Medical Engineering & Physics最新文献_第8页

BAEN-SKCNN: A novel framework for scoliosis early screening and severity diagnosis using unclothed back images BAEN-SKCNN：利用裸背图像进行脊柱侧凸早期筛查和严重程度诊断的新框架

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-12-01 Epub Date: 2025-09-07 DOI: 10.1016/j.medengphy.2025.104429

Jie Cao , Lingfeng Xie , Bingjin Wang , Chao Deng , Changhe Zhang , Zidong Yu

Scoliosis is a common spinal disease and it’s early screening is essential for planning treatment and avoiding deterioration. The traditional screening methods for scoliosis have the disadvantages of unnecessary radiation exposure, the dependence on equipment, and the high demand on operators. Although the advent of deep learning techniques provides a new perspective for rapid and convenient screening of scoliosis, the existing related research faces challenges caused by issues such as image background diversity, image size inconsistency, and class imbalance. In order to solve the about problems, a method based on BAEN-SKCNN is proposed for early screening and severity diagnosis of scoliosis using back images. Specifically, BAEN is constructed to extract the back region to improve the diagnostic accuracy and model universality. Spatial pyramid pooling and selective kernel network are used to construct SKCNN for early screening and severity diagnosis of scoliosis. On a self-made scoliosis dataset, the proposed method achieves 98 % accuracy for early screening and 73 % accuracy for severity diagnosis, respectively. Combined with the APP software developed, the proposed method can easily and quickly complete the diagnosis of scoliosis without the limitation of venues, equipment and personnel. It has a certain application prospect in the large-scale screening of scoliosis, and has certain clinical significance for improving the diagnostic rate of scoliosis.

脊柱侧凸是一种常见的脊柱疾病，早期筛查对于制定治疗计划和避免病情恶化至关重要。传统的脊柱侧凸筛查方法存在不必要的辐射暴露、对设备的依赖性、对操作人员的要求高等缺点。尽管深度学习技术的出现为快速便捷地筛查脊柱侧凸提供了新的视角，但现有的相关研究面临着图像背景多样性、图像尺寸不一致、班级不平衡等问题带来的挑战。为了解决这些问题，提出了一种基于BAEN-SKCNN的背部图像早期筛查和脊柱侧凸严重程度诊断方法。具体而言，构建BAEN提取背区，提高诊断准确性和模型通用性。利用空间金字塔池和选择性核网络构建SKCNN，用于脊柱侧凸的早期筛查和严重程度诊断。在自制的脊柱侧凸数据集上，该方法的早期筛查准确率为98%，严重程度诊断准确率为73%。结合所开发的APP软件，该方法可以不受场地、设备、人员的限制，方便快捷地完成脊柱侧凸的诊断。在脊柱侧凸的大规模筛查中具有一定的应用前景，对提高脊柱侧凸诊断率具有一定的临床意义。

{"title":"BAEN-SKCNN: A novel framework for scoliosis early screening and severity diagnosis using unclothed back images","authors":"Jie Cao , Lingfeng Xie , Bingjin Wang , Chao Deng , Changhe Zhang , Zidong Yu","doi":"10.1016/j.medengphy.2025.104429","DOIUrl":"10.1016/j.medengphy.2025.104429","url":null,"abstract":"<div><div>Scoliosis is a common spinal disease and it’s early screening is essential for planning treatment and avoiding deterioration. The traditional screening methods for scoliosis have the disadvantages of unnecessary radiation exposure, the dependence on equipment, and the high demand on operators. Although the advent of deep learning techniques provides a new perspective for rapid and convenient screening of scoliosis, the existing related research faces challenges caused by issues such as image background diversity, image size inconsistency, and class imbalance. In order to solve the about problems, a method based on BAEN-SKCNN is proposed for early screening and severity diagnosis of scoliosis using back images. Specifically, BAEN is constructed to extract the back region to improve the diagnostic accuracy and model universality. Spatial pyramid pooling and selective kernel network are used to construct SKCNN for early screening and severity diagnosis of scoliosis. On a self-made scoliosis dataset, the proposed method achieves 98 % accuracy for early screening and 73 % accuracy for severity diagnosis, respectively. Combined with the APP software developed, the proposed method can easily and quickly complete the diagnosis of scoliosis without the limitation of venues, equipment and personnel. It has a certain application prospect in the large-scale screening of scoliosis, and has certain clinical significance for improving the diagnostic rate of scoliosis.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"146 ","pages":"Article 104429"},"PeriodicalIF":2.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stiffness-observation-based force feedforward compensation control for interactive robot-assisted surgical bone milling 基于刚度观测的交互式机器人辅助外科骨铣削力前馈补偿控制

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-12-01 Epub Date: 2025-09-12 DOI: 10.1016/j.medengphy.2025.104431

