Finally, numerical analysis of gradient cycles yields solutions that lower both vibration and noise levels.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251353069"},"PeriodicalIF":2.3,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12254674/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144627376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning based Model Reveals the Metabolites Involved in Coronary Artery Disease.","authors":"Fathima Lamya, Muhammad Arif, Mahbuba Rahman, Abdul Rehman Zar Gul, Tanvir Alam","doi":"10.1177/11795972251352014","DOIUrl":"10.1177/11795972251352014","url":null,"abstract":"<p><strong>Introduction: </strong>Coronary artery disease (CAD) is a major global cause of morbidity and mortality. Therefore, advances in early identification and individualized treatment plans are crucial.</p><p><strong>Methods: </strong>This article presents machine learning (ML) based model that can recognize metabolomic compounds associated with CAD in the Qatari population for the early detection of CAD. We also identified statistically significant metabolic profiles and potential biomarkers using ML methods.</p><p><strong>Results: </strong>Among all ML models, artificial neural network (ANN) outstands all with an accuracy of 91.67%, recall of 80.0%, and specificity of 100%. The results show that 173 metabolites (<i>P</i> < .05) are significantly associated with CAD. Of these metabolites, the majority (95/173, 54.91%) were high in CAD patients, while 45.09% (78/173) were high in the control group. Two metabolites 2-hydroxyhippurate (salicylurate) and salicylate were notably higher in CAD patients compared to the control group. Conversely, 4 metabolites, cholate, 3-hydroxybutyrate (BHBA), 4-allyl catechol sulfate, and indolepropionate, showed relatively higher level in the control group.</p><p><strong>Conclusion: </strong>We believe our study will support in advancing personalized diagnosis plan for CAD patients by considering the metabolites involved in CAD.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251352014"},"PeriodicalIF":2.3,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12246536/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144627377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rib and Sternum Fractures From Falls: Global Burden of Disease and Predictions.","authors":"Zhanghao Huang, Jun Zhu","doi":"10.1177/11795972251350223","DOIUrl":"10.1177/11795972251350223","url":null,"abstract":"<p><strong>Background: </strong>By combining existing Global Burden of Disease (GBD) data with the economic conditions of different regions, we can better understand disease trends and make more accurate estimations, facilitating effective public health interventions. Medical institutions can consequently allocate resources more efficiently. For patients, this helps lower disease risk and reduce the overall disease burden in affected areas.</p><p><strong>Methods: </strong>We analyzed health patterns in 204 countries using GBD 2021 methodologies and conducted separate analyses of disease burden in China and worldwide. We estimated incidence, prevalence, and years lived with disability (YLDs). We further assessed disease status by incorporating Socio-Demographic Index (SDI) values. In addition, we used Mendelian randomization to identify factors leading from falls to thoracic rib fractures, and we investigated the key protein involved in thoracic rib fractures through detection of 4907 plasma proteins.</p><p><strong>Results: </strong>From 1990 to 2021, the age-standardized incidence rate (ASIR) and age-standardized prevalence rate (ASPR) generally showed an upward trend, although male ASIR, and ASPR displayed a slight decline. In China, however, ASIR and ASPR reached a turning point in 2000, dipped in 2005, then trended upward again. Morbidity and prevalence were negatively correlated with SDI. Based on Mendelian randomization analyses, falls leading to thoracic rib fractures were linked to education level and osteoporosis. Moreover, HAMP was identified as the key protein in thoracic rib fractures.</p><p><strong>Conclusion: </strong>As global populations age, analyzing the global burden of thoracic rib fractures caused by falls from 1990 to 2021 can help guide the development of effective public health prevention strategies and optimize the allocation of existing medical resources.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251350223"},"PeriodicalIF":2.3,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12205187/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144530227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Muscle Forces and Their Impact on Femoral Bone Stresses Using Response Surface Methodology (RSM).","authors":"Saeed Habibi, Mohammad Nazari Shalkouhi, Mohammad Javad Keyhani Dehnavi, Mahkame Sharbatdar, Aisa Rassoli","doi":"10.1177/11795972251351766","DOIUrl":"10.1177/11795972251351766","url":null,"abstract":"<p><p>In this study, reliability methods were demonstrated as a promising approach in medical engineering by identifying the most significant muscle forces affecting femoral stress. First, the finite element method (FEM) in Abaqus software was used to model the effects of 10 muscle and joint forces across various regions of the femur. Then, using the response surface methodology (RSM), and examining the effect coefficients of each joint and muscle force, the hip joint reaction force with an impact coefficient of 210.97 was identified as the most effective force on bone stress. After that, the gluteus minimus and gluteus medius muscle forces were ranked second and third in terms of stress effect with coefficients of 66.6 and 34.47. This study showed that the anterior femoral muscles have a significant effect on stress compared to the posterior femoral muscles. RSM enables faster and more precise identification of joint and muscle forces influencing femoral stresses compared to conventional methods. This innovative approach not only increased the understanding of biomechanical phenomena, but also provided a more efficient tool for investigating and optimizing such processes in biomedical engineering applications.