Journal of Biomedical Physics and Engineering最新文献

{"title":"Short-term Classification of Neurodegenerative Diseases using Time-series Features Based on Analysis of Gait Dynamics.","authors":"Negar Monfared Jahromi, Ali Maleki","doi":"10.31661/jbpe.v0i0.2510-1997","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2510-1997","url":null,"abstract":"<p><strong>Background: </strong>Neurodegenerative Diseases (NDDs) refer to disorders, leading to the gradual degeneration of neurons in the human nervous system and profoundly affecting individuals' motor and cognitive functions. Early diagnosis and monitoring of the progression of NDDs are of critical importance.</p><p><strong>Objective: </strong>The primary aim of this study is to present an automatic diagnostic method using time-domain analysis of short-term gait signals of two consecutive steps, for the classification of Parkinson's Disease (PD), Huntington's Disease (HD), Amyotrophic Lateral Sclerosis (ALS), and a Healthy Control Group (HC).</p><p><strong>Material and methods: </strong>This analytical study used datasets from PhysioNet, including 64 five-minute recordings from 13 individuals with ALS, 15 with Parkinson's, 20 with Huntington's, and 16 healthy individuals. To reduce noise and enhance signal quality, a median filter was applied. The preprocessed gait signals were then systematically segmented into consecutive two-step windows, which were used to construct the feature vectors. Finally, the constructed feature vectors were used as inputs for both linear and nonlinear classifiers. The proposed method was evaluated by calculating the accuracy index.</p><p><strong>Results: </strong>The quaternary classification of ALS vs. PD vs. HD vs. HC using the bag-tree classifier achieved an accuracy of 82.8%. Furthermore, for the binary classifications of HC vs. HD, HC vs. ALS, HC vs. PD and NDD vs. HC, the accuracies were 88.4%, 97.6%, 90% and 89.1%, respectively.</p><p><strong>Conclusion: </strong>Gait dynamics analysis has a high potential for the rapid diagnosis of neurodegenerative diseases. Short term analysis in two consecutive stages enables the use of the Kinect sensor for gait analysis.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"395-406"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658911/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184906","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":"Advancing Breast Cancer Diagnosis with Deep Layer-wise Feature Integration from Histopathology Images.","authors":"Maryam Madani, Hasti Shabani","doi":"10.31661/jbpe.v0i0.2508-1970","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2508-1970","url":null,"abstract":"<p><strong>Background: </strong>Breast Cancer (BC) remains a leading cause of cancer-related deaths among women. Diagnosis from histopathology images can be inconsistent in pathologist assessments, highlighting the need for reliable computer-aided diagnostic systems. Existing approaches overlook multi-layer features or employ extraction methods that lack generalizability.</p><p><strong>Objective: </strong>This study proposes a layer-wise feature integration framework to enhance BC histopathology classification.</p><p><strong>Material and methods: </strong>In this analytical and computational study, using the BreakHis and ICIAR/BACH datasets, features are extracted from intermediate and high-level layers of pre-trained Convolutional Neural Networks (CNNs). Mutual Information (MI) between each layer's features and true labels is computed to identify the most informative layers, and those with the highest MI are selected. To address overfitting, Principal Component Analysis (PCA) with optimal Cumulative Explained Variance (CEV) is applied. The transformed features are then concatenated and classified using a Support Vector Machine (SVM).</p><p><strong>Results: </strong>The method is evaluated using VGG19, DenseNet, and ConvNextTiny across both datasets and demonstrates significant improvements in image-wise and patient-wise classification. ConvNextTiny, enhanced with Synthetic Minority Oversampling Technique (SMOTE) for class-imbalance mitigation, achieves the highest accuracy of 99.14% at 40× in BreakHis dataset.</p><p><strong>Conclusion: </strong>Although the achieved accuracies of 97.32% and 99.14% (without and with imbalance handling, respectively), are slightly below the best-reported results, the method offers notable advantages in simplicity and computational efficiency. It provides a lightweight alternative to ensemble-based or fine-tuned deep models. Results highlight the critical role of intermediate layers in capturing discriminative features and challenge reliance on final-layer outputs for histopathology image classification.