Journal of Biomedical Physics and Engineering最新文献

{"title":"Diagnosing Epilepsy using Entropy Measures and Embedding Parameters of EEG Signals.","authors":"Fatemeh Valipour, Zahra Valipour, Mani Garousi, Ali Khadem","doi":"10.31661/jbpe.v0i0.2402-1720","DOIUrl":"10.31661/jbpe.v0i0.2402-1720","url":null,"abstract":"<p><strong>Background: </strong>Manual analysis of electroencephalography (EEG) for epilepsy diagnosis can be subjective and time-consuming, leading to potential errors. An automatic classification system with high detection accuracy is essential for improving diagnostic efficiency and reliability.</p><p><strong>Objective: </strong>This study aimed to evaluate a comprehensive set of entropy measures, along with embedding parameters, to identify the most effective single measure for epilepsy diagnosis.</p><p><strong>Material and methods: </strong>This analytical study used EEG data from the University of Bonn, including healthy controls (HCs) with open eyes and epileptic seizure patients, each with 100 single-channel segments. Discrete wavelet transform was applied, extracting ten entropy measures and two embedding parameters. Statistical tests evaluated feature significance, and a linear discriminant analysis (LDA) classifier was used for classification. Robustness was assessed by introducing Gaussian noise at varying signal-to-noise ratios (SNRs) and analyzing classification performance.</p><p><strong>Results: </strong>Our findings indicated that embedding parameters, permutation entropy, fuzzy entropy, sample entropy, norm entropy, sure entropy, log entropy, and threshold entropy significantly differentiated epileptic patients from HCs. Among these, sample entropy, norm entropy, sure entropy, log entropy, threshold entropy, and embedding delay achieved classification accuracies between 97% and 100% using LDA classifier. Furthermore, even with substantial Gaussian noise, the classifier maintained an accuracy above 84%, demonstrating the robustness of these features in noisy conditions.</p><p><strong>Conclusion: </strong>This study demonstrated that embedding-based and entropy-based features can serve as effective individual measures for discriminating epileptic EEG signals from HCs. These findings underscore the potential of these measures in automated epilepsy diagnosis systems, resulting in a robust and reliable tool for clinical applications.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 3","pages":"231-244"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13263383/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148253669","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":"Determining the Correlation and Effect of Rectal and Bladder Volume Change in Shift of Planning Target Volume and Calculating Planning Target Volume Margin with Van Herk Formula in Prostate Cancer Tomotherapy.","authors":"Vahid Shabaninejad, Ahmad Shanei, Mahnaz Roayaei, Ali Akhavan, Mohsen Saeb, Samira Hadinezhad","doi":"10.31661/jbpe.v0i0.2407-1796","DOIUrl":"10.31661/jbpe.v0i0.2407-1796","url":null,"abstract":"<p><strong>Background: </strong>Movement of the Planning Target Volume (PTV) is considered one of the main challenges in radiotherapy for prostate cancer.</p><p><strong>Objective: </strong>The current study aimed to assess the correlation and impact of rectal and bladder volume changes on PTV shift during tomotherapy for prostate cancer, calculate PTV margins using the Van Herk formula to optimize treatment accuracy, and reduce healthy tissue irradiation.</p><p><strong>Material and methods: </strong>This prospective study investigates PTV displacement and calculates PTV margin considering changes in rectum, bladder, and prostate volumes in 20 prostate cancer patients undergoing tomotherapy. PTV contouring, including prostate and seminal vesicles was performed on patient CT images. Systematic and random PTV motion errors were measured on Mega Voltage Computed Tomography (MVCT) images relative to the reference CT. PTV margin for 95% prescription dose coverage was calculated using the van Herk formula. The correlation between PTV displacement and prostate volume, rectum volume changes, bladder volume changes, age, and patient weight was investigated.</p><p><strong>Results: </strong>Linear regression analysis showed that changes in rectum and bladder volumes were significantly correlated with PTV displacement. The PTV margin was calculated using the van Herk formula, effectively achieving 95% prescription dose coverage. The largest PTV displacement range was in the anterior direction and related to the seminal vesicles.