Computer methods and programs in biomedicine update最新文献_第5页

Privacy-preserving brain tumor detection using FPGA-accelerated deep learning on Kria KV260 for smart healthcare 在Kria KV260上使用fpga加速深度学习进行智能医疗的隐私保护脑肿瘤检测

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100205

Kusum Lata , Prashant Singh , Sandeep Saini , Linga Reddy Cenkeramaddi

Technological advancements in high-performance electronics have fueled the development of cutting-edge medical applications, leading to exponential growth in effective treatment and diagnostic solutions for various medical problems. Incorporating deep learning-based systems with medical imaging technologies has revolutionized the field of disease detection. Ensuring the security and privacy of patient’s health records is crucial to developing sophisticated medical imaging diagnostic applications. This paper presents a privacy-focused, vision-based approach for effective brain tumor detection using deep learning algorithms such as ResNet-18, ResNet-50, and InceptionV3, deployed on the KV260 board, which is based on Xilinx® Kria™ K26 System on Module (SOM) platform, a Zynq® UltraScale+ MPSoC. We have integrated the AES-128 cryptographic algorithm with the Password-Based Key Derivation Function 2 (PBKDF2) hashing algorithm to maintain patients' privacy in MRI scans. This ensures the protection of patient data on the server and data movement to and from external servers. The designed system is evaluated for performance by examining its technical metric parameters- accuracy, precision, F1 score, and Recall. Security parameters such as entropy, energy, contrast, and correlation are used to evaluate the security strength of the proposed system. Microsoft operating systems compatible web application is also developed while integrating the above-proposed system on the KV 260 FPGA board. This application can be used remotely to upload the MRI scans and get the prediction results quickly and accurately. Performance assessment shows that ResNet18 outperforms testing-related metric parameters and execution time on the KV260 FPGA board while keeping patient data confidential, making it an ideal edge-device implementation for real-time clinical use.

高性能电子技术的进步推动了尖端医疗应用的发展，导致各种医疗问题的有效治疗和诊断解决方案呈指数级增长。将基于深度学习的系统与医学成像技术相结合，已经彻底改变了疾病检测领域。确保患者健康记录的安全性和隐私性对于开发复杂的医学成像诊断应用程序至关重要。本文介绍了一种以隐私为中心、基于视觉的有效脑肿瘤检测方法，该方法使用深度学习算法（如ResNet-18、ResNet-50和InceptionV3）部署在KV260板上，KV260板基于Xilinx®Kria™K26 System on Module （SOM）平台、Zynq®UltraScale+ MPSoC。我们将AES-128加密算法与基于密码的密钥派生函数2 （PBKDF2）散列算法集成在一起，以维护MRI扫描中患者的隐私。这确保了对服务器上的患者数据的保护以及与外部服务器之间的数据移动。通过检查其技术度量参数-准确性，精密度，F1分数和召回率来评估设计的系统的性能。安全参数如熵、能量、对比度和相关性被用来评估所提议系统的安全强度。将该系统集成在kv260 FPGA板上，开发了兼容微软操作系统的web应用程序。该应用程序可以远程上传MRI扫描，并快速准确地获得预测结果。性能评估表明，ResNet18在KV260 FPGA板上的性能优于测试相关指标参数和执行时间，同时保持患者数据的机密性，使其成为实时临床使用的理想边缘设备实现。

{"title":"Privacy-preserving brain tumor detection using FPGA-accelerated deep learning on Kria KV260 for smart healthcare","authors":"Kusum Lata , Prashant Singh , Sandeep Saini , Linga Reddy Cenkeramaddi","doi":"10.1016/j.cmpbup.2025.100205","DOIUrl":"10.1016/j.cmpbup.2025.100205","url":null,"abstract":"<div><div>Technological advancements in high-performance electronics have fueled the development of cutting-edge medical applications, leading to exponential growth in effective treatment and diagnostic solutions for various medical problems. Incorporating deep learning-based systems with medical imaging technologies has revolutionized the field of disease detection. Ensuring the security and privacy of patient’s health records is crucial to developing sophisticated medical imaging diagnostic applications. This paper presents a privacy-focused, vision-based approach for effective brain tumor detection using deep learning algorithms such as ResNet-18, ResNet-50, and InceptionV3, deployed on the KV260 board, which is based on Xilinx® Kria™ K26 System on Module (SOM) platform, a Zynq® UltraScale+ MPSoC. We have integrated the AES-128 cryptographic algorithm with the Password-Based Key Derivation Function 2 (PBKDF2) hashing algorithm to maintain patients' privacy in MRI scans. This ensures the protection of patient data on the server and data movement to and from external servers. The designed system is evaluated for performance by examining its technical metric parameters- accuracy, precision, F1 score, and Recall. Security parameters such as entropy, energy, contrast, and correlation are used to evaluate the security strength of the proposed system. Microsoft operating systems compatible web application is also developed while integrating the above-proposed system on the KV 260 FPGA board. This application can be used remotely to upload the MRI scans and get the prediction results quickly and accurately. Performance assessment shows that ResNet18 outperforms testing-related metric parameters and execution time on the KV260 FPGA board while keeping patient data confidential, making it an ideal edge-device implementation for real-time clinical use.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100205"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144685869","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