Hao Ren , Zhichao Li , Zhaowei Liang , Wenqing Ren , Xiaodong Ma , Dan Wu

Robot-assisted surgery encounters critical force control challenges during risky operations like craniotomy skull milling, where collaborative operation demands adaptation to three surgical-specific complexities: multi-scale stiffness variations across biological tissues, abrupt stiffness discontinuities at critical boundaries (e.g. skull-dura interface), and unintuitive operator inputs during human-robot interaction. Consequently, controllers must dynamically adapt to this wide spectrum of tissue properties, a capability which exceeds the limits of conventional compliance control frameworks. This work presents a stiffness-observation-based force feedforward compensation controller that monitors the force-feedrate differential relationship to estimate real-time tissue stiffness, discriminating tissue types while compensating real-time force controllers. This controller is integrated into an active-constrained framework, replacing compliance control in the depth direction during milling operations. It establishes a hierarchical force control architecture where stiffness-derived information autonomously steers safety strategies, while surgeon-defined force constraints enable shared autonomy in human-robot interaction. The controller is numerically validated in simulated surgical environments and experimentally tested via in vivo craniotomies, demonstrating effective force tracking and safety assurance during complex milling tasks. By converting stiffness observations into real-time control actions, this approach enhances surgical safety in bone-tissue boundary transitions while maintaining intuitive human-robot collaboration.

在开颅颅骨铣削等高风险手术中，机器人辅助手术遇到了关键的力控制挑战，其中协作操作需要适应三种手术特定的复杂性：跨生物组织的多尺度刚度变化，关键边界（例如颅骨-硬脑膜界面）的突然刚度不连续，以及人机交互过程中不直观的操作员输入。因此，控制器必须动态适应这种广泛的组织特性，这种能力超出了常规合规控制框架的限制。这项工作提出了一种基于刚度观测的力前馈补偿控制器，该控制器通过监测力-进给差关系来估计实时组织刚度，在补偿实时力控制器的同时区分组织类型。该控制器集成到主动约束框架中，在铣削过程中取代深度方向的顺应性控制。它建立了一个层次力控制体系结构，其中刚度派生的信息自主地指导安全策略，而外科医生定义的力约束使人机交互中的共享自治成为可能。该控制器在模拟手术环境中进行了数值验证，并通过体内开颅手术进行了实验测试，证明了在复杂的铣削任务中有效的力跟踪和安全保证。通过将刚度观察转化为实时控制动作，该方法在保持直观的人机协作的同时，增强了骨组织边界转换的手术安全性。

{"title":"Stiffness-observation-based force feedforward compensation control for interactive robot-assisted surgical bone milling","authors":"Hao Ren , Zhichao Li , Zhaowei Liang , Wenqing Ren , Xiaodong Ma , Dan Wu","doi":"10.1016/j.medengphy.2025.104431","DOIUrl":"10.1016/j.medengphy.2025.104431","url":null,"abstract":"<div><div>Robot-assisted surgery encounters critical force control challenges during risky operations like craniotomy skull milling, where collaborative operation demands adaptation to three surgical-specific complexities: multi-scale stiffness variations across biological tissues, abrupt stiffness discontinuities at critical boundaries (e.g. skull-dura interface), and unintuitive operator inputs during human-robot interaction. Consequently, controllers must dynamically adapt to this wide spectrum of tissue properties, a capability which exceeds the limits of conventional compliance control frameworks. This work presents a stiffness-observation-based force feedforward compensation controller that monitors the force-feedrate differential relationship to estimate real-time tissue stiffness, discriminating tissue types while compensating real-time force controllers. This controller is integrated into an active-constrained framework, replacing compliance control in the depth direction during milling operations. It establishes a hierarchical force control architecture where stiffness-derived information autonomously steers safety strategies, while surgeon-defined force constraints enable shared autonomy in human-robot interaction. The controller is numerically validated in simulated surgical environments and experimentally tested via in vivo craniotomies, demonstrating effective force tracking and safety assurance during complex milling tasks. By converting stiffness observations into real-time control actions, this approach enhances surgical safety in bone-tissue boundary transitions while maintaining intuitive human-robot collaboration.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"146 ","pages":"Article 104431"},"PeriodicalIF":2.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099334","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-objective optimisation of vibration-assisted electrode insertion parameters for DBS using hybrid approach of grey-orthogonal coupled response surface methodology 基于灰色正交耦合响应面法的振动辅助电极插入参数多目标优化

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-12-01 Epub Date: 2025-09-07 DOI: 10.1016/j.medengphy.2025.104430

Kaiwen Zheng, Songsong Xu, Houru Gao, Tingting Gao, Yan Li

To minimize brain traumas during deep brain stimulation, multi-objective optimisation of vibration-assisted electrode insertion parameters are investigated using hybrid approach of grey-orthogonal coupled response surface methodology. Based on the LuGre model, mathematical models of friction force under vibration-assisted insertion are established. According to the orthogonal experimental results, the effects of each parameter of insertion performance for vibration-assisted insertion and optimal parameters of a single evaluation index are investigated through range analysis. The optimal parameters under the multi-evaluation indexes and mathematical models for the relationship between the parameters and the evaluation index are determined using grey relational analysis coupled response surface analysis. The results show that the vibration parameter combination optimized by response surface analysis results in excellent insertion performance with a puncture force of 9.656 mN and a friction growth rate of 2.191 mN/mm. The hybrid approach of grey-orthogonal coupled response surface methodology can act as a new methodology for optimizing vibration-assisted insertion parameters.

