Pub Date : 2024-10-15DOI: 10.1088/2057-1976/ad8095
Ishan R Sathone, Umesh G Potdar
Tibial fractures account for approximately 15% of all fractures, typically resulting from high-energy trauma. A critical surgical approach to treat these fractures involves the fixation of the tibia using a plate with minimally invasive osteosynthesis. The selection and fixation of the implant plate are vital for stabilizing the fracture. This selection is highly dependent on the plate's stability, which is influenced by factors like the stresses generated in the plate due to the load on the bone, as well as the plate's length, thickness, and number of screw holes. Minimizing these stresses is essential to reduce the risk of implant failure, ensuring optimal stress distribution and promoting faster, more effective bone healing. In the present work, the finite element and statistical approach was used to optimize the geometrical parameters of the implant plate made of SS 316L steel and Ti6Al4V alloy. A 3D finite element model was developed for analyzing the stresses and deformation, and implant plates were manufactured to validate the results with the help of an experiment conducted on the universal testing machine. A strong correlation was observed between the experimental and predicted results, with an average error of 8.6% and 8.55% for SS316L and Ti6Al4V alloy, respectively. Further, using the signal-to-noise ratio for the minimum stress condition was applied to identify the optimum parameters of the plate. Finally, regression models were developed to predict the stresses generated in SS316L and Ti6Al4V alloy plates with different input conditions. The statistical model helps us to develop the relation between different geometrical parameters of the Tibia implant plate. As determined by the present work, the parameter most influencing is implant plate length. This outcome will be used to select the implant for a specific patient, resulting in a reduction in implant failure post-surgery.
{"title":"Finite element analysis and optimization studies on tibia implant of SS 316L steel and Ti6Al4V alloy.","authors":"Ishan R Sathone, Umesh G Potdar","doi":"10.1088/2057-1976/ad8095","DOIUrl":"10.1088/2057-1976/ad8095","url":null,"abstract":"<p><p>Tibial fractures account for approximately 15% of all fractures, typically resulting from high-energy trauma. A critical surgical approach to treat these fractures involves the fixation of the tibia using a plate with minimally invasive osteosynthesis. The selection and fixation of the implant plate are vital for stabilizing the fracture. This selection is highly dependent on the plate's stability, which is influenced by factors like the stresses generated in the plate due to the load on the bone, as well as the plate's length, thickness, and number of screw holes. Minimizing these stresses is essential to reduce the risk of implant failure, ensuring optimal stress distribution and promoting faster, more effective bone healing. In the present work, the finite element and statistical approach was used to optimize the geometrical parameters of the implant plate made of SS 316L steel and Ti6Al4V alloy. A 3D finite element model was developed for analyzing the stresses and deformation, and implant plates were manufactured to validate the results with the help of an experiment conducted on the universal testing machine. A strong correlation was observed between the experimental and predicted results, with an average error of 8.6% and 8.55% for SS316L and Ti6Al4V alloy, respectively. Further, using the signal-to-noise ratio for the minimum stress condition was applied to identify the optimum parameters of the plate. Finally, regression models were developed to predict the stresses generated in SS316L and Ti6Al4V alloy plates with different input conditions. The statistical model helps us to develop the relation between different geometrical parameters of the Tibia implant plate. As determined by the present work, the parameter most influencing is implant plate length. This outcome will be used to select the implant for a specific patient, resulting in a reduction in implant failure post-surgery.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142340546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1088/2057-1976/ad8202
Sachin Deshmukh, Aditya Chand, Ratnakar Ghorpade
A scaffold is a three-dimensional porous structure that is used as a template to provide structural support for cell adhesion and the formation of new cells. Metallic cellular scaffolds are a good choice as a replacement for human bones in orthopaedic implants, which enhances the quality and longevity of human life. In contrast to conventional methods that produce irregular pore distributions, 3D printing, or additive manufacturing, is characterized by high precision and controlled manufacturing processes. AM processes can precisely control the scaffold's porosity, which makes it possible to produce patient specific implants and achieve regular pore distribution. This review paper explores the potential of Ti-6Al-4V scaffolds produced via the SLM method as a bone substitute. A state-of-the-art review on the effect of design parameters, material, and surface modification on biological and mechanical properties is presented. The desired features of the human tibia and femur bones are compared to bulk and porous Ti6Al4V scaffold. Furthermore, the properties of various porous scaffolds with varying unit cell structures and design parameters are compared to find out the designs that can mimic human bone properties. Porosity up to 65% and pore size of 600 μm was found to give optimum trade-off between mechanical and biological properties. Current manufacturing constraints, biocompatibility of Ti-6Al-4V material, influence of various factors on bio-mechanical properties, and complex interrelation between design parameters are discussed herein. Finally, the most appropriate combination of design parameters that offers a good trade-off between mechanical strength and cell ingrowth are summarized.