Dynamics and optimal control of fractional-order monkeypox epidemic model with social distancing habits and public awareness 具有社会距离习惯和公众意识的分数阶猴痘流行模型动力学及最优控制

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100187

Raqqasyi Rahmatullah Musafir, Agus Suryanto, Isnani Darti, Trisilowati

In this article, we propose a fractional-order monkeypox epidemic model incorporating social distancing habits and public awareness. The model includes the addition of a protected compartment and a saturated transmission rate. We implement a power rescaling for the parameters of the proposed model to ensure dimensional consistency. We have investigated the existence, uniqueness, nonnegativity, and boundedness of the solution. The model features monkeypox-free, human-endemic, and endemic equilibrium points, which depend on the order of derivative. The existence and stability of each equilibrium point have been analyzed locally and globally, depending on the basic reproduction number. Moreover, the basic reproduction number of the model also depends on the order of derivative. We carried out a case study using real data showing that the fractional-order model performs better than the first-order model in calibration and forecasting. Numerical simulations confirm the stability properties of each equilibrium point with respect to the specified parameter values. Numerical simulations also demonstrate that the social distancing habits can reduce monkeypox cases in the early stages, but do not significantly alter the basic reproduction number. Meanwhile, public awareness can substantially modify the basic reproduction number, shifting the endemic condition towards a disease-free state, although its impact on case reduction in the early period is not significant. We also implemented optimal control strategies for vector culling and vaccination in the proposed model. We have solved the optimal control problem, and the simulation results show that the combination of both controls yields the minimum cost with better effectiveness compared to the controls implemented separately.

在本文中，我们提出了一个包含社会距离习惯和公众意识的分数阶猴痘流行模型。该模型包括增加一个保护隔间和饱和传输速率。我们对所提出的模型的参数进行幂次缩放以确保维度的一致性。我们研究了解的存在性、唯一性、非负性和有界性。该模型具有无猴痘、人类地方病和地方病的平衡点，这些平衡点取决于导数的阶数。根据基本复制数，分析了各平衡点的局部和全局存在性和稳定性。此外，模型的基本再现数还取决于导数的阶数。用实际数据进行了实例研究，结果表明分数阶模型在校正和预测方面优于一阶模型。数值模拟证实了各平衡点相对于指定参数值的稳定性。数值模拟还表明，保持社交距离的习惯可以在早期减少猴痘病例，但不会显著改变基本繁殖数量。同时，公众意识可以大大改变基本繁殖数，将地方病状况转变为无病状态，尽管其对早期病例减少的影响并不显著。我们还在该模型中实现了媒介扑杀和疫苗接种的最优控制策略。我们解决了最优控制问题，仿真结果表明，与单独实现控制相比，两种控制组合产生的成本最小且效果更好。