为了最大限度地减少深部脑刺激过程中的脑损伤，采用灰色正交耦合响应面法的混合方法研究了振动辅助电极插入参数的多目标优化。基于LuGre模型，建立了振动辅助插入摩擦力的数学模型。根据正交试验结果，通过极差分析探讨了振动辅助插入各参数对插入性能的影响，并确定了单个评价指标的最优参数。采用灰色关联分析耦合响应面分析法确定了多评价指标下的最优参数，并建立了参数与评价指标之间关系的数学模型。结果表明，通过响应面分析优化的振动参数组合具有良好的插入性能，穿刺力为9.656 mN，摩擦增长率为2.191 mN/mm。灰色正交耦合响应面法的混合方法可以作为振动辅助插入参数优化的一种新方法。

{"title":"Multi-objective optimisation of vibration-assisted electrode insertion parameters for DBS using hybrid approach of grey-orthogonal coupled response surface methodology","authors":"Kaiwen Zheng, Songsong Xu, Houru Gao, Tingting Gao, Yan Li","doi":"10.1016/j.medengphy.2025.104430","DOIUrl":"10.1016/j.medengphy.2025.104430","url":null,"abstract":"<div><div>To minimize brain traumas during deep brain stimulation, multi-objective optimisation of vibration-assisted electrode insertion parameters are investigated using hybrid approach of grey-orthogonal coupled response surface methodology. Based on the LuGre model, mathematical models of friction force under vibration-assisted insertion are established. According to the orthogonal experimental results, the effects of each parameter of insertion performance for vibration-assisted insertion and optimal parameters of a single evaluation index are investigated through range analysis. The optimal parameters under the multi-evaluation indexes and mathematical models for the relationship between the parameters and the evaluation index are determined using grey relational analysis coupled response surface analysis. The results show that the vibration parameter combination optimized by response surface analysis results in excellent insertion performance with a puncture force of 9.656 mN and a friction growth rate of 2.191 mN/mm. The hybrid approach of grey-orthogonal coupled response surface methodology can act as a new methodology for optimizing vibration-assisted insertion parameters.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"146 ","pages":"Article 104430"},"PeriodicalIF":2.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adverse events associated with single-use bronchoscopes: analysis from the MAUDE database 与一次性支气管镜相关的不良事件：来自MAUDE数据库的分析

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-12-01 Epub Date: 2025-09-23 DOI: 10.1016/j.medengphy.2025.104443

Xibin Su, Huitong Cheng, Wentao Rao, Chenghong Xue, Donghui Gan, Binjian Liu

Background

Bronchoscopy is an aerosol-generating procedure and associated with a high risk of viral transmission, particularly during the coronavirus disease (COVID-19) pandemic. This circumstance has expedited the adoption of single-use flexible bronchoscopes (SUFBs) due to their potential to mitigate healthcare personnel exposure to SARS-CoV-2 and reduce patient infection risks.

Objective

This study aims at analyzing reported adverse events and complications associated with SUFBs, while delineating recommendations for risk mitigation strategies and ensuring patient safety through an examination of data from the Manufacturer and User Facility Device Experience (MAUDE) database.

Methods

We conducted an evaluation of adverse events related to SUFBs as documented in the FDA MAUDE database from January 1, 2014, to June 30, 2025. All reports were manually reviewed and categorized based on the primary device problem and any associated patient outcomes.

Results

A total of 280 reports were issued regarding SUFBs. Manual review categorized these into 280 primary device-related problems and 286 patient-related outcomes. The primary category of device-related problems predominately pertained to breakage/fracture (85 cases; 30.4 %), and a loss of image/display (57 cases; 20.4 %). Among patient adverse events, the most frequently encountered were foreign bodies and airway obstruction.

Conclusion

Our study augments the existing clinical literature and body of knowledge by providing a comprehensive understanding of potential problems related to SUFBs. It underscores the imperative for continuous surveillance and vigilance to ensure the safety and effectiveness of SUFBs.