{"title":"Bio-mechanical analysis of porous Ti-6Al-4V scaffold: a comprehensive review on unit cell structures in orthopaedic application.","authors":"Sachin Deshmukh, Aditya Chand, Ratnakar Ghorpade","doi":"10.1088/2057-1976/ad8202","DOIUrl":"10.1088/2057-1976/ad8202","url":null,"abstract":"<p><p>A scaffold is a three-dimensional porous structure that is used as a template to provide structural support for cell adhesion and the formation of new cells. Metallic cellular scaffolds are a good choice as a replacement for human bones in orthopaedic implants, which enhances the quality and longevity of human life. In contrast to conventional methods that produce irregular pore distributions, 3D printing, or additive manufacturing, is characterized by high precision and controlled manufacturing processes. AM processes can precisely control the scaffold's porosity, which makes it possible to produce patient specific implants and achieve regular pore distribution. This review paper explores the potential of Ti-6Al-4V scaffolds produced via the SLM method as a bone substitute. A state-of-the-art review on the effect of design parameters, material, and surface modification on biological and mechanical properties is presented. The desired features of the human tibia and femur bones are compared to bulk and porous Ti6Al4V scaffold. Furthermore, the properties of various porous scaffolds with varying unit cell structures and design parameters are compared to find out the designs that can mimic human bone properties. Porosity up to 65% and pore size of 600 μm was found to give optimum trade-off between mechanical and biological properties. Current manufacturing constraints, biocompatibility of Ti-6Al-4V material, influence of various factors on bio-mechanical properties, and complex interrelation between design parameters are discussed herein. Finally, the most appropriate combination of design parameters that offers a good trade-off between mechanical strength and cell ingrowth are summarized.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142364238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-14DOI: 10.1088/2057-1976/ad2a1a
Erdem Atbas, Patrick Gaydecki, Michael J Callaghan
Idiopathic Normal Pressure Hydrocephalus (iNPH) is a progressive neurologic disorder (fluid build-up in the brain) that affects 0.2%-5% of the UK population aged over 65. Mobility problems, dementia and urinary incontinence are symptoms of iNPH but often these are not properly evaluated, and patients receive the wrong diagnosis. Here, we describe the development and testing of firmware embedded in a wearable device in conjunction with a user-based software system that records and analyses a patient's gait. The movement patterns, expressed as quantitative data, allow clinicians to improve the non-invasive assessment of iNPH as well as monitor the management of patients undergoing treatment. The wearable sensor system comprises a miniature electronic unit that attaches to one ankle of the patient via a simple Velcro strap which was designed for this application. The unit monitors acceleration along three axes with a sample rate of 60 Hz and transmits the data via a Bluetooth communication link to a tablet or smart phone running the Android and the iOS operating systems. The software package extracts statistics based on stride length, stride height, distance walked and speed. Analysis confirmed that the system achieved an average accuracy of at least 98% for gait tests conducted over distances 9 m. This device has been developed to assist in the management and treatment of older adults diagnosed with iNPH.