{"title":"Dynamics and optimal control of fractional-order monkeypox epidemic model with social distancing habits and public awareness","authors":"Raqqasyi Rahmatullah Musafir, Agus Suryanto, Isnani Darti, Trisilowati","doi":"10.1016/j.cmpbup.2025.100187","DOIUrl":"10.1016/j.cmpbup.2025.100187","url":null,"abstract":"<div><div>In this article, we propose a fractional-order monkeypox epidemic model incorporating social distancing habits and public awareness. The model includes the addition of a protected compartment and a saturated transmission rate. We implement a power rescaling for the parameters of the proposed model to ensure dimensional consistency. We have investigated the existence, uniqueness, nonnegativity, and boundedness of the solution. The model features monkeypox-free, human-endemic, and endemic equilibrium points, which depend on the order of derivative. The existence and stability of each equilibrium point have been analyzed locally and globally, depending on the basic reproduction number. Moreover, the basic reproduction number of the model also depends on the order of derivative. We carried out a case study using real data showing that the fractional-order model performs better than the first-order model in calibration and forecasting. Numerical simulations confirm the stability properties of each equilibrium point with respect to the specified parameter values. Numerical simulations also demonstrate that the social distancing habits can reduce monkeypox cases in the early stages, but do not significantly alter the basic reproduction number. Meanwhile, public awareness can substantially modify the basic reproduction number, shifting the endemic condition towards a disease-free state, although its impact on case reduction in the early period is not significant. We also implemented optimal control strategies for vector culling and vaccination in the proposed model. We have solved the optimal control problem, and the simulation results show that the combination of both controls yields the minimum cost with better effectiveness compared to the controls implemented separately.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100187"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143609293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MORIX: Machine learning-aided framework for lethality detection and MORtality inference with eXplainable artificial intelligence in MAFLD subjects 机器学习辅助框架的致命性检测和死亡率推理与可解释的人工智能在MAFLD科目

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2024.100176

Domenico Lofù , Paolo Sorino , Tommaso Colafiglio , Caterina Bonfiglio , Rossella Donghia , Gianluigi Giannelli , Angela Lombardi , Tommaso Di Noia , Eugenio Di Sciascio , Fedelucio Narducci

Metabolic dysfunction-associated fatty liver disease (MAFLD) introduces new diagnostic criteria for fatty liver disease that are independent of alcohol consumption and viral hepatitis infection. Therefore, investigating how biochemical and anthropometric factors influence mortality in MAFLD subjects is of significant interest. In this work, we propose MORIX, an Artificial Intelligence-based framework capable of predicting fatal mortality outcomes in subjects with MAFLD. MORIX utilizes data from epidemiological datasets containing carefully selected anthropometric and biochemical information. This selection is achieved through Recursive Feature Elimination (RFE) using a Random Forest (RF) to train Machine Learning (ML) algorithms and provide a mortality risk (Yes/No) output. To provide physicians with a valuable tool, MORIX was trained and tested on a dataset of MAFLD subjects, comparing five different models: Random Forest (RF), eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Light Gradient Boosting Model (LGBM) in a 5-fold cross-validation training strategy. Experimental results identified the RF as the best model, achieving a high accuracy for both mortality risks predicted. Additionally, an eXplainable Artificial Intelligence (XAI) analysis was conducted to clarify the diagnostic logic of the RF model and to assess the impact of each feature to the prediction. Moreover, a web application was developed to predict mortality risk and provide explanations of how the input features influenced the final prediction. In conclusion, the MORIX framework is easy to apply, and the required parameters are readily available in healthcare datasets, making it a practical tool for medical professionals.

代谢功能障碍相关性脂肪肝（MAFLD）引入了新的脂肪肝诊断标准，与饮酒和病毒性肝炎感染无关。因此，研究生化和人体测量因素如何影响 MAFLD 受试者的死亡率具有重要意义。在这项工作中，我们提出了基于人工智能的 MORIX 框架，该框架能够预测 MAFLD 患者的致命死亡结果。MORIX 利用的数据来自流行病学数据集，其中包含精心挑选的人体测量和生化信息。这种选择是通过使用随机森林（RF）的递归特征消除（RFE）来实现的，以训练机器学习（ML）算法并提供死亡风险（是/否）输出。为了给医生提供有价值的工具，我们在 MAFLD 受试者的数据集上对 MORIX 进行了训练和测试，比较了五种不同的模型：随机森林 (RF)、极端梯度提升 (XGB)、支持向量机 (SVM)、多层感知器 (MLP) 和轻梯度提升模型 (LGBM) 采用 5 倍交叉验证训练策略。实验结果表明，RF 是最佳模型，在预测两种死亡风险方面都达到了很高的准确度。此外，还进行了可扩展人工智能（XAI）分析，以明确 RF 模型的诊断逻辑，并评估每个特征对预测的影响。此外，还开发了一个网络应用程序来预测死亡风险，并解释输入特征如何影响最终预测结果。总之，MORIX 框架易于应用，所需的参数在医疗数据集中随处可见，是医疗专业人员的实用工具。