</p><p><strong>Conclusion: </strong>Significant PTV displacements were observed in prostate cancer patients undergoing tomotherapy. Rectum and bladder volume changes are key parameters associated with PTV displacement. Clinical Target Volume (CTV) to PTV margin for delivery of 95% of the prescribed dose is different and non-homogeneous in different parts of the target volume.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 3","pages":"179-190"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13263382/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148253704","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":"<i>In Vitro</i> Radiosensitizing Effects of Urtica Dioica Leaf Aqueous Extract on the Killing of U87MG Glioblastoma Cell Line.","authors":"Maryam Khorramizadeh, Zaynab Kord, Mina Cheshmberah, Marzieh Anaam, Aziz Kassani, Behnaz Deihim","doi":"10.31661/jbpe.v0i0.2403-1739","DOIUrl":"10.31661/jbpe.v0i0.2403-1739","url":null,"abstract":"<p><strong>Background: </strong>Glioblastoma Multiforme (GBM) is a highly aggressive brain tumor with a poor prognosis. Despite advancements in radiotherapy, its effectiveness is limited due to challenges in delivering high doses without harming healthy tissues.</p><p><strong>Objective: </strong>The current study aimed to determine whether Urtica dioica extract could enhance the cytotoxic effects of radiation on U87MG glioma cells and explore the underlying mechanisms.</p><p><strong>Material and methods: </strong>This <i>in-vitro</i> study was conducted on the U87MG glioma cell line and investigated the effects of Urtica dioica extract (at various concentrations) and irradiation (2 Gy) on cell viability, cell cycle distribution, and apoptosis.</p><p><strong>Results: </strong>Urtica dioica extract exhibited a concentration and time-dependent cytotoxic effect on U87MG cells. Notably, combining the extract with radiotherapy resulted in a significantly greater reduction in cell viability compared to either treatment alone. Cell cycle analysis revealed that the combination treatment induced G2/M phase arrest more effectively than either treatment alone. Additionally, Urtica dioica extract enhanced the pro-apoptotic effects of radiation, indicated by a significant increase in the late apoptotic cell population.</p><p><strong>Conclusion: </strong>This study demonstrates the radiosensitizing properties of Urtica dioica extract in U87MG glioma cells. The extract promotes cell cycle arrest and apoptosis, potentially leading to improved radiotherapy efficacy. These findings suggest Urtica dioica as a promising complementary therapy for GBM treatment.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 3","pages":"169-178"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13263386/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148253779","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":"Neural Changes in Patients with Post-Traumatic Anosmia: Insights from Resting-State fMRI.","authors":"Abolhasan Rezaeyan, Fatemeh Shahi Moridi, Seyed Kamran Kamrava, Mohammad Bagher Shiran, Arash Zare-Sadeghi","doi":"10.31661/jbpe.v0i0.2505-1930","DOIUrl":"10.31661/jbpe.v0i0.2505-1930","url":null,"abstract":"<p><strong>Background: </strong>Functional Magnetic Resonance Imaging (fMRI) is a powerful modality for investigating changes in healthy brains and those with disorders. Anosmia, an olfactory disorder, is commonly associated with traumatic brain injury, particularly in patients suffering from severe trauma.</p><p><strong>Objective: </strong>In this study, we aimed to utilize Resting-State fMRI (rs-fMRI) to examine changes in Functional Connectivity (FC) networks between Healthy Controls (HCs) and patients with Post-Traumatic Anosmia (PTA).</p><p><strong>Material and methods: </strong>In this retrospective study, we performed rs-fMRI on forty-four PTA patients and forty-three HCs. The Sniffin' Sticks test was used to assess olfactory function. Seed-based Analysis (SBA) and Independent Component Analysis (ICA) were conducted using MATLAB-based imaging software.