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"407-424"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658907/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184800","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":"Beyond Physical Shielding: The Case for Biological Protection in Deep Space.","authors":"Seyed Mohammad Javad Mortazavi, Joseph J Bevelacqua, James S Welsh","doi":"10.31661/jbpe.v0i0.2609-2162","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2609-2162","url":null,"abstract":"","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"361-364"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184876","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":"Radioprotective Effect of α-Tocotrienol on Radiation-Induced Brain Injury in Rats.","authors":"Karim Ghazikhanlou Sani, Muhammad Javad Ebrahimi, Salman Jafari, Abbas Bakhtiari","doi":"10.31661/jbpe.v0i0.2505-1923","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2505-1923","url":null,"abstract":"<p><strong>Background: </strong>In medicine, ionizing radiation can damage cells by generating free radicals, harming healthy tissues during radiotherapy. Radioprotectors help mitigate this damage, but current options often have low efficacy, high cost, or side effects.</p><p><strong>Objective: </strong>This study aimed to investigate α-Tocotrienol, a vitamin E isomer with antioxidant and anti-cancer properties, as a potential radioprotector for brain radiotherapy patients and radiation workers. While its protective effects on normal brain tissue are promising, its potential impact on tumor cells remains a critical consideration for future studies.</p><p><strong>Material and methods: </strong>This randomized controlled experimental animal study was conducted on healthy male Wistar rats maintained under standardized laboratory conditions. The animals were randomly divided into groups and pretreated with α-Tocotrienol prior to localized brain irradiation. Following irradiation, brain tissues were harvested and evaluated for histopathological alterations and biochemical markers of oxidative stress.</p><p><strong>Results: </strong>Pretreated rats with α-Tocotrienol showed fewer nerve cell injuries compared to untreated irradiated rats. Biochemically, irradiated rats had increased malondialdehyde (oxidative stress marker) and decreased antioxidant enzymes (superoxide dismutase, catalase, glutathione peroxidase), while α-Tocotrienol-treated rats maintained higher enzyme activity.</p><p><strong>Conclusion: </strong>α-Tocotrienol enhances radiation resistance by boosting antioxidant defenses and reducing neuronal damage. However, given the possibility of parallel protection of tumor cells, its clinical translation requires careful evaluation and optimization. Further studies are needed to determine selective dosing strategies and timing that maximize neuroprotection without compromising tumor control.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"373-382"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184844","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 Infant Brain MR Image Segmentation Method with Attention Mechanism, Multi-Resolution Deep Supervision and Class Weight Tuning Strategy.","authors":"Mohamad Reza Akbarzadeh Lari, Habibollah Danyali, Kamran Kazemi","doi":"10.31661/jbpe.v0i0.2512-2034","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2512-2034","url":null,"abstract":"<p><strong>Background: </strong>Infant brain tissue segmentation is critical for understanding early brain development and detecting neurodevelopmental abnormalities. However, accurate segmentation remains challenging due to partial-volume effects, imaging noise, and low contrast between tissues in isointense regions.</p><p><strong>Objective: </strong>This study aimed to automatically segment infant brain Magnetic Resonance Imaging (MRI) images into white matter, gray matter, and cerebrospinal fluid.</p><p><strong>Material and methods: </strong>In this analytical study, we addressed the challenges of infant brain tissue segmentation. We proposed a deep, lightweight dense backbone architecture incorporating transition blocks. The backbone was enhanced with a spatial-channel attention mechanism to capture global dependencies and emphasize task-relevant features, as well as multi-resolution deep supervision to mitigate vanishing gradients and reduce overfitting. Moreover, we used class weighting strategy to deal with class imbalance and low contrast between brain tissues.</p><p><strong>Results: </strong>Our method attains Dice similarity scores of 91.80%, 92.07% and 94.58% for white matter, gray matter, and cerebrospinal fluid, respectively. Quantitative and qualitative evaluations show that the proposed approach accurately segments infant brain MR images and reduces errors in isointense regions.</p><p><strong>Conclusion: </strong>The results demonstrate that the proposed method precisely delineates infant brain tissues and effectively overcomes common segmentation challenges.