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251351766"},"PeriodicalIF":2.3,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12198530/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144508790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Enhanced Hybrid Model Combining CNN, BiLSTM, and Attention Mechanism for ECG Segment Classification.","authors":"Mechichi Najia, Benzarti Faouzi","doi":"10.1177/11795972251341051","DOIUrl":"10.1177/11795972251341051","url":null,"abstract":"<p><p>Deep learning models are necessary in the field of healthcare for the diagnosis of cardiac rhythm diseases since the conventional ECG classification is based on hand-crafted feature engineering and traditional machine learning. Nevertheless, CNN and BiLSTM architectures provide automatic feature learning, enhancing ECG classification accuracy. The current research work puts forward a framework integrating CNN with CBAM and BiLSTM layers for the purpose of extracting valuable features and classifying ECG signals. The model classifies heartbeats according to the AAMI EC57 standard into 5 categories: normal beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F), and unknown beats (Q). To tackle uneven class distributions, SMOTE synthesizes new samples, making the model more robust. Evaluation on MIT-BIH arrhythmia database yields remarkable results with 99.20% accuracy, 97.50% sensitivity, 99.81% specificity, and 98.29% mean <i>F</i>1 score. Deep learning methods have great potential to alleviate clinicians' workload and improve diagnostic accuracy of cardiac diseases.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251341051"},"PeriodicalIF":2.3,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12174755/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144327171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Screening Biomarkers and Risk Factors for COVID-19 Progression in a Border Population Between Brazil-Bolivia.","authors":"Ana Maísa Passos-Silva, Adrhyan Araújo, Tárcio Peixoto Roca, Jackson Alves da Silva Queiroz, Gabriella Sgorlon, Rita de Cássia Pontello Rampazzo, Juan Miguel Villalobos Salcedo, Juliana Pavan Zuliani, Deusilene Vieira","doi":"10.1177/11795972241298786","DOIUrl":"https://doi.org/10.1177/11795972241298786","url":null,"abstract":"<p><strong>Background: </strong>The performance and genetic role in host response delineate investigative points of polymorphisms as potential biomarkers in viral infections.</p><p><strong>Methods: </strong>Thus, this research aimed to map biomarkers and risk factors in the severity of COVID-19 in individuals in Western Amazon (n = 243).</p><p><strong>Results: </strong>Patients aged 40 to 59 years showed an association with clinical progression (<i>P</i> = .003), also evidencing the relationship for individuals >60 years (<i>P</i> < .001), besides the non-vaccination influenced the pathology (<i>P</i> = .023). qPCR for human genotyping of the targets rs2070788, rs4702, rs76635825, rs540856718, rs35803318, rs12979860, and rs16899066, as well as for gene expression of ACE2, HLA-A, HLA-B, IFNL-3/2, IL-6, and TMPRSS2 was used. The rs12979860 (C > T) and rs2070788 (A > G) showed association among the analyzed groups (<i>P</i> < .05) with the allelic and genotypic frequency of rs12979860 (<i>x</i> ² < 3.84) and evolutionary pointing of rs2070788G allele among infected people, including deaths.</p><p><strong>Conclusion: </strong>Gene expression showed high levels between the moderate and severe groups, with emphasis on TMPRSS2 and IL-6 genes that performed better. Thus, there is possibly an association regarding the role of the TMPRSS2 gene and rs2070788G, as well as age and IL-6 levels for COVID-19, pointing in parallel to the considerable influence of the vaccine on the SARS-CoV-2 pathway.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972241298786"},"PeriodicalIF":2.3,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12044272/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144040732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Is it Curbing-spread of SARS-CoV-2 Variants by Considering Non-linear Predictive Control?","authors":"Mohadeseh Najafi, Hamidreza Mortazavy Beni, Ashkan Heydarian, Samaneh Sadat Sajjadi, Ahmad Hajipour","doi":"10.1177/11795972251321306","DOIUrl":"https://doi.org/10.1177/11795972251321306","url":null,"abstract":"<p><p>Although SARS-COV-2 started in 2019, its losses are still significant, and it takes victims. In the present study, the epidemic patterns of SARS-COV-2 disease have been investigated from the point of view of mathematical modeling. Also, the effect of quarantine has been considered. This mathematical model is designed in the form of fractional calculations along with a model predictive control (MPC) to monitor this model. The fractional-order model has the memory and hereditary properties of the system, which can provide more adjustable parameters to the designer. Because the MPC can predict future outputs, it can overcome the conditions and events that occur in the future. The results of the simulations show that the proposed nonlinear model predictive controller (NMPC) of fractional-order has a lower mean squared error in susceptible people compared to the optimal control of fractional-order (~3.6e-04 vs. 47.4). This proposed NMPC of fractional-order can be used for other models of epidemics.