背景：支气管镜检查是一种产生气溶胶的过程，与病毒传播的高风险相关，特别是在冠状病毒病（COVID-19）大流行期间。这种情况加速了一次性柔性支气管镜（SUFBs）的采用，因为它们有可能减少医护人员接触SARS-CoV-2并降低患者感染风险。本研究旨在分析报道的与sufb相关的不良事件和并发症，同时通过检查制造商和用户设施设备体验（MAUDE）数据库的数据，描绘风险缓解策略的建议，并确保患者安全。方法我们对2014年1月1日至2025年6月30日FDA MAUDE数据库中记录的与sufb相关的不良事件进行了评估。所有的报告都是根据主要的器械问题和任何相关的患者结果进行人工审查和分类的。结果共发表了280份关于sufb的报告。人工审查将这些分类为280个与器械相关的主要问题和286个与患者相关的结果。器械相关问题的主要类别主要与断裂/骨折（85例，30.4%）和图像/显示丢失（57例，20.4%）有关。在患者不良事件中，最常见的是异物和气道阻塞。结论我们的研究增加了现有的临床文献和知识体系，提供了对与sufb相关的潜在问题的全面了解。它强调了持续监测和警惕的必要性，以确保sufb的安全性和有效性。

{"title":"Adverse events associated with single-use bronchoscopes: analysis from the MAUDE database","authors":"Xibin Su, Huitong Cheng, Wentao Rao, Chenghong Xue, Donghui Gan, Binjian Liu","doi":"10.1016/j.medengphy.2025.104443","DOIUrl":"10.1016/j.medengphy.2025.104443","url":null,"abstract":"<div><h3>Background</h3><div>Bronchoscopy is an aerosol-generating procedure and associated with a high risk of viral transmission, particularly during the coronavirus disease (COVID-19) pandemic. This circumstance has expedited the adoption of single-use flexible bronchoscopes (SUFBs) due to their potential to mitigate healthcare personnel exposure to SARS-CoV-2 and reduce patient infection risks.</div></div><div><h3>Objective</h3><div>This study aims at analyzing reported adverse events and complications associated with SUFBs, while delineating recommendations for risk mitigation strategies and ensuring patient safety through an examination of data from the Manufacturer and User Facility Device Experience (MAUDE) database.</div></div><div><h3>Methods</h3><div>We conducted an evaluation of adverse events related to SUFBs as documented in the FDA MAUDE database from January 1, 2014, to June 30, 2025. All reports were manually reviewed and categorized based on the primary device problem and any associated patient outcomes.</div></div><div><h3>Results</h3><div>A total of 280 reports were issued regarding SUFBs. Manual review categorized these into 280 primary device-related problems and 286 patient-related outcomes. The primary category of device-related problems predominately pertained to breakage/fracture (85 cases; 30.4 %), and a loss of image/display (57 cases; 20.4 %). Among patient adverse events, the most frequently encountered were foreign bodies and airway obstruction.</div></div><div><h3>Conclusion</h3><div>Our study augments the existing clinical literature and body of knowledge by providing a comprehensive understanding of potential problems related to SUFBs. It underscores the imperative for continuous surveillance and vigilance to ensure the safety and effectiveness of SUFBs.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"146 ","pages":"Article 104443"},"PeriodicalIF":2.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A knowledge graph-based post-stroke gait assessment system: A pilot study 基于知识图谱的卒中后步态评估系统：初步研究

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-09-30 DOI: 10.1016/j.medengphy.2025.104449

Yiran Jiao , Zengkun Liu , Stacey Reading , Marie-Claire Smith , Jianhua Lin , Yanxin Zhang

Instrumented gait analysis (IGA) has been widely used in research, but not typically in clinical practice, as it requires expertise in data analysis and interpretation. Post-stroke clinical gait assessment could be improved by integrating artificial intelligence into IGA, but previous gait assessment systems have relatively low clinical utility. This study aims to develop a clinically oriented automatic post-stroke gait assessment system based on knowledge graph (KG) to better support clinicians. A domain KG is first constructed in the field of gait analysis. This system can process IGA data to identify gait abnormalities and their potential causes based on kinematic analysis and KG. A preliminary evaluation with twenty post-stroke patients and four domain experts tested the system's performance in clinical settings, showing an average recall, precision, and F-score of 1, 0.78, and 0.89. Four clinical professionals showed high behavioural intention to use the system in clinical settings (4.33 ± 0.41 on a 5-point Likert scale based on the Technology Acceptance Model). The results depicted that this system has potential to be applied in clinical settings to provide useful supplementary insights for clinicians, which may promote the interpretation and clinical utility of IGA. The schema of this KG could be generalised or extended to gait analysis related to other diseases.

仪器步态分析（IGA）已广泛应用于研究，但通常不用于临床实践，因为它需要数据分析和解释方面的专业知识。将人工智能集成到IGA中可以改善脑卒中后临床步态评估，但以往的步态评估系统的临床实用性相对较低。本研究旨在开发一种基于知识图谱（KG）的面向临床的脑卒中后步态自动评估系统，以更好地支持临床医生。首先在步态分析领域建立了一个域KG。该系统可以处理IGA数据，基于运动学分析和KG识别步态异常及其潜在原因。对20名中风后患者和4名领域专家的初步评估测试了该系统在临床环境中的表现，显示平均召回率、准确率和f分数分别为1.78、0.89。4名临床专业人员表现出在临床环境中使用该系统的高行为意愿（基于技术接受模型的5点李克特量表为4.33±0.41）。结果表明，该系统有可能应用于临床环境，为临床医生提供有用的补充见解，这可能会促进对IGA的解释和临床应用。这种KG的模式可以推广或扩展到与其他疾病相关的步态分析。