{"title":"A wearable gait-analysis device for idiopathic normal-pressure hydrocephalus (INPH) monitoring.","authors":"Erdem Atbas, Patrick Gaydecki, Michael J Callaghan","doi":"10.1088/2057-1976/ad2a1a","DOIUrl":"10.1088/2057-1976/ad2a1a","url":null,"abstract":"<p><p>Idiopathic Normal Pressure Hydrocephalus (iNPH) is a progressive neurologic disorder (fluid build-up in the brain) that affects 0.2%-5% of the UK population aged over 65. Mobility problems, dementia and urinary incontinence are symptoms of iNPH but often these are not properly evaluated, and patients receive the wrong diagnosis. Here, we describe the development and testing of firmware embedded in a wearable device in conjunction with a user-based software system that records and analyses a patient's gait. The movement patterns, expressed as quantitative data, allow clinicians to improve the non-invasive assessment of iNPH as well as monitor the management of patients undergoing treatment. The wearable sensor system comprises a miniature electronic unit that attaches to one ankle of the patient via a simple Velcro strap which was designed for this application. The unit monitors acceleration along three axes with a sample rate of 60 Hz and transmits the data via a Bluetooth communication link to a tablet or smart phone running the Android and the iOS operating systems. The software package extracts statistics based on stride length, stride height, distance walked and speed. Analysis confirmed that the system achieved an average accuracy of at least 98% for gait tests conducted over distances 9 m. This device has been developed to assist in the management and treatment of older adults diagnosed with iNPH.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139745960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-11DOI: 10.1088/2057-1976/ad81ff
Mariem Trabelsi, Hamida Romdhane, Lotfi Ben Salem, Dorra Ben-Sellem
The integration of artificial intelligence (AI) into lung cancer management offers immense potential to revolutionize diagnostic and treatment strategies. The aim is to develop a resilient AI framework capable of two critical tasks: firstly, achieving accurate and automated segmentation of lung tumors and secondly, facilitating the T classification of lung cancer according to the ninth edition of TNM staging 2024 based on PET/CT imaging. This study presents a robust AI framework for the automated segmentation of lung tumors and T classification of lung cancer using PET/CT imaging. The database includes axial DICOM CT and18FDG-PET/CT images. A modified ResNet-50 model was employed for segmentation, achieving high precision and specificity. Reconstructed 3D models of segmented slices enhance tumor boundary visualization, which is essential for treatment planning. The Pulmonary Toolkit facilitated lobe segmentation, providing critical diagnostic insights. Additionally, the segmented images were used as input for the T classification using a CNN ResNet-50 model. Our classification model demonstrated excellent performance, particularly for T1a, T2a, T2b, T3 and T4 tumors, with high precision, F1 scores, and specificity. The T stage is particularly relevant in lung cancer as it determines treatment approaches (surgery, chemotherapy and radiation therapy or supportive care) and prognosis assessment. In fact, for Tis-T2, each increase of one centimeter in tumor size results in a worse prognosis. For locally advanced tumors (T3-T4) and regardless of size, the prognosis is poorer. This AI framework marks a significant advancement in the automation of lung cancer diagnosis and staging, promising improved patient outcomes.
{"title":"Advanced artificial intelligence framework for T classification of TNM lung cancer in<sup>18</sup>FDG-PET/CT imaging.","authors":"Mariem Trabelsi, Hamida Romdhane, Lotfi Ben Salem, Dorra Ben-Sellem","doi":"10.1088/2057-1976/ad81ff","DOIUrl":"10.1088/2057-1976/ad81ff","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) into lung cancer management offers immense potential to revolutionize diagnostic and treatment strategies. The aim is to develop a resilient AI framework capable of two critical tasks: firstly, achieving accurate and automated segmentation of lung tumors and secondly, facilitating the T classification of lung cancer according to the ninth edition of TNM staging 2024 based on PET/CT imaging. This study presents a robust AI framework for the automated segmentation of lung tumors and T classification of lung cancer using PET/CT imaging. The database includes axial DICOM CT and<sup>18</sup>FDG-PET/CT images. A modified ResNet-50 model was employed for segmentation, achieving high precision and specificity. Reconstructed 3D models of segmented slices enhance tumor boundary visualization, which is essential for treatment planning. The Pulmonary Toolkit facilitated lobe segmentation, providing critical diagnostic insights. Additionally, the segmented images were used as input for the T classification using a CNN ResNet-50 model. Our classification model demonstrated excellent performance, particularly for T1a, T2a, T2b, T3 and T4 tumors, with high precision, F1 scores, and specificity. The T stage is particularly relevant in lung cancer as it determines treatment approaches (surgery, chemotherapy and radiation therapy or supportive care) and prognosis assessment. In fact, for Tis-T2, each increase of one centimeter in tumor size results in a worse prognosis. For locally advanced tumors (T3-T4) and regardless of size, the prognosis is poorer. This AI framework marks a significant advancement in the automation of lung cancer diagnosis and staging, promising improved patient outcomes.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":"10 6","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142457122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1088/2057-1976/ad8200
Tao Sun, Changqing Liu, Ling Kong, Jingjing Zha, Guohua Ni
Cold atmospheric plasma (CAP) has been extensively utilized in medical treatment, particularly in cancer therapy. However, the underlying mechanism of CAP in skin cancer treatment remains elusive. In this study, we established a skin cancer model using CAP treatmentin vitro. Also, we established the Xenograft experiment modelin vivo. The results demonstrated that treatment with CAP induced ferroptosis, resulting in a significant reduction in the viability, migration, and invasive capacities of A431 squamous cell carcinoma, a type of skin cancer. Mechanistically, the significant production of reactive oxygen species (ROS) by CAP induces DNA damage, which then activates Ataxia-telangiectasia mutated (ATM) and p53 through acetylation, while simultaneously suppressing the expression of Solute Carrier Family 7 Member 11 (SLC7A11). Consequently, this cascade led to the down-regulation of intracellular Glutathione peroxidase 4 (GPX4), ultimately resulting in ferroptosis. CAP exhibits a favorable impact on skin cancer treatment, suggesting its potential medical application in skin cancer therapy.
