Medicine in Novel Technology and Devices最新文献_第6页

Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework 糖尿病病理图像分析：通过升级的resnet50框架进行精确分类

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-07-05 DOI: 10.1016/j.medntd.2025.100385

Caisheng Liao , Chenhao Pu , Tianqi Chen , Yuki Todo , Kengo Furuichi , Tomohisa Yabe , DeLai Qiu

{"title":"Image analysis of diabetes pathology: classifying with precision via an upgraded resnet50 framework","authors":"Caisheng Liao , Chenhao Pu , Tianqi Chen , Yuki Todo , Kengo Furuichi , Tomohisa Yabe , DeLai Qiu","doi":"10.1016/j.medntd.2025.100385","DOIUrl":"10.1016/j.medntd.2025.100385","url":null,"abstract":"<div><div>Diabetes is a growing global health issue, and effective diagnostic tools are needed to support early detection. This study proposes an enhanced deep learning framework, SE-ResNet50, which integrates a squeeze-and-excitation (SE) block into the conventional ResNet50 architecture to improve the classification of diabetic kidney pathology from glomerular images. The SE block adaptively recalibrates feature responses, enabling the model to emphasize diagnostically relevant structures better. The proposed framework was trained and validated on a kidney tissue dataset from Kanazawa Medical University, achieving superior performance with an accuracy of 97.02 %, precision of 0.96, and an AUC of 0.9856. SE-ResNet50 exhibited superior robustness and generalizability compared to established CNN architectures such as EfficientNet B0, Inception V3, and ConvNeXt. Further visualization via Grad-CAM revealed that the model effectively localizes critical regions within glomerular images. These results highlight the potential of SE-ResNet50 as a reliable and interpretable tool for advancing diabetes-related CKD diagnosis in clinical settings.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100385"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587547","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}

引用次数: 0

Effects of geometrical parameters on hemodynamics of arteriovenous graft: A 3D numerical simulation 几何参数对动静脉移植物血流动力学的影响：三维数值模拟

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-06-11 DOI: 10.1016/j.medntd.2025.100376

Maryam Assadi, Aisa Rassoli

{"title":"Effects of geometrical parameters on hemodynamics of arteriovenous graft: A 3D numerical simulation","authors":"Maryam Assadi, Aisa Rassoli","doi":"10.1016/j.medntd.2025.100376","DOIUrl":"10.1016/j.medntd.2025.100376","url":null,"abstract":"<div><div>Although arteriovenous grafts (AVGs) serve as a significant long-term hemodialysis access, they encounter issues such as stenosis, thrombosis, and potential graft failure. This study utilizes computational fluid dynamics to examine various combinations of geometric parameters in AVG design. Twelve looped AVG configurations are generated, including two representing commercially available AVGs. These models vary in length (60 mm and 150 mm), diameter (4 mm, 5 mm, and 6 mm), and venous anastomosis (VA) angles (30° and 60°). A time-dependent velocity waveform is applied at the artery inlet, with rigid walls and non-Newtonian blood modeling. AVG performance is assessed using velocity, streamlines, graft flow, and wall shear stress metrics, such as time-averaged wall shear stress, oscillatory shear index, and relative residence time. Comparative analysis identifies an AVG with a 60 mm length, 5 mm diameter, and 30° VA angle as a promising alternative to conventional graft configurations. This model demonstrates approximately 50 % less exposure to unfavorable hemodynamics, with a marginal decrease of around 9 % in maximum graft flow compared to commercial models. Shorter graft lengths, smaller diameters, and relatively smaller VA angles contribute to improved hemodynamic distribution. These findings offer insights applicable to clinical research on arteriovenous grafts and aid in developing effective therapeutic strategies.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100376"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280037","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}

引用次数: 0

Artificial intelligence and biosensors: Transforming cancer diagnostics 人工智能和生物传感器：改变癌症诊断

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-06-13 DOI: 10.1016/j.medntd.2025.100378

Maryam Althobiti , Trinh Thi Trang Nhung , Swati Verma , Raef R. Albugami , Rajender Kumar