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"383-394"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184822","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 [18F]-FDG PET/CT Image Dataset for Artificial Intelligence-Based Classification of Lung Cancer.","authors":"Mohammad Karimpour, Alireza Mehdizadeh, Mehrosadat Alavi, Tahereh Mahmoudi","doi":"10.31661/jbpe.v0i0.2607-2122","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2607-2122","url":null,"abstract":"<p><p>Lung cancer is a leading cause of cancer-related mortality worldwide. [18F]-fluorodeoxyglucose ([18F]-FDG) Positron Emission Tomography/Computed Tomography (PET/CT) imaging is an advanced medical imaging modality used for lung cancer diagnosis. However, despite the availability of such an imaging modality, current methods of diagnosing cancer and interpreting images are prone to error. Therefore, Artificial Intelligence (AI)-based methods for medical image analysis are introduced and widely applied to enhance diagnostic accuracy. These methods, particularly deep learning techniques, require large datasets. Collecting image datasets, especially PET/CT images, is time-consuming, labor-intensive, and in some instances impossible due to the high costs and low availability of imaging centers. To facilitate further research in AI for lung cancer diagnosis, we present a publicly available 2D [18F]-FDG PET/CT lung image dataset comprising 3,061 image slices obtained from 94 patients. The dataset provides pathology-confirmed ground truth annotations together with patient-level identifiers, making it suitable for developing, validating, benchmarking, and comparing AI algorithms for lung cancer classification, localization, explainable AI, and other PET/CT-based computer-aided diagnostic applications.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"425-430"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658906/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184803","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":"Comparison of the Measurement Uncertainty of Thermoluminescence Dosimeters (TLD-100 and GR-200) in Clinical Radiotherapy Energies.","authors":"Bahare Sadeghi, Reza Pur Imani, Hossein Kiani, Mohamad Reza Bayatiani, Fatemeh Seif","doi":"10.31661/jbpe.v0i0.2410-1847","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2410-1847","url":null,"abstract":"<p><strong>Background: </strong>Accurate determination of individual radiation doses is critical in dosimetry, and international standards emphasize the importance of reporting measurement uncertainties. Neglecting measurement uncertainty undermines the reliability of reported dosimetric values, as emphasized by international standards.</p><p><strong>Objective: </strong>This study aimed to evaluate the measurement of uncertainties in two Thermoluminescent Dosimeters (TLDs)-100 and GR-200, in the dose range of 30-150 cGy.</p><p><strong>Material and methods: </strong>In this experimental study, we evaluated the measurement of uncertainties in two thermoluminescent dosimeters, TLD-100 and GR-200, in the dose range of 30-150 cGy. The study investigated both random (Type A) and systematic (Type B) uncertainties. Random uncertainties include the non-uniformity of dosimeter sensitivity Element Correction Coefficient (ECC), variability in dosimeter response at zero dose, and repeatability. Systematic uncertainties include the dependence of dosimeter response on radiation energy, radiation angle, nonlinearity of dosimeter response, fading, ambient light effects, and reference calibration errors.</p><p><strong>Results: </strong>The total uncertainty for TLD-100 was calculated as 10.99% at a 68% confidence level (21.99% at 95% confidence), while for GR-200, it was 13.63% at a 68% confidence level (27.26% at 95% confidence). These values are well below the 42% threshold recommended by the International Atomic Energy Agency (IAEA) for personal dosimetry services.</p><p><strong>Conclusion: </strong>The GR-200 exhibits higher sensitivity for low-dose radiation detection; however, its greater uncertainty makes TLD-100 more suitable for clinical and personal dosimetry applications, where precision and reliability are paramount.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"365-372"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658908/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184857","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":"Optical Dynamics of Violet and Blue Light in Myopia Development: A Comparative and Historical Analysis.","authors":"M Hossein Nowroozzadeh, Joshua Ong, Mohsen Ostovari, Ethan Waisberg, Seyed Mohammad Javad Mortazavi, Kaveh Abri Aghdam, Seyed Alireza Mortazavi","doi":"10.31661/jbpe.v0i0.2501-1882","DOIUrl":"https://doi.org/10.31661/jbpe.v0i0.2501-1882","url":null,"abstract":"<p><p>The rising prevalence of myopia in children has become a major concern due to its long-term effects on eye health and vision. This increase has prompted extensive research into the environmental and biological factors influencing eye development. Recent studies