冷大气等离子体(CAP)已被广泛应用于医疗领域,尤其是癌症治疗。然而,冷大气等离子体治疗皮肤癌的基本机制仍不明确。在本研究中,我们在体外建立了使用 CAP 治疗的皮肤癌模型。此外,我们还在体内建立了异种移植实验模型。结果表明,CAP 能诱导铁变态反应,从而显著降低 A431 鳞状细胞癌(一种皮肤癌)的存活率、迁移和侵袭能力。从机理上讲,CAP产生的大量活性氧(ROS)会诱导DNA损伤,然后通过乙酰化激活共济失调-特朗吉赛病突变(ATM)和p53,同时抑制溶质运载家族7成员11(SLC7A11)的表达。因此,这种级联反应导致细胞内谷胱甘肽过氧化物酶 4(GPX4)的下调,最终导致铁变态反应。CAP 对皮肤癌的治疗产生了有利影响,这表明它在皮肤癌治疗中具有潜在的医学应用价值。
{"title":"Cold plasma irradiation inhibits skin cancer via ferroptosis.","authors":"Tao Sun, Changqing Liu, Ling Kong, Jingjing Zha, Guohua Ni","doi":"10.1088/2057-1976/ad8200","DOIUrl":"10.1088/2057-1976/ad8200","url":null,"abstract":"<p><p>Cold atmospheric plasma (CAP) has been extensively utilized in medical treatment, particularly in cancer therapy. However, the underlying mechanism of CAP in skin cancer treatment remains elusive. In this study, we established a skin cancer model using CAP treatment<i>in vitro</i>. Also, we established the Xenograft experiment model<i>in vivo</i>. The results demonstrated that treatment with CAP induced ferroptosis, resulting in a significant reduction in the viability, migration, and invasive capacities of A431 squamous cell carcinoma, a type of skin cancer. Mechanistically, the significant production of reactive oxygen species (ROS) by CAP induces DNA damage, which then activates Ataxia-telangiectasia mutated (ATM) and p53 through acetylation, while simultaneously suppressing the expression of Solute Carrier Family 7 Member 11 (SLC7A11). Consequently, this cascade led to the down-regulation of intracellular Glutathione peroxidase 4 (GPX4), ultimately resulting in ferroptosis. CAP exhibits a favorable impact on skin cancer treatment, suggesting its potential medical application in skin cancer therapy.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":"10 6","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142399228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-10DOI: 10.1088/2057-1976/ad857b
Jai Kumar B, Mohanasundaram Ranganathan
Currently, Diabetes Mellitus (DM) can be life-threatening due to the dietary habits and lifestyle choices of individuals. Diabetes is characterised by elevated levels of glucose in the blood and an excess of protein in the blood. Poor eating habits and lifestyles are largely responsible for the rise in overweight, obesity, and various related conditions. This study investigated many diabetes-related risk forecasting techniques and algorithms. The eight machine learning (ML) algorithms used the diabetes dataset to test various prediction techniques, including a Support Vector Classifier, gradient-boosting, multilayer perceptron, random forest, K-nearest neighbors, logistic regression, extreme gradient boosting, and decision tree. To enhance the diabetic prediction ability of the model, we suggested using Feature Engineering (FE) and feature scaling. For our investigation, we utilized the Mendeley dataset on diabetes to assess the capacity of the model to predict diabetes. We developed a model by using Python programming and eight classification techniques. The Random Forest with 99.21%, Gradient Boosting with 99.61%, Extreme Gradient Boosting, and Decision Tree achieved the highest F1 score (99.81%), accuracy rate (99.80%), precision (99.81%), and recall (99.81%) of all classification approaches.