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251321306"},"PeriodicalIF":2.3,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033554/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144001695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can Smart Alloy Material Improve the Biomechanical Behavior of Prostheses Used in the Human Trachea? A Fluid-Structure Interaction Approach.","authors":"Hamidreza Mortazavy Beni","doi":"10.1177/11795972251330678","DOIUrl":"https://doi.org/10.1177/11795972251330678","url":null,"abstract":"<p><strong>Background and objective: </strong>The Shape-Memory Alloy (SMA) or smart alloy stent can be used in the upper respiratory system by reducing problems such as changing the shape according to the actual conditions of the body compared to other stents.</p><p><strong>Methods: </strong>In this study, the behavior of 2 types of SMA stents with different metallurgical properties was studied using the Finite Element Method (FEM). Tracheal geometry was obtained from CT images of a healthy man. Then, a computational model of a real human trachea was selected to analyze the deformation of the trachea after implantation of the prosthesis. Finally, it was analyzed under the maximum average static pressure of the entrance to the trachea using the Fluid-Structure Interaction (FSI) approach. A mesh based on unstructured elements for air and structured elements for the tracheal wall was created to perform simulations using ANSYS software.</p><p><strong>Results: </strong>The deformation of the stent was compared and analyzed with the deformation of the healthy trachea in the absence of the stent. The results presented that the most deformation in the trachea before stenting is up to 8.3 mm. The behavior of SMA2 with a deformation of 5.8 mm was more consistent with the deformation conditions of the trachea for real body conditions without the presence of a stent.</p><p><strong>Conclusions: </strong>As much as the deformation is reduced by the degree of stress concentration at the connection point of the stent to the trachea, the risks of stent displacement and patient suffocation are avoided.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251330678"},"PeriodicalIF":2.3,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12033672/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144020428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Potential Drugs Targeting Acute Pancreatitis Based on the HLA-DR-Related Gene-Monocyte Infiltration Regulatory Network.","authors":"Wei Xu, Lan Hu, Shengyi Shi, Jie Gao, Jing Ye, Yiming Lu","doi":"10.1177/11795972251328458","DOIUrl":"10.1177/11795972251328458","url":null,"abstract":"<p><strong>Background: </strong>Acute pancreatitis (AP) is a common disease of acute abdominal pain, the incidence of which is increasing annually, but its pathogenesis remains incompletely understood.</p><p><strong>Methods: </strong>Gene expression profiles of AP were obtained from the Gene Expression Omnibus (GEO) database. R software was used to identify differentially expressed genes (DEGs) and perform functional analysis. The diagnostic value of HLA-DR-related genes was assessed by receiver operating characteristic (ROC) curves. Monocyte infiltration abundance in AP and normal groups was analyzed by Cibersort method, and the correlation between HLA-DR-related genes and monocyte abundance was analyzed. The modules highly correlated with HLA-DR-related genes were clarified by WGCNA modeling, and the core genes regulating HLA-DR were obtained by using LASSO regression. Finally, potential drugs targeting the above genes were analyzed by Enrichr database.</p><p><strong>Result: </strong>A Total of 3 HLA-DR-related genes (HLA-DRA, HLA-DRB1, and HLA-DRB5) were identified, which were negatively correlated with the severity of AP and had excellent disease diagnostic value (AUC = 0.761, 0.761, and 0.718), were were positively correlated with monocyte abundance. We identified 110 genes that positively regulate HLA-DR and 130 genes that negatively regulate HLA-DR. LASSO regression identified UCP2, GK, and SAMHD1 as the core nodes of the regulated genes. Compared with the normal group, UCP2 and SAMHD1 were reduced in AP, and the opposite was true for GK, and SAMHD1 had better sensitivity and specificity in diagnosing AP. Drug sensitivity analysis predicted 12 drugs acting on HLA-DRA, HLA-DRB1, and HLA-DRB5 and 8 drugs acting on UCP2, GK, and SAMHD1.</p><p><strong>Conclusion: </strong>We identified 3 HLA-DR-related genes (HLA-DRA, HLA-DRB1, and HLA-DRB5) and 3 coregulatory nodes (UCP2, GK, and SAMHD1), which were associated with AP severity and monocyte abundance. Based on these genes, we predicted 20 potential therapeutic agents for AP.</p>","PeriodicalId":42484,"journal":{"name":"Biomedical Engineering and Computational Biology","volume":"16 ","pages":"11795972251328458"},"PeriodicalIF":2.3,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11956513/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143755009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}