{"title":"Artificial intelligence and biosensors: Transforming cancer diagnostics","authors":"Maryam Althobiti , Trinh Thi Trang Nhung , Swati Verma , Raef R. Albugami , Rajender Kumar","doi":"10.1016/j.medntd.2025.100378","DOIUrl":"10.1016/j.medntd.2025.100378","url":null,"abstract":"<div><div>Cancer is one of the leading causes of death worldwide. Early detection of cancer can play a decisive role in cancer treatment and improving survival rates. Conventional cancer detection methods, such as biopsy, imaging and blood tests are generally invasive and time-consuming, and their results have accuracy issues. Biosensors with artificial intelligence integration play a significant and evolving role in cancer diagnostics, offering non-invasive, rapid, and highly sensitive methods for early detection, monitoring, and treatment of cancer. Biosensors detect specific biomarkers associated with cancerous cells or tumours, such as nucleic acid (DNA, RNA), small molecules, peptides, proteins and metabolites. In recent years, many predictive artificial intelligence models and bioinformatics tools have been developed to integrate biosensors, emerging as powerful tools for cancer diagnostics. This review explores the role of biosensors in cancer detection, the development and application of predictive AI models and bioinformatics tools in cancer detection through biosensor technologies, and the challenges associated with their clinical adoption.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100378"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313049","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}

引用次数: 0

Advanced artificial intelligence driven framework for lung cancer diagnosis leveraging SqueezeNet with machine learning algorithms using transfer learning 先进的人工智能驱动的肺癌诊断框架，利用SqueezeNet和使用迁移学习的机器学习算法

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-07-05 DOI: 10.1016/j.medntd.2025.100383

Vineet Mehan

{"title":"Advanced artificial intelligence driven framework for lung cancer diagnosis leveraging SqueezeNet with machine learning algorithms using transfer learning","authors":"Vineet Mehan","doi":"10.1016/j.medntd.2025.100383","DOIUrl":"10.1016/j.medntd.2025.100383","url":null,"abstract":"<div><div>Lung cancer is a severe global public health problem, and early detection is important for improving patient wellbeing. This research presents an advanced Artificial Intelligence (AI) driven framework that integrates deep learning and machine learning techniques to enhance lung cancer classification in chest Computed Tomography (CT) scans. Leveraging transfer learning, SqueezeNet a lightweight Convolutional Neural Network (CNN) is employed for feature extraction, which is then processed by Machine Learning (ML) classifiers. A dataset comprising 950 chest scans from 110 test cases is used to classify tumors into benign, malignant, and normal categories. Among the tested models, SqueezeNet combined with Logistic Regression (LR) achieves the highest accuracy of 92.9 %. Performance evaluation is conducted using multiple classification metrics, including Confusion Matrix and Calibration plots, demonstrating the model's reliability in early lung cancer detection. The proposed AI-driven hybrid framework offers a promising approach to improving diagnostic accuracy, ultimately benefiting both patients and the healthcare system.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100383"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144587546","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}

引用次数: 0

Unveiling the role of post-translational modifications in bone metabolism: implications for osteoporosis 揭示翻译后修饰在骨代谢中的作用：对骨质疏松症的影响

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-08-06 DOI: 10.1016/j.medntd.2025.100391

Suleiman Kolawole Yusuf , Abubakar Danmaigoro , Onwuama Kenechukwu Tobechukwu , Samuel Odo Uko , Sadudeen Adetayo Amid , Okediran Babatunde Samuel , Alhaji Zubair Jaji