{"title":"A knowledge graph-based post-stroke gait assessment system: A pilot study","authors":"Yiran Jiao , Zengkun Liu , Stacey Reading , Marie-Claire Smith , Jianhua Lin , Yanxin Zhang","doi":"10.1016/j.medengphy.2025.104449","DOIUrl":"10.1016/j.medengphy.2025.104449","url":null,"abstract":"<div><div>Instrumented gait analysis (IGA) has been widely used in research, but not typically in clinical practice, as it requires expertise in data analysis and interpretation. Post-stroke clinical gait assessment could be improved by integrating artificial intelligence into IGA, but previous gait assessment systems have relatively low clinical utility. This study aims to develop a clinically oriented automatic post-stroke gait assessment system based on knowledge graph (KG) to better support clinicians. A domain KG is first constructed in the field of gait analysis. This system can process IGA data to identify gait abnormalities and their potential causes based on kinematic analysis and KG. A preliminary evaluation with twenty post-stroke patients and four domain experts tested the system's performance in clinical settings, showing an average recall, precision, and F-score of 1, 0.78, and 0.89. Four clinical professionals showed high behavioural intention to use the system in clinical settings (4.33 ± 0.41 on a 5-point Likert scale based on the Technology Acceptance Model). The results depicted that this system has potential to be applied in clinical settings to provide useful supplementary insights for clinicians, which may promote the interpretation and clinical utility of IGA. The schema of this KG could be generalised or extended to gait analysis related to other diseases.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"145 ","pages":"Article 104449"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing nanoparticle design for selective targeting of breast cancer cells 优化纳米颗粒设计选择性靶向乳腺癌细胞

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-09-02 DOI: 10.1016/j.medengphy.2025.104420

Sarah Iaquinta , Shahram Khazaie , Sylvain Fréour , Frédéric Jacquemin

Recent efforts in cancer targeting have focused on nanoparticle (NP) drug delivery, yet the complexity of NP uptake makes experimental studies challenging. To streamline this, numerical models help identify key parameters. This study's model, focusing on elliptical NPs, aims to optimize NP aspect ratios for selective uptake by breast cancer cells. Mechanical properties of cells were taken from literature, and the model suggests that non-deformable NPs with aspect ratios between 1/3 and 1/2 are optimal for selective cancer cell internalization. These promising results require experimental validation.

最近的癌症靶向研究主要集中在纳米颗粒（NP）药物递送上，然而纳米颗粒摄取的复杂性使得实验研究具有挑战性。为了简化这一过程，数值模型帮助确定关键参数。本研究的模型，专注于椭圆NP，旨在优化NP的纵横比选择性摄取乳腺癌细胞。从文献中获取细胞的力学特性，该模型表明，长宽比在1/3和1/2之间的不可变形NPs最适合选择性癌细胞内化。这些有希望的结果需要实验验证。

引用次数: 0

Use of Ozonated water in the processing of human amniotic membrane and low pressure induced dehydration associated with thermal radiation 使用臭氧水处理人羊膜和低气压引起的与热辐射有关的脱水

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-08-12 DOI: 10.1016/j.medengphy.2025.104414

Aline Casarin dos Santos , Bianca Akemi Kawata , Luiz Fernando Ferreira de Oliveira , Pedro Augusto Laurindo Igreja Marrafa , Sílvia Móbille Awoyama , Adriana Barrinha Fernandes , Carlos José de Lima

The human amniotic membrane (HAM) is a biological material that is part of the placenta and contains compounds that enhance its applicability in the treatment of skin injuries, particularly concerning tissue regeneration. To utilize this membrane, it is essential to process it after collection, involving proper sterilization and storage. In this study, a dehydration technique for the amniotic membrane was developed using low pressure and incident thermal radiation. Histological analyses were performed after applying the sterilization protocol with ozonated water under hydrodynamic conditions, followed by submitting the samples to low pressure and light exposure. The results indicated that sterilization with ozonated water affected the integrity of the epithelium but did not induce significant changes in the morphology of the other components of the HAM. Additionally, exposure of this biomaterial to low pressure and thermal radiation was able to dehydrate it without altering the tissue integrity, which is extremely relevant considering its use in wound treatment. In this regard, the present study suggests that ozonation combined with exposure to low pressure and thermal radiation has the potential to be employed in the processing of HAM, thus favoring greater durability and ease of storage and transport of the biomaterial.