目前,由于个人饮食习惯和生活方式的选择,糖尿病(DM)可能危及生命。糖尿病的特征是血液中葡萄糖水平升高和血液中蛋白质过量。不良的饮食习惯和生活方式是导致超重、肥胖和各种相关疾病增加的主要原因。本研究调查了许多与糖尿病相关的风险预测技术和算法。八种机器学习(ML)算法使用糖尿病数据集来测试各种预测技术,包括支持向量分类器、梯度提升、多层感知器、随机森林、K-近邻、逻辑回归、极端梯度提升和决策树。为了提高模型的糖尿病预测能力,我们建议使用特征工程(FE)和特征缩放。在调查中,我们利用 Mendeley 糖尿病数据集来评估模型预测糖尿病的能力。我们使用 Python 编程和八种分类技术开发了一个模型。在所有分类方法中,随机森林(99.21%)、梯度提升(99.61%)、极端梯度提升和决策树分别获得了最高的 F1 分数(99.81%)、准确率(99.80%)、精确率(99.81%)和召回率(99.81%)。
{"title":"A machine learning classifier-based approach for diabetes mellitus risk prediction.","authors":"Jai Kumar B, Mohanasundaram Ranganathan","doi":"10.1088/2057-1976/ad857b","DOIUrl":"https://doi.org/10.1088/2057-1976/ad857b","url":null,"abstract":"<p><p>Currently, Diabetes Mellitus (DM) can be life-threatening due to the dietary habits and lifestyle choices of individuals. Diabetes is characterised by elevated levels of glucose in the blood and an excess of protein in the blood. Poor eating habits and lifestyles are largely responsible for the rise in overweight, obesity, and various related conditions. This study investigated many diabetes-related risk forecasting techniques and algorithms. The eight machine learning (ML) algorithms used the diabetes dataset to test various prediction techniques, including a Support Vector Classifier, gradient-boosting, multilayer perceptron, random forest, K-nearest neighbors, logistic regression, extreme gradient boosting, and decision tree. To enhance the diabetic prediction ability of the model, we suggested using Feature Engineering (FE) and feature scaling. For our investigation, we utilized the Mendeley dataset on diabetes to assess the capacity of the model to predict diabetes. We developed a model by using Python programming and eight classification techniques. The Random Forest with 99.21%, Gradient Boosting with 99.61%, Extreme Gradient Boosting, and Decision Tree achieved the highest F1 score (99.81%), accuracy rate (99.80%), precision (99.81%), and recall (99.81%) of all classification approaches.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142399227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-09DOI: 10.1088/2057-1976/ad8094
Amira Mohamed, Doha Eid, Mariam M Ezzat, Mayar Ehab, Maye Khaled, Sarah Gaber, Amira Gaber
Facial paralysis (FP) is a condition characterized by the inability to move some or all of the muscles on one or both sides of the face. Diagnosing FP presents challenges due to the limitations of traditional methods, which are time-consuming, uncomfortable for patients, and require specialized clinicians. Additionally, more advanced tools are often uncommonly available to all healthcare providers. Early and accurate detection of FP is crucial, as timely intervention can prevent long-term complications and improve patient outcomes. To address these challenges, our research introduces Facia-Fix, a mobile application for Bell's palsy diagnosis, integrating computer vision and deep learning techniques to provide real-time analysis of facial landmarks. The classification algorithms are trained on the publicly available YouTube FP (YFP) dataset, which is labeled using the House-Brackmann (HB) method, a standardized system for assessing the severity of FP. Different deep learning models were employed to classify the FP severity, such as MobileNet, CNN, MLP, VGG16, and Vision Transformer. The MobileNet model which uses transfer learning, achieved the highest performance (Accuracy: 0.9812, Precision: 0.9753, Recall: 0.9727, F1 Score: 0.974), establishing it as the optimal choice among the evaluated models. The innovation of this approach lies in its use of advanced deep learning models to provide accurate, objective, non-invasive and real-time comprehensive quantitative assessment of FP severity. Preliminary results highlight the potential of Facia-Fix to significantly improve the diagnostic and follow-up experiences for both clinicians and patients.