highlight the critical role of specific light wavelengths, particularly violet (360-400 nm) and blue (400-500 nm), in regulating eye growth. Violet light is thought to support choroidal health by activating photopigments in the retina, helping to maintain proper eye growth and reduce the risk of myopia. Conversely, the elimination of blue light through blue-blocking lenses has been linked to changes in the refractive dynamics of the eye, potentially contributing to excessive axial elongation a key characteristic of myopia. Modern lighting systems, such as LED lights and the widespread use of blue-blocking lenses, have disrupted natural light exposure, reducing access to these critical wavelengths. One perspective emphasizes the importance of reintroducing violet light into children's environments through natural sunlight and specially designed lighting systems to stabilize eye growth. Another approach focuses on minimizing the prolonged use of blue-blocking lenses during critical periods of eye development, cautioning against unintended structural changes in the eye. Future research should evaluate the potential of artificial violet light for controlling myopia, and quantify the differences between indoor and outdoor light environments. A comprehensive understanding of these factors is essential for creating effective strategies, such as optimized lighting and lens designs, to address the growing challenge of myopia in children.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 5","pages":"431-434"},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149184917","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":"PET-based Radiomics Analysis for Predicting Prognosis and Differentiation Treatment-Related Changes in Glioma: A Systematic Review.","authors":"Mahsa Shakeri, Azadeh Amraee, Seyyed Mohammad Hosseini, Leili Darvish, Forough Farkhondeh, Ahmad Mostaar, Hossein Ghadiri","doi":"10.31661/jbpe.v0i0.2409-1821","DOIUrl":"10.31661/jbpe.v0i0.2409-1821","url":null,"abstract":"<p><strong>Background: </strong>The assessment of treatment-induced changes in glioma and the evaluation of glioma prognosis are crucial components of effective treatment management. Radiomics models based on Positron Emission Tomography (PET) imaging can provide critical insights into therapeutic response monitoring.</p><p><strong>Objective: </strong>This systematic review aimed to evaluate the performance of PET-based radiomics models in distinguishing treatment-related changes and predicting the prognosis of glioma.</p><p><strong>Material and methods: </strong>In this systematic review, the articles were searched from the Web of Science databases, MEDLINE, PubMed, and EMBASE. The search terms were \"amino acid PET\", \"PET\", \"glioblastoma\", \"glioma\", \"positron emission tomography\", \"machine learning\", \"deep learning\", \"radiomics\", \"artificial intelligence\", \"AI\", \"prognosis\", \"outcome\", \"post treatment changes\", \"treatment-related changes\", \"progression\", \"true progression\" \"pseudo-progression\", and \"necrosis\". The titles, abstracts, and full text of the recognized citations were reviewed by two independent reviewers and then the selected articles were abstracted by two independent reviewers based on a standard grid. PRISMA checklist was applied to assess the overall quality of evidence for each outcome.</p><p><strong>Results: </strong>The PET-based radiomics models outperform conventional PET parameter models, such as maximum tumor-to-brain ratios and mean tumor-to-brain ratios in distinguishing post-treatment changes and predicting glioma prognosis. The model integrating radiomics features and the conventional PET parameters achieved superior diagnostic performance compared to radiomics and conventional parameter models solely in differentiation treatment related changes.</p><p><strong>Conclusion: </strong>PET based radiomics models demonstrate enhanced capability in differentiating tumor recurrence from treatment-related changes. The implementation of these models can facilitate personalized treatment plans and increase the patient's overall survival or quality of life.</p>","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 4","pages":"267-284"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13457499/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148713932","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":"Quantum Biology; From Classic Medical Physics to Quantum Medicine.","authors":"Seyedeh Haniyeh Mortazavi, Alireza Mehdizadeh","doi":"10.31661/jbpe.v0i0.2606-2114","DOIUrl":"10.31661/jbpe.v0i0.2606-2114","url":null,"abstract":"","PeriodicalId":38035,"journal":{"name":"Journal of Biomedical Physics and Engineering","volume":"16 4","pages":"265-266"},"PeriodicalIF":0.0,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13457671/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148713878","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}