人羊膜（HAM）是一种生物材料，是胎盘的一部分，它含有的化合物增强了它在皮肤损伤治疗中的适用性，特别是在组织再生方面。为了利用这种膜，必须在收集后对其进行处理，包括适当的灭菌和储存。研究了一种利用低压和入射热辐射对羊膜进行脱水的技术。在水动力条件下用臭氧水消毒后进行组织学分析，然后将样品提交到低压和光照下。结果表明，臭氧水灭菌影响了上皮的完整性，但没有引起HAM其他成分形态学的显著变化。此外，将这种生物材料暴露在低压和热辐射下，能够在不改变组织完整性的情况下使其脱水，考虑到它在伤口治疗中的应用，这一点非常重要。在这方面，本研究表明，臭氧化结合暴露于低压和热辐射有可能用于火腿的加工，从而有利于生物材料的耐久性和易于储存和运输。

{"title":"Use of Ozonated water in the processing of human amniotic membrane and low pressure induced dehydration associated with thermal radiation","authors":"Aline Casarin dos Santos , Bianca Akemi Kawata , Luiz Fernando Ferreira de Oliveira , Pedro Augusto Laurindo Igreja Marrafa , Sílvia Móbille Awoyama , Adriana Barrinha Fernandes , Carlos José de Lima","doi":"10.1016/j.medengphy.2025.104414","DOIUrl":"10.1016/j.medengphy.2025.104414","url":null,"abstract":"<div><div>The human amniotic membrane (HAM) is a biological material that is part of the placenta and contains compounds that enhance its applicability in the treatment of skin injuries, particularly concerning tissue regeneration. To utilize this membrane, it is essential to process it after collection, involving proper sterilization and storage. In this study, a dehydration technique for the amniotic membrane was developed using low pressure and incident thermal radiation. Histological analyses were performed after applying the sterilization protocol with ozonated water under hydrodynamic conditions, followed by submitting the samples to low pressure and light exposure. The results indicated that sterilization with ozonated water affected the integrity of the epithelium but did not induce significant changes in the morphology of the other components of the HAM. Additionally, exposure of this biomaterial to low pressure and thermal radiation was able to dehydrate it without altering the tissue integrity, which is extremely relevant considering its use in wound treatment. In this regard, the present study suggests that ozonation combined with exposure to low pressure and thermal radiation has the potential to be employed in the processing of HAM, thus favoring greater durability and ease of storage and transport of the biomaterial.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"145 ","pages":"Article 104414"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reducing leads, enhancing wearable practicality: A comparative study of 3-lead vs. 12-lead ECG classification 减少导联，增强可穿戴实用性：3导联与12导联心电图分类的比较研究

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-08-27 DOI: 10.1016/j.medengphy.2025.104419

Sergio González-Cabeza , Mario Sanz-Guerrero , Luis Piñuel , Mauro Luis Buelga Suárez , Gonzalo Luis Alonso Salinas , Marian Diaz-Vicente , Joaquín Recas

Inspired by recent advances in clinical research and the growing adoption of wearable ECG devices, this study explores the feasibility of using reduced-lead ECGs for automated detection of heart anomalies using deep learning, providing a more accessible and cost-effective alternative to traditional 12-lead ECGs. This research adapts and evaluates a state-of-the-art 12-lead deep learning model (from Ribeiro et al. [1]) for 3-lead configurations. The 12-lead ECG model architecture was trained from scratch on the public database PTB-XL. It was then modified to use 3 leads by only changing the input layer. Despite a 75% reduction in input data, the 3-lead model showed only a subtle 3% performance drop. To address this gap, the 3-lead model was further optimized using a novel strategy that combines transfer learning and a One-vs-All classification approach. Using PTB-XL's five-class setup (normal vs. four pathologies: myocardial infarction, ST/T change, conduction disturbance, and hypertrophy), we report the micro-averaged F1-score across all test samples. The new optimized 3-lead model achieves a global (micro-averaged) F1-score of 77% (vs. 78% for the 12-lead model). These findings highlight the potential of simplified and cost-effective reduced-lead classification models to deliver near-equivalent diagnostic accuracy. This advancement could democratize access to early cardiac diagnostics, particularly in resource-limited settings.

受近期临床研究进展和可穿戴心电图设备日益普及的启发，本研究探索了使用减少导联心电图进行深度学习自动检测心脏异常的可行性，为传统的12导联心电图提供了一种更容易获得且更具成本效益的替代方案。本研究采用并评估了最先进的12导联深度学习模型（来自Ribeiro等人的[1]），用于3导联配置。12导联心电图模型架构在公共数据库PTB-XL上从零开始训练。然后修改为仅通过改变输入层使用3引线。尽管输入数据减少了75%，但3导联模型的性能仅下降了3%。为了解决这一差距，使用一种结合迁移学习和一对一分类方法的新策略进一步优化了3-lead模型。使用PTB-XL的五类设置（正常与四种病理：心肌梗死，ST/T改变，传导障碍和肥大），我们报告所有测试样本的微平均f1评分。新优化的3导联模型实现了77%的全局（微平均）f1得分（12导联模型为78%）。这些发现强调了简化的、具有成本效益的低铅分类模型的潜力，以提供接近同等的诊断准确性。这一进步可以使早期心脏诊断大众化，特别是在资源有限的情况下。