{"title":"Facia-fix: mobile application for bell's palsy diagnosis and assessment using computer vision and deep learning.","authors":"Amira Mohamed, Doha Eid, Mariam M Ezzat, Mayar Ehab, Maye Khaled, Sarah Gaber, Amira Gaber","doi":"10.1088/2057-1976/ad8094","DOIUrl":"10.1088/2057-1976/ad8094","url":null,"abstract":"<p><p>Facial paralysis (FP) is a condition characterized by the inability to move some or all of the muscles on one or both sides of the face. Diagnosing FP presents challenges due to the limitations of traditional methods, which are time-consuming, uncomfortable for patients, and require specialized clinicians. Additionally, more advanced tools are often uncommonly available to all healthcare providers. Early and accurate detection of FP is crucial, as timely intervention can prevent long-term complications and improve patient outcomes. To address these challenges, our research introduces Facia-Fix, a mobile application for Bell's palsy diagnosis, integrating computer vision and deep learning techniques to provide real-time analysis of facial landmarks. The classification algorithms are trained on the publicly available YouTube FP (YFP) dataset, which is labeled using the House-Brackmann (HB) method, a standardized system for assessing the severity of FP. Different deep learning models were employed to classify the FP severity, such as MobileNet, CNN, MLP, VGG16, and Vision Transformer. The MobileNet model which uses transfer learning, achieved the highest performance (Accuracy: 0.9812, Precision: 0.9753, Recall: 0.9727, F1 Score: 0.974), establishing it as the optimal choice among the evaluated models. The innovation of this approach lies in its use of advanced deep learning models to provide accurate, objective, non-invasive and real-time comprehensive quantitative assessment of FP severity. Preliminary results highlight the potential of Facia-Fix to significantly improve the diagnostic and follow-up experiences for both clinicians and patients.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142340545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-drug resistance (MDR) infections are a significant global challenge, necessitating innovative and eco-friendly approaches for developing effective antimicrobial agents. This study focuses on the synthesis, characterization, and evaluation of cerium oxide nanoparticles (CeO2NPs) for their antioxidant, anti-inflammatory, and antibacterial properties. The CeO2NPs were synthesized using aTribulus terrestrisaqueous extract through an environmentally friendly process. Characterization techniques included UV-visible spectroscopy, Fourier Transform Infrared Spectroscopy (FT-IR), x-ray Diffraction (XRD), Scanning Electron Microscopy (SEM), and Energy Dispersive x-ray (EDX) analysis. The UV-vis spectroscopy shows the presence of peak at 320 nm which confirms the formation of CeO2NPs. The FT-IR analysis of the CeO2NPs revealed several distinct functional groups, with peak values at 3287, 2920, 2340, 1640, 1538, 1066, 714, and 574 cm-1. These peaks correspond to specific functional groups, including C-H stretching in alkynes and alkanes, C=C=O, C=C, alkanes, C-O-C, C-Cl, and C-Br, indicating the presence of diverse chemical bonds within the CeO2NPs. XRD revealed that the nanoparticles were highly crystalline with a face-centered cubic structure, and SEM images showed irregularly shaped, agglomerated particles ranging from 100-150 nm. In terms of biological activity, the synthesized CeO2NPs demonstrated significant antioxidant and anti-inflammatory properties. The nanoparticles exhibited 82.54% antioxidant activity at 100 μg ml-1, closely matching the 83.1% activity of ascorbic acid. Additionally, the CeO2NPs showed 65.2% anti-inflammatory activity at the same concentration, compared to 70.1% for a standard drug. Antibacterial testing revealed that the CeO2NPs were particularly effective against multi-drug resistant strains, includingPseudomonas aeruginosa,Enterococcus faecalis, and MRSA, with moderate activity againstKlebsiella pneumoniae. These findings suggest that CeO2NPs synthesized viaT. terrestrishave strong potential as antimicrobial agents in addressing MDR infections.