{"title":"Unveiling the role of post-translational modifications in bone metabolism: implications for osteoporosis","authors":"Suleiman Kolawole Yusuf , Abubakar Danmaigoro , Onwuama Kenechukwu Tobechukwu , Samuel Odo Uko , Sadudeen Adetayo Amid , Okediran Babatunde Samuel , Alhaji Zubair Jaji","doi":"10.1016/j.medntd.2025.100391","DOIUrl":"10.1016/j.medntd.2025.100391","url":null,"abstract":"<div><div>Bone metabolism is a highly dynamic process regulated by osteoblasts, osteoclasts, and osteocytes, ensuring skeletal integrity through continuous remodeling. Disruptions in this balance contribute to osteoporosis, a debilitating condition characterized by reduced bone mass and increased fracture risk. Emerging research highlights the pivotal role of post-translational modifications (PTMs) in regulating bone cell activity, influencing protein stability, function, and signaling pathways. Key PTMs, including phosphorylation, glycosylation, acetylation, ubiquitination, and SUMOylation, govern osteoblast differentiation, osteoclast activity, and extracellular matrix organization. Dysregulation of these modifications has been linked to osteoporosis pathogenesis, making them promising therapeutic targets. RUNX2, a master osteogenic transcription factor, is extensively regulated by PTMs, affecting its activity in skeletal development. Similarly, extracellular matrix proteins and osteocyte-derived factors, such as sclerostin and fibroblast growth factor 23, undergo PTMs that influence bone homeostasis. Advances in proteomics and molecular biology have facilitated the identification of PTM-mediated mechanisms, paving the way for targeted therapies, including kinase inhibitors, histone deacetylase modulators, and ubiquitination regulators. This review explores the mechanistic contributions of PTMs in bone metabolism, their dysregulation in osteoporosis, and potential therapeutic interventions, offering insights into novel strategies for bone health preservation and osteoporosis treatment.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100391"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878883","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}

引用次数: 0

Research progress and prospects of experimental murine behavior evaluation methods 实验小鼠行为评价方法的研究进展与展望

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-06-02 DOI: 10.1016/j.medntd.2025.100371

Chen Du , Ying Wang , Ziyi Li , Ziyan Wu , Dingyuan Liang , Yuliang Zhao , Jin Zhou , Yubo Fan

引用次数: 0

Corneal material nonlinearity and its effects on the comparative study of corneal biomechanics 角膜材料非线性及其对角膜生物力学比较研究的影响

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-06-21 DOI: 10.1016/j.medntd.2025.100380

Yingmei Fan , Yudi Han , Xuefei Li , Shenglong Luo , Xin Zhang , Lvfu He , Yuxuan Wang , Fangjun Bao , Ahmed Elsheikh , Junjie Wang

{"title":"Corneal material nonlinearity and its effects on the comparative study of corneal biomechanics","authors":"Yingmei Fan , Yudi Han , Xuefei Li , Shenglong Luo , Xin Zhang , Lvfu He , Yuxuan Wang , Fangjun Bao , Ahmed Elsheikh , Junjie Wang","doi":"10.1016/j.medntd.2025.100380","DOIUrl":"10.1016/j.medntd.2025.100380","url":null,"abstract":"<div><div>Corneal biomechanical evaluation has become a research hotspot with wide clinical relevance in fields such as keratoconus, corneal cross-linking, refractive surgery, and glaucoma. Despite advances in in-vivo corneal biomechanical imaging, ex-vivo experiments remain essential for comparing biomechanical effects of diseases and treatment protocols. However, due to the nonlinear behaviour of corneal material, comparisons of biomechanical metrics obtained under different loading conditions can be difficult and misleading. Furthermore, biomechanical estimations conducted under unrealistic loads that exceed normal living conditions may have limited clinical relevance. The current study aims to evaluate this issue by assessing the biomechanical properties of the cornea under physiologic and extreme conditions. Stress-strain data were obtained for porcine corneal specimens subjected to widely different strain rates (0.8 %, 25 %, 83 % and 420 %/min). In all cases, the behaviour closely matched a two-stage pattern consisting of an initial nonlinear low-stress region followed by a linear region under higher stresses. Tangent moduli (Et) were calculated at physiologic stress levels (0.01, 0.015, and 0.02 MPa) and extreme ones (0.15, 1.0, and 2.0 MPa). While comparisons at physiologic stress levels showed similar increasing trends in Et with faster strain rates, at high/non-physiologic stress levels, Et values remained relatively unchanged across strain rates from 25 % to 420 %/min. These findings underscore the importance of testing corneal behaviour under physiologic loading levels and signal cautions when interpreting results under high loads that do not represent normal tissue conditions.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100380"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144480391","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}

引用次数: 0

Engineering nanofibers for cutaneous drug delivery systems and therapeutic applications 用于皮肤药物输送系统和治疗应用的工程纳米纤维

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-07-08 DOI: 10.1016/j.medntd.2025.100386