{"title":"Reducing leads, enhancing wearable practicality: A comparative study of 3-lead vs. 12-lead ECG classification","authors":"Sergio González-Cabeza , Mario Sanz-Guerrero , Luis Piñuel , Mauro Luis Buelga Suárez , Gonzalo Luis Alonso Salinas , Marian Diaz-Vicente , Joaquín Recas","doi":"10.1016/j.medengphy.2025.104419","DOIUrl":"10.1016/j.medengphy.2025.104419","url":null,"abstract":"<div><div>Inspired by recent advances in clinical research and the growing adoption of wearable ECG devices, this study explores the feasibility of using reduced-lead ECGs for automated detection of heart anomalies using deep learning, providing a more accessible and cost-effective alternative to traditional 12-lead ECGs. This research adapts and evaluates a state-of-the-art 12-lead deep learning model (from Ribeiro et al. <span><span>[1]</span></span>) for 3-lead configurations. The 12-lead ECG model architecture was trained from scratch on the public database PTB-XL. It was then modified to use 3 leads by only changing the input layer. Despite a 75% reduction in input data, the 3-lead model showed only a subtle 3% performance drop. To address this gap, the 3-lead model was further optimized using a novel strategy that combines transfer learning and a One-vs-All classification approach. Using PTB-XL's five-class setup (normal vs. four pathologies: myocardial infarction, ST/T change, conduction disturbance, and hypertrophy), we report the micro-averaged F1-score across all test samples. The new optimized 3-lead model achieves a global (micro-averaged) F1-score of 77% (vs. 78% for the 12-lead model). These findings highlight the potential of simplified and cost-effective reduced-lead classification models to deliver near-equivalent diagnostic accuracy. This advancement could democratize access to early cardiac diagnostics, particularly in resource-limited settings.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"145 ","pages":"Article 104419"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144913386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Graph-enhanced deep learning for ECG arrhythmia detection: An integration of CNN-GNN-BiLSTM approach 图增强深度学习用于心电心律失常检测：CNN-GNN-BiLSTM方法的集成

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-08-22 DOI: 10.1016/j.medengphy.2025.104418

Piyush Mahajan, Amit Kaul

Early and accurate detection of cardiac arrhythmias is crucial for preventing severe cardiovascular events. This study proposes a CNN–GNN–BiLSTM integrated framework for automated ECG arrhythmia classification, combining spatial, relational, and temporal learning to achieve enhanced predictive accuracy. Convolutional Neural Networks (CNNs) serve as feature extractors from ECG spectrograms, while Graph Attention Networks (GATs) capture inter-beat relationships through graph-based modeling. In parallel, Bidirectional Long Short-Term Memory (BiLSTM) networks refine temporal dependencies, ensuring robust sequential representation. Outputs from GAT and BiLSTM modules are concatenated to form a unified feature representation, which is passed through a fully connected classifier for final prediction. The model is evaluated on three benchmark ECG datasets—MIT-BIH, PTB, and Chapman-Shaoxing—as well as a combined 11-class dataset, demonstrating superior generalization. Results indicate significant performance improvement over conventional deep learning approaches, achieving 96.0% overall accuracy and up to 99.89% accuracy on MIT-BIH. The proposed framework effectively mitigates misclassification errors and offers a scalable, real-time solution for AI-driven cardiac monitoring systems.

早期准确发现心律失常对预防严重心血管事件至关重要。本研究提出了一个CNN-GNN-BiLSTM集成框架用于自动心电心律失常分类，结合空间、关系和时间学习来提高预测准确性。卷积神经网络（cnn）作为心电频谱的特征提取器，而图注意网络（GATs）通过基于图的建模来捕获心跳间的关系。同时，双向长短期记忆（BiLSTM）网络改进了时间依赖性，确保了稳健的序列表示。GAT和BiLSTM模块的输出被连接起来，形成一个统一的特征表示，并通过一个全连接的分类器进行最终预测。该模型在三个基准心电数据集（mit - bih， PTB和chapman - shaoxi）以及11类数据集上进行了评估，显示出优越的泛化能力。结果表明，与传统的深度学习方法相比，性能有了显著的提高，在MIT-BIH上达到了96.0%的总体准确率和99.89%的准确率。提出的框架有效地减轻了误分类错误，并为人工智能驱动的心脏监测系统提供了可扩展的实时解决方案。