{"title":"Green synthesis of cerium oxide nanoparticles using<i>Tribulus terrestris</i>: characterization and evaluation of antioxidant, anti-inflammatory and antibacterial efficacy against wound isolates.","authors":"Maganti Raghav Prasad Choudary, Muthuvel Surya, Muthupandian Saravanan","doi":"10.1088/2057-1976/ad7f59","DOIUrl":"10.1088/2057-1976/ad7f59","url":null,"abstract":"<p><p>Multi-drug resistance (MDR) infections are a significant global challenge, necessitating innovative and eco-friendly approaches for developing effective antimicrobial agents. This study focuses on the synthesis, characterization, and evaluation of cerium oxide nanoparticles (CeO<sub>2</sub>NPs) for their antioxidant, anti-inflammatory, and antibacterial properties. The CeO<sub>2</sub>NPs were synthesized using a<i>Tribulus terrestris</i>aqueous extract through an environmentally friendly process. Characterization techniques included UV-visible spectroscopy, Fourier Transform Infrared Spectroscopy (FT-IR), x-ray Diffraction (XRD), Scanning Electron Microscopy (SEM), and Energy Dispersive x-ray (EDX) analysis. The UV-vis spectroscopy shows the presence of peak at 320 nm which confirms the formation of CeO<sub>2</sub>NPs. The FT-IR analysis of the CeO<sub>2</sub>NPs revealed several distinct functional groups, with peak values at 3287, 2920, 2340, 1640, 1538, 1066, 714, and 574 cm<sup>-1</sup>. These peaks correspond to specific functional groups, including C-H stretching in alkynes and alkanes, C=C=O, C=C, alkanes, C-O-C, C-Cl, and C-Br, indicating the presence of diverse chemical bonds within the CeO<sub>2</sub>NPs. XRD revealed that the nanoparticles were highly crystalline with a face-centered cubic structure, and SEM images showed irregularly shaped, agglomerated particles ranging from 100-150 nm. In terms of biological activity, the synthesized CeO<sub>2</sub>NPs demonstrated significant antioxidant and anti-inflammatory properties. The nanoparticles exhibited 82.54% antioxidant activity at 100 μg ml<sup>-1</sup>, closely matching the 83.1% activity of ascorbic acid. Additionally, the CeO<sub>2</sub>NPs showed 65.2% anti-inflammatory activity at the same concentration, compared to 70.1% for a standard drug. Antibacterial testing revealed that the CeO<sub>2</sub>NPs were particularly effective against multi-drug resistant strains, including<i>Pseudomonas aeruginosa</i>,<i>Enterococcus faecalis</i>, and MRSA, with moderate activity against<i>Klebsiella pneumoniae</i>. These findings suggest that CeO<sub>2</sub>NPs synthesized via<i>T. terrestris</i>have strong potential as antimicrobial agents in addressing MDR infections.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142340559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-04DOI: 10.1088/2057-1976/ad7e2d
Amna Ghani, Hartmut Heinrich, Trevor Brown, Klaus Schellhorn
Automation is revamping our preprocessing pipelines, and accelerating the delivery of personalized digital medicine. It improves efficiency, reduces costs, and allows clinicians to treat patients without significant delays. However, the influx of multimodal data highlights the need to protect sensitive information, such as clinical data, and safeguard data fidelity. One of the neuroimaging modalities that produces large amounts of time-series data is Electroencephalography (EEG). It captures the neural dynamics in a task or resting brain state with high temporal resolution. EEG electrodes placed on the scalp acquire electrical activity from the brain. These electrical potentials attenuate as they cross multiple layers of brain tissue and fluid yielding relatively weaker signals than noise-low signal-to-noise ratio. EEG signals are further distorted by internal physiological artifacts, such as eye movements (EOG) or heartbeat (ECG), and external noise, such as line noise (50 Hz). EOG artifacts, due to their proximity to the frontal brain regions, are particularly challenging to eliminate. Therefore, a widely used EOG rejection method, independent component analysis (ICA), demands manual inspection of the marked EOG components before they are rejected from the EEG data. We underscore the inaccuracy of automatized ICA rejection and provide an auxiliary algorithm-Second Layer Inspection for EOG (SLOG) in the clinical environment. SLOG based on spatial and temporal patterns of eye movements, re-examines the already marked EOG artifacts and confirms no EEG-related activity is mistakenly eliminated in this artifact rejection step. SLOG achieved a 99% precision rate on the simulated dataset while 85% precision on the real EEG dataset. One of the primary considerations for cloud-based applications is operational costs, including computing power. Algorithms like SLOG allow us to maintain data fidelity and precision without overloading the cloud platforms and maxing out our budgets.