</p><p><strong>Results: </strong>PTA patients showed lower Threshold-Discrimination-Identification (TDI) scores compared to HCs. SBA revealed increased FC correlations in the anterior cingulate cortex, piriform, insular cortex, and prefrontal area in PTA patients. Using ICA on the whole brain network, we found increased FC in the right frontal pole, cerebellum, right putamen, anterior cingulate cortex, postcentral gyrus, orbitofrontal cortex, and amygdala in PTA compared to HCs. In PTA patients, global efficiency of the entire brain network showed a significant association with olfactory performance.</p><p><strong>Conclusion: </strong>This study suggests that neural-level olfactory deficits following head trauma are most accurately characterized through SBA and ICA analyses in higher-order regions outside the primary olfactory cortex.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 3","pages":"205-218"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13263385/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148253636","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":"Anesthesia Services Can be Provided via Telemedicine: An Assessment of the Readiness.","authors":"Zeinab Kohzadi, Shahabedin Rahmatizadeh, Ali Dabbagh, Hassan Emami, Zahra Kohzadi","doi":"10.31661/jbpe.v0i0.2311-1686","DOIUrl":"10.31661/jbpe.v0i0.2311-1686","url":null,"abstract":"<p><strong>Background: </strong>Telemedicine technology can not only improve service quality, reduce costs, and broaden access to specialized and subspecialty healthcare services, but also be utilized to provide certain anesthesia services.</p><p><strong>Objective: </strong>The objective of this study was to translate and assess the validity and reliability of the Telehealth Readiness Assessment (TRA) tool, used to evaluate the readiness of healthcare providers, for anesthesia services to implement telemedicine for delivering anesthesia services to patients.</p><p><strong>Material and methods: </strong>In this cross-sectional study, the initial step involved translating the questionnaire followed by an assessment of its validity and reliability. The questionnaire was then distributed to the staff members in the Anesthesiology Research Center. The readiness assessment encompassed various aspects, including Core Readiness, Financial Considerations, Operations, Staff Engagement, and Patient Readiness.</p><p><strong>Results: </strong>The Content Validity Index (CVI) and Content Validity Ratio (CVR) were 93% and 72%, respectively. The internal consistency of each item and the overall TRA score demonstrated excellent reliability, with all values exceeding 0.90. The internal consistency coefficients ranged from 0.92 to 1.00, indicating high reliability and consistency in the measurements of the TRA questionnaire. Cronbach's alpha was 99%. The TRA subscales mean scores were 71.77±14.76, 63.25±16.14, 67.36±20.46, 68.81±18.50, and 72.52±14.39, respectively. The TRA total mean score was 68.61±17.33.</p><p><strong>Conclusion: </strong>The Persian version of the TRA questionnaire exhibits acceptable levels of validity and reliability. The readiness level related to the implementation of telemedicine for anesthesiologists was obtained as moderate. To ensure the success of telemedicine projects, it is of the utmost importance to pay close attention to the relevant indicators, with particular focus on financial considerations, as this area received the lowest score.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"97-108"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122348/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784084","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":"Evaluating the Protective Effect of Melatonin on Apoptosis, Expression of Bax and Bcl2 Genes, and ROS Level after Radiofrequency Radiation on L929 Fibroblast Cell Line.","authors":"Reza Fardid, Fateme Zaker, Masoud Haghani, Jamileh Saberzadeh","doi":"10.31661/jbpe.v0i0.2409-1828","DOIUrl":"10.31661/jbpe.v0i0.2409-1828","url":null,"abstract":"<p><strong>Background: </strong>The increasing use of mobile phones has raised concerns about potential health risks. In addition, the effect of protective materials is also important.</p><p><strong>Objective: </strong>This study aimed to evaluate the protective effect of Melatonin on cell viability, apoptosis, Reactive Oxygen Species (ROS) level, and gene expression of Bax and Bcl2 in L929 fibroblast cells after Radiofrequency (RF) radiation.