{"title":"MORIX: Machine learning-aided framework for lethality detection and MORtality inference with eXplainable artificial intelligence in MAFLD subjects","authors":"Domenico Lofù , Paolo Sorino , Tommaso Colafiglio , Caterina Bonfiglio , Rossella Donghia , Gianluigi Giannelli , Angela Lombardi , Tommaso Di Noia , Eugenio Di Sciascio , Fedelucio Narducci","doi":"10.1016/j.cmpbup.2024.100176","DOIUrl":"10.1016/j.cmpbup.2024.100176","url":null,"abstract":"<div><div>Metabolic dysfunction-associated fatty liver disease (MAFLD) introduces new diagnostic criteria for fatty liver disease that are independent of alcohol consumption and viral hepatitis infection. Therefore, investigating how biochemical and anthropometric factors influence mortality in MAFLD subjects is of significant interest. In this work, we propose MORIX, an Artificial Intelligence-based framework capable of predicting fatal mortality outcomes in subjects with MAFLD. MORIX utilizes data from epidemiological datasets containing carefully selected anthropometric and biochemical information. This selection is achieved through Recursive Feature Elimination (RFE) using a Random Forest (RF) to train Machine Learning (ML) algorithms and provide a mortality risk (Yes/No) output. To provide physicians with a valuable tool, MORIX was trained and tested on a dataset of MAFLD subjects, comparing five different models: Random Forest (RF), eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Light Gradient Boosting Model (LGBM) in a 5-fold cross-validation training strategy. Experimental results identified the RF as the best model, achieving a high accuracy for both mortality risks predicted. Additionally, an eXplainable Artificial Intelligence (XAI) analysis was conducted to clarify the diagnostic logic of the RF model and to assess the impact of each feature to the prediction. Moreover, a web application was developed to predict mortality risk and provide explanations of how the input features influenced the final prediction. In conclusion, the MORIX framework is easy to apply, and the required parameters are readily available in healthcare datasets, making it a practical tool for medical professionals.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100176"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An analytical framework for smoking epidemic modeling using fuzzy logic and dual time-delay dynamics 基于模糊逻辑和双时滞动力学的吸烟流行建模分析框架

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100218

Muhammad Tashfeen , Hothefa Shaker Jassim , Muhammad Aziz ur Rehman , Fazal Dayan , Muhammad Adil Sadiq , Husam A. Neamah

The process of smoking is divided into several stages and has a clear tendency towards uncertainty and variability, which are not reflected in the traditional models with presumed parameters. To overcome this difficulty, a fuzzy mathematical model is derived to represent smoking dynamics more accurately under uncertainty. The PSRQE model presented and comprises Potential, Social, Regular, Transitional Non-smokers, and Ex-smokers, integrates vital considerations like the chance of developing smoking and the chance of quitting smoking. The model is analyzed by a stability analysis, numerical simulations, and sensitivity analysis of the basic reproduction number

R_{o}

. Three algorithms based on the Forward Euler scheme, the Fourth-Order Runge-Kutta (RK-4) treatment method, and the Non-Standard Finite Difference (NSFD) technique are used to obtain numerical solutions. The NSFD scheme is positive and bounded by convergence analysis, and simulation results have shown that it also preserves the structural properties of the model even when the step sizes are larger. Moreover, the influence of time deviations

τ_{1}

and

τ_{2}

on the smoking habits is also examined. It is demonstrated that this framework provides a valuable foundation for comprehending the leading patterns that govern smoking behavior that are required to reduce smoking rates and the related social, health, and economic impacts.

吸烟过程分为几个阶段，具有明显的不确定性和可变性趋势，这在具有假定参数的传统模型中没有反映出来。为了克服这一困难，导出了模糊数学模型，以更准确地表示不确定情况下的吸烟动力学。提出的PSRQE模型包括潜在吸烟者、社会吸烟者、常规吸烟者、过渡性非吸烟者和戒烟者，整合了诸如发展吸烟的机会和戒烟的机会等重要因素。对模型进行了稳定性分析、数值模拟和基本再现数Ro的敏感性分析。采用基于正演欧拉格式、四阶龙格-库塔（RK-4）处理方法和非标准有限差分（NSFD）技术的三种算法获得数值解。通过收敛分析，NSFD格式是正的且有界的，仿真结果表明，当步长较大时，该格式仍然保持了模型的结构特性。此外，还分析了时间偏差τ1和τ2对吸烟习惯的影响。研究表明，这一框架为理解控制吸烟行为的主要模式提供了宝贵的基础，这些模式是降低吸烟率和相关的社会、健康和经济影响所必需的。