{"title":"Enhancing EEG data quality and precision for cloud-based clinical applications: an evaluation of the SLOG framework.","authors":"Amna Ghani, Hartmut Heinrich, Trevor Brown, Klaus Schellhorn","doi":"10.1088/2057-1976/ad7e2d","DOIUrl":"10.1088/2057-1976/ad7e2d","url":null,"abstract":"<p><p>Automation is revamping our preprocessing pipelines, and accelerating the delivery of personalized digital medicine. It improves efficiency, reduces costs, and allows clinicians to treat patients without significant delays. However, the influx of multimodal data highlights the need to protect sensitive information, such as clinical data, and safeguard data fidelity. One of the neuroimaging modalities that produces large amounts of time-series data is Electroencephalography (EEG). It captures the neural dynamics in a task or resting brain state with high temporal resolution. EEG electrodes placed on the scalp acquire electrical activity from the brain. These electrical potentials attenuate as they cross multiple layers of brain tissue and fluid yielding relatively weaker signals than noise-low signal-to-noise ratio. EEG signals are further distorted by internal physiological artifacts, such as eye movements (EOG) or heartbeat (ECG), and external noise, such as line noise (50 Hz). EOG artifacts, due to their proximity to the frontal brain regions, are particularly challenging to eliminate. Therefore, a widely used EOG rejection method, independent component analysis (ICA), demands manual inspection of the marked EOG components before they are rejected from the EEG data. We underscore the inaccuracy of automatized ICA rejection and provide an auxiliary algorithm-Second Layer Inspection for EOG (SLOG) in the clinical environment. SLOG based on spatial and temporal patterns of eye movements, re-examines the already marked EOG artifacts and confirms no EEG-related activity is mistakenly eliminated in this artifact rejection step. SLOG achieved a 99% precision rate on the simulated dataset while 85% precision on the real EEG dataset. One of the primary considerations for cloud-based applications is operational costs, including computing power. Algorithms like SLOG allow us to maintain data fidelity and precision without overloading the cloud platforms and maxing out our budgets.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142307069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-01DOI: 10.1088/2057-1976/ad8201
Negin Piran Nanekaran, Tony H Felefly, Nicola Schieda, Scott C Morgan, Richa Mittal, Eran Ukwatta
Background: The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy.
Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners.
Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion.
Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model.
Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.
{"title":"Prediction of prostate cancer recurrence after radiotherapy using a fused machine learning approach: Utilizing radiomics from pretreatment T2W MRI images with clinical and pathological information.","authors":"Negin Piran Nanekaran, Tony H Felefly, Nicola Schieda, Scott C Morgan, Richa Mittal, Eran Ukwatta","doi":"10.1088/2057-1976/ad8201","DOIUrl":"https://doi.org/10.1088/2057-1976/ad8201","url":null,"abstract":"<p><strong>Background: </strong>The risk of biochemical recurrence (BCR) after radiotherapy for localized prostate cancer (PCa) varies widely within standard risk groups. There is a need for low-cost tools to more robustly predict recurrence and personalize therapy. Radiomic features from pretreatment MRI show potential as noninvasive biomarkers for BCR prediction. However, previous research has not fully combined radiomics with clinical and pathological data to predict BCR in PCa patients following radiotherapy.
Purpose: This study aims to predict 5-year BCR using radiomics from pretreatment T2W MRI and clinical-pathological data in PCa patients treated with radiation therapy, and to develop a unified model compatible with both 1.5T and 3T MRI scanners.
Methods: A total of 150 T2W scans and clinical parameters were preprocessed. Of these, 120 cases were used for training and validation, and 30 for testing. Four distinct machine learning models were developed: Model 1 used radiomics, Model 2 used clinical and pathological data, and Model 3 combined these using late fusion. Model 4 integrated radiomic and clinical-pathological data using early fusion.
Results: Model 1 achieved an AUC of 0.73, while Model 2 had an AUC of 0.64 for predicting outcomes in 30 new test cases. Model 3, using late fusion, had an AUC of 0.69. Early fusion models showed strong potential, with Model 4 reaching an AUC of 0.84, highlighting the effectiveness of the early fusion model.
Conclusions: This study is the first to use a fusion technique for predicting BCR in PCa patients following radiotherapy, utilizing pre-treatment T2W MRI images and clinical-pathological data. The methodology improves predictive accuracy by fusing radiomics with clinical-pathological information, even with a relatively small dataset, and introduces the first unified model for both 1.5T and 3T MRI images.</p>","PeriodicalId":8896,"journal":{"name":"Biomedical Physics & Engineering Express","volume":" ","pages":""},"PeriodicalIF":1.3,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142364240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}