{"title":"Graph-enhanced deep learning for ECG arrhythmia detection: An integration of CNN-GNN-BiLSTM approach","authors":"Piyush Mahajan, Amit Kaul","doi":"10.1016/j.medengphy.2025.104418","DOIUrl":"10.1016/j.medengphy.2025.104418","url":null,"abstract":"<div><div>Early and accurate detection of cardiac arrhythmias is crucial for preventing severe cardiovascular events. This study proposes a CNN–GNN–BiLSTM integrated framework for automated ECG arrhythmia classification, combining spatial, relational, and temporal learning to achieve enhanced predictive accuracy. Convolutional Neural Networks (CNNs) serve as feature extractors from ECG spectrograms, while Graph Attention Networks (GATs) capture inter-beat relationships through graph-based modeling. In parallel, Bidirectional Long Short-Term Memory (BiLSTM) networks refine temporal dependencies, ensuring robust sequential representation. Outputs from GAT and BiLSTM modules are concatenated to form a unified feature representation, which is passed through a fully connected classifier for final prediction. The model is evaluated on three benchmark ECG datasets—MIT-BIH, PTB, and Chapman-Shaoxing—as well as a combined 11-class dataset, demonstrating superior generalization. Results indicate significant performance improvement over conventional deep learning approaches, achieving 96.0% overall accuracy and up to 99.89% accuracy on MIT-BIH. The proposed framework effectively mitigates misclassification errors and offers a scalable, real-time solution for AI-driven cardiac monitoring systems.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"145 ","pages":"Article 104418"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144896120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EMI caused artifact removal in LED-based photoacoustic tomography system for image quality enhancement 在基于led的光声断层成像系统中，电磁干扰引起的伪影去除可提高图像质量

IF 2.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Medical Engineering & Physics

Pub Date : 2025-11-01 Epub Date: 2025-10-01 DOI: 10.1016/j.medengphy.2025.104450

Xinyu Lu , Enxiang Shen , Jie Yuan , Xiao Yin , Zhendong Yao

The Light Emitting Diode (LED) based photoacoustic computed tomography (PACT) system offers advantages such as safety, low cost, portability, and wavelength adjustability. In order to obtain high-quality photoacoustic signals, LEDs are driven by periodic nanosecond pulses. This results in a significant variation in the current flowing through the LEDs during the turn-on and turn-off moments, generating strong electromagnetic interference (EMI) around the LED circuit. In LED-based PACT systems, the light source is typically placed near the ultrasound transducer. Under the influence of the EMI emitted from the LEDs, the coil in the ultrasound transducer picks up induced currents, causing the transducer to emit ultrasonic signals. The ultrasonic echoes are received by the transducer, mixing with the photoacoustic signals and resulting in image artifacts. In this study, we propose an optimized design for the LED-based PACT system that suppresses EMI, thereby reducing image artifacts. We designed several circuit modules to reduce EMI and incorporated external electromagnetic wave absorption techniques, then conducted EMI measurements and imaging comparison experiments to demonstrate the effectiveness of this design. The proposed approach is expected to advance the application of LED-based PACT systems in fields such as surface vascular imaging and photoacoustic endoscopy.

基于发光二极管（LED）的光声计算机断层扫描（PACT）系统具有安全、低成本、便携性和波长可调等优点。为了获得高质量的光声信号，led采用周期纳秒脉冲驱动。这导致在打开和关闭时刻流过LED的电流发生显著变化，在LED电路周围产生强烈的电磁干扰（EMI）。在基于led的PACT系统中，光源通常放置在超声波换能器附近。在led发出的电磁干扰的影响下，超声波换能器中的线圈接收感应电流，使换能器发出超声波信号。超声波回波被换能器接收，与光声信号混合，产生图像伪影。在这项研究中，我们提出了一种基于led的PACT系统的优化设计，该系统可以抑制EMI，从而减少图像伪影。我们设计了几个电路模块来减少电磁干扰，并结合了外部电磁波吸收技术，然后进行了电磁干扰测量和成像比较实验来证明该设计的有效性。该方法有望推进基于led的PACT系统在表面血管成像和光声内窥镜等领域的应用。

{"title":"EMI caused artifact removal in LED-based photoacoustic tomography system for image quality enhancement","authors":"Xinyu Lu , Enxiang Shen , Jie Yuan , Xiao Yin , Zhendong Yao","doi":"10.1016/j.medengphy.2025.104450","DOIUrl":"10.1016/j.medengphy.2025.104450","url":null,"abstract":"<div><div>The Light Emitting Diode (LED) based photoacoustic computed tomography (PACT) system offers advantages such as safety, low cost, portability, and wavelength adjustability. In order to obtain high-quality photoacoustic signals, LEDs are driven by periodic nanosecond pulses. This results in a significant variation in the current flowing through the LEDs during the turn-on and turn-off moments, generating strong electromagnetic interference (EMI) around the LED circuit. In LED-based PACT systems, the light source is typically placed near the ultrasound transducer. Under the influence of the EMI emitted from the LEDs, the coil in the ultrasound transducer picks up induced currents, causing the transducer to emit ultrasonic signals. The ultrasonic echoes are received by the transducer, mixing with the photoacoustic signals and resulting in image artifacts. In this study, we propose an optimized design for the LED-based PACT system that suppresses EMI, thereby reducing image artifacts. We designed several circuit modules to reduce EMI and incorporated external electromagnetic wave absorption techniques, then conducted EMI measurements and imaging comparison experiments to demonstrate the effectiveness of this design. The proposed approach is expected to advance the application of LED-based PACT systems in fields such as surface vascular imaging and photoacoustic endoscopy.</div></div>","PeriodicalId":49836,"journal":{"name":"Medical Engineering & Physics","volume":"145 ","pages":"Article 104450"},"PeriodicalIF":2.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0