</p><p><strong>Material and methods: </strong>In this experimental study, cells were divided into six groups with at least 3 replications in each group. The two groups were respectively exposed to radiofrequency waves for 8 and 16 hours. They were pretreated with melatonin before radiation exposure, while the control group did not receive any radiation or melatonin during the experiment, and the melatonin group was just treated with melatonin.</p><p><strong>Results: </strong>Cell survival was reduced after 8 hours of RF radiation. After 16 hours, the total apoptosis was increased, and pretreatment with melatonin increased cell survival and reduced total apoptosis. Radiation increased intracellular ROS levels. RF increased the Bax/Bcl2 ratio, and the treatment with melatonin decreased it after 8 hours.</p><p><strong>Conclusion: </strong>Melatonin prevents the increase in apoptosis and Bax/Bcl2 ratio, but there are no significant changes in survival and ROS levels.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"131-138"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122364/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784134","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":"Introducing Data Descriptors: A New Article Type to Advance Data-Driven Science.","authors":"Tahereh Mahmoudi, Ali Razmkon","doi":"10.31661/jbpe.v0i0.2602-2053","DOIUrl":"10.31661/jbpe.v0i0.2602-2053","url":null,"abstract":"","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"85-86"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784064","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":"The Role of Adipose Tissue-Derived Stem Cells together with Vitamin C on Survival of Rats with Acute Radiation Syndrome.","authors":"Seyed Mohammad Javad Mortazavi, Fatemeh Kadivar, Shahrokh Zare, Abolfazl Kanani, Mohammad Amin Mosleh-Shirazi, Sadegh Masoudi, Feridoun Karimi-Busheri, Davood Mehrabani","doi":"10.31661/jbpe.v0i0.2310-1680","DOIUrl":"10.31661/jbpe.v0i0.2310-1680","url":null,"abstract":"<p><strong>Background: </strong>Following any injury in radiation accidents, such as Acute Radiation Syndrome (ARS), medical interventions are recommended based on radiation dose and physiological response. Clinical management encompasses blood transfusion, hematopoietic cytokines, and stem-cell transplantation.</p><p><strong>Objective: </strong>This study aimed to determine the effect of adipose tissue-derived stem cells (AdSCs) together with vitamin C on the survival of rats with ARS.</p><p><strong>Material and methods: </strong>In this experimental study, 45 rats were randomly divided into 3 equal groups of animals administered with a single dose of oral 400 mg/kg vitamin C; those injected intravenously with 1.5×10⁵ AdSCs; and rats transplanted intravenously with 1.5×10⁵ AdSCs together with a single oral dose of 400 mg/kg vitamin C. All rats were already irradiated with 10 Gy (dose rate 0.286 Gy/ min) ⁶⁰CO, for 35 minutes with a field size of 35 cm × 35 cm for all body areas.</p><p><strong>Results: </strong>A significant increase in survival rate was visible one month after γ irradiation in 73.3% of animals received AdSCs+vitamin C, 60% of rats injected with just AdSCs, and 13.3% of the group received just vitamin C.</p><p><strong>Conclusion: </strong>Our findings revealed significant efficacy of a combined approach involving AdSC transplantation and vitamin C to enhance the survival rate following lethal irradiation. This combination could offer a potential avenue for addressing the alleviation of tissue damage caused by chemotherapy and toxic drugs. We recommend the administration of AdSCs together with vitamin C as an effective and prompt treatment option for irradiation injuries.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"87-96"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122367/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784131","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":"Investigating Depression and MRI Associations in Middle Eastern Relapsing-Remitting Multiple Sclerosis.","authors":"Parisa Pishdad, Banafsheh Zeinali-Rafsanjani, Maryam Poursadeghfard, Mahsa Kalaee, Jeyran Ostovarfar, Alireza Salehi","doi":"10.31661/jbpe.v0i0.2505-1929","DOIUrl":"10.31661/jbpe.v0i0.2505-1929","url":null,"abstract":"<p><strong>Background: </strong>Multiple Sclerosis (MS) is often complicated by depression, worsening disability and quality of life. Global depression prevalence in MS is ~27%, but Middle Eastern data are scarce. The neurobiological basis of depression in Relapsing-Remitting Multiple Sclerosis (RRMS) is unclear.