Madhulika Pradhan , N. Saleem Basha , Kantrol Kumar Sahu , Krishna Yadav , Sucheta , Akhilesh Dubey , Hare Krishna Pradhan , John Kirubakaran

{"title":"Engineering nanofibers for cutaneous drug delivery systems and therapeutic applications","authors":"Madhulika Pradhan , N. Saleem Basha , Kantrol Kumar Sahu , Krishna Yadav , Sucheta , Akhilesh Dubey , Hare Krishna Pradhan , John Kirubakaran","doi":"10.1016/j.medntd.2025.100386","DOIUrl":"10.1016/j.medntd.2025.100386","url":null,"abstract":"<div><div>In the field of dermatological treatment and therapeutic innovation, nanofiber engineered through electrospinning technology have gained significant attention. These ultrafine structures replicate the natural framework of the extracellular environment, delivering exceptional breathability, malleability, and capacity to enhance cellular adhesion and tissue restoration. Scientists can precisely engineer these microscopic threads to administer pharmaceutical compounds with controlled released characteristics, rendering them particularly advantageous for addressing various skin conditions including lesions, eczematous inflammation, scaly erythematous plaques, follicular eruptions, and cutaneous malignancies. Incorporating antimicrobial elements, such as particulate zinc compounds and graphene-derived sheets can substantially improve their effectiveness in combating pathogenic invasion and accelerating dermal recovery. Furthermore, the electrospinning process facilitates the creation of multifunction-capable filaments with sophisticated attributes, including environment-sensitive drug release mechanisms that respond to skin surface acidity fluctuations, alongside diagnostic-therapeutic dual functionalities that permit continuous wound monitoring and assessment in clinical settings. Notwithstanding their remarkable promise, several hurdles persist in refining nanofiber architecture for bedside implementation, guaranteeing industrial-scale production capability, and executing thorough living organism investigations. This review examines cutting-edge developments in engineering nanofibers for cutaneous drug delivery systems and therapeutic applications and underscores their capacity to transform topical drug delivery systems, delivering personalized, effective, and precisely-directed treatment options.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100386"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144634399","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}

引用次数: 0

Cover 封面

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-09-09 DOI: 10.1016/S2590-0935(25)00053-0

引用次数: 0

A hierarchical framework for cervical cell classification using attention-based multi-scale local binary convolutional neural networks 基于注意力的多尺度局部二值卷积神经网络的宫颈细胞分类层次框架

Medicine in Novel Technology and Devices Pub Date : 2025-09-01 Epub Date: 2025-08-14 DOI: 10.1016/j.medntd.2025.100392

Tao Wan , Lei Cao , Yulan Jin , Dong Chen , Zengchang Qin

{"title":"A hierarchical framework for cervical cell classification using attention-based multi-scale local binary convolutional neural networks","authors":"Tao Wan , Lei Cao , Yulan Jin , Dong Chen , Zengchang Qin","doi":"10.1016/j.medntd.2025.100392","DOIUrl":"10.1016/j.medntd.2025.100392","url":null,"abstract":"<div><div>Traditional classification methods for cervical cells heavily rely on manual feature extraction, constraining their versatility due to the intricacies of cytology images. Although deep learning approaches offer remarkable potential, they often sacrifice domain-specific knowledge, particularly the morphological patterns characterizing various cell subtypes during automated feature extraction. To bridge this gap, we introduce a novel hierarchical framework that integrates robust features from color, texture, and morphology with latent representations discovered by an improved attention-based multi-scale local binary convolutional neural networks (MS-LBCNN), designed to facilitate powerful feature extraction mechanism. We enhance the standard 6-class Bethesda system (TBS) classification by incorporating a coarse-to-refine fusion strategy, which optimizes the classification process. The proposed method is uniquely equipped to manage the complexities present in both individual and clustered cell images. Upon rigorous evaluation across three independent data cohorts, our method consistently surpassed existing state-of-the-art techniques. The experimental results indicated the potential of our method in enhancing the development of automation-aided diagnostic systems, and bolstering both the accuracy and efficiency of cytology screening procedures.</div></div>","PeriodicalId":33783,"journal":{"name":"Medicine in Novel Technology and Devices","volume":"27 ","pages":"Article 100392"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904115","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}

引用次数: 0