</p><p><strong>Objective: </strong>This study aimed to assess depression prevalence in Middle Eastern RRMS patients versus controls, evaluate disability using the Expanded Disability Status Scale (EDSS), and explore Magnetic Resonance Imaging (MRI) correlations with depressive symptoms.</p><p><strong>Material and methods: </strong>In a cross-sectional study (June 2022-June 2023), 105 RRMS patients (mean age 36.2±13.9 years, 83.8% female) and 111 controls (mean age 39.1±10.9 years, 74.8% female) were recruited from Shiraz, Iran MS clinics. Depression was measured using the Beck Depression Inventory (BDI), disability via EDSS, and MRI (1.5-Tesla) analyzed for lesion burden and brain volume using VolBrain. Statistical analyses included t-tests, chi-squared tests, and correlations (<i>P</i>-value<0.05).</p><p><strong>Results: </strong>Depression was more prevalent in RRMS patients (33.3%) than controls (24.5%; <i>P</i>-value=0.15), especially in younger females (<i>P</i>-value=0.02). Mean EDSS was low (1.3-1.4), weakly correlating with right insular cortex plaque volume (r=0.20, <i>P</i>-value=0.03). Depressed patients had higher left limbic (<i>P</i>-value=0.05) and insular cortex (<i>P</i>-value=0.05) plaque burdens, with weak BDI correlations (r=0.19-0.20, <i>P</i>-value<0.04). Brain volume was reduced in depressed patients (<i>P</i>-value=0.09).</p><p><strong>Conclusion: </strong>Depression affects one-third of Middle Eastern RRMS patients, exceeding controls. Limbic and insular plaque burdens suggest network dysconnectivity drives depressive symptoms. Routine screening and region-specific interventions are needed.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"153-164"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122374/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784093","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":"Detection of Valve Vegetations in Native and Prosthetic Valves using Echocardiographic Radiomics and Deep Learning on Transesophageal Echocardiography Images.","authors":"Farid Esmaely, Pardis Moradnejad, Shabnam Boudagh, Seyed Mohammad Zamani-Aliabadi, Hamid Reza Pasha, Ahmad Bitarafan-Rajabi, Leyla Ansari","doi":"10.31661/jbpe.v0i0.2505-1915","DOIUrl":"10.31661/jbpe.v0i0.2505-1915","url":null,"abstract":"<p><strong>Background: </strong>Infective Endocarditis (IE) is a life-threatening condition that requires rapid and accurate diagnosis. Transesophageal Echocardiography (TEE) is the gold standard for detecting valve vegetations; however, its interpretation is highly operator-dependent and particularly challenging in patients with prosthetic valves. Recent advances in artificial intelligence, especially deep learning, offer opportunities to improve diagnostic accuracy and reduce observer variability.</p><p><strong>Objective: </strong>This study aimed to evaluate the performance of deep learning-based models for detecting vegetations in TEE images to support the diagnostic workflow of IE.</p><p><strong>Material and methods: </strong>In this retrospective experimental study, a Faster Region-based Convolutional Neural Network (Faster R-CNN) was implemented to localize valve vegetations in TEE images. Four model configurations were developed using DenseNet121 and ResNet50 backbones, each trained in frozen and fine-tuned modes. All models were pretrained on RadImageNet. The dataset consisted of 1,000 annotated TEE frames acquired from both native and prosthetic heart valves.</p><p><strong>Results: </strong>The fine-tuned DenseNet121 model achieved the best performance, with a mean Average Precision (mAP) of 0.653 and an Area Under the Curve (AUC) of 0.858. Its frozen version demonstrated lower performance (mAP=0.416, AUC=0.640). The fine-tuned ResNet50 model reached a mAP of 0.593 and an AUC of 0.789, while the frozen ResNet50 showed the lowest performance (mAP=0.403, AUC=0.601).</p><p><strong>Conclusion: </strong>Both fine-tuned DenseNet121 and ResNet50 models demonstrated effective localization of valve vegetations in TEE images, with comparable IoU performance. Although DenseNet121 showed superior classification accuracy, the similar localization results highlight the potential of both models as physician-assistive tools for enhancing IE diagnostic workflows.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 2","pages":"139-152"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13122342/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147784097","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}