{"title":"An analytical framework for smoking epidemic modeling using fuzzy logic and dual time-delay dynamics","authors":"Muhammad Tashfeen , Hothefa Shaker Jassim , Muhammad Aziz ur Rehman , Fazal Dayan , Muhammad Adil Sadiq , Husam A. Neamah","doi":"10.1016/j.cmpbup.2025.100218","DOIUrl":"10.1016/j.cmpbup.2025.100218","url":null,"abstract":"<div><div>The process of smoking is divided into several stages and has a clear tendency towards uncertainty and variability, which are not reflected in the traditional models with presumed parameters. To overcome this difficulty, a fuzzy mathematical model is derived to represent smoking dynamics more accurately under uncertainty. The PSRQE model presented and comprises Potential, Social, Regular, Transitional Non-smokers, and Ex-smokers, integrates vital considerations like the chance of developing smoking and the chance of quitting smoking. The model is analyzed by a stability analysis, numerical simulations, and sensitivity analysis of the basic reproduction number <span><math><msub><mi>R</mi><mi>o</mi></msub></math></span>. Three algorithms based on the Forward Euler scheme, the Fourth-Order Runge-Kutta (RK-4) treatment method, and the Non-Standard Finite Difference (NSFD) technique are used to obtain numerical solutions. The NSFD scheme is positive and bounded by convergence analysis, and simulation results have shown that it also preserves the structural properties of the model even when the step sizes are larger. Moreover, the influence of time deviations <span><math><mrow><msub><mi>τ</mi><mn>1</mn></msub><mspace></mspace></mrow></math></span>and <span><math><msub><mi>τ</mi><mn>2</mn></msub></math></span> on the smoking habits is also examined. It is demonstrated that this framework provides a valuable foundation for comprehending the leading patterns that govern smoking behavior that are required to reduce smoking rates and the related social, health, and economic impacts.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100218"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104731","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

A morphological approach for efficient macular center detection to support pre-diagnosis of diabetic retinopathy 一种有效的黄斑中心检测形态学方法支持糖尿病视网膜病变的预诊断

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100212

E. de-la-Cruz-Espinosa , Rita Q. Fuentes-Aguilar , E. Morales-Vargas

Diabetes is a disease with a worldwide presence and a high mortality rate, causing a significant social and economic impact. One of the more adverse effects of diabetes is visual loss due to diabetic retinopathy. Current methods to identify patients who need to be seen by a specialist to prevent vision impairment include screening and optical coherence tomography examinations; however, the number of devices and ophthalmologists is insufficient to cover the diabetic population. To address this, computational methods have been developed for rapid early-damage detection. This work presents an algorithm for ocular macula identification using simple image processing techniques for a low computational cost. The proposed algorithm achieved an Euclidean distance of 8.162

\pm

6.774 px (1.496

\pm

1.190% Relative error) in a processing time of 0.458

\pm

0.874 s across four databases, demonstrating competitive accuracy (100%) and speed on low-resource hardware.

糖尿病是一种世界性的疾病，死亡率高，造成重大的社会和经济影响。糖尿病的一个更不利的影响是由糖尿病视网膜病变引起的视力丧失。目前识别需要由专家检查以预防视力损害的患者的方法包括筛查和光学相干断层扫描检查；然而，设备和眼科医生的数量不足以覆盖糖尿病人群。为了解决这个问题，已经开发了用于快速早期损伤检测的计算方法。本文提出了一种使用简单图像处理技术的低计算成本眼黄斑识别算法。该算法在4个数据库的处理时间为0.458±0.874 s，欧氏距离为8.162±6.774 px（1.496±1.190%的相对误差），在低资源硬件上具有竞争力的精度（100%）和速度。

{"title":"A morphological approach for efficient macular center detection to support pre-diagnosis of diabetic retinopathy","authors":"E. de-la-Cruz-Espinosa , Rita Q. Fuentes-Aguilar , E. Morales-Vargas","doi":"10.1016/j.cmpbup.2025.100212","DOIUrl":"10.1016/j.cmpbup.2025.100212","url":null,"abstract":"<div><div>Diabetes is a disease with a worldwide presence and a high mortality rate, causing a significant social and economic impact. One of the more adverse effects of diabetes is visual loss due to diabetic retinopathy. Current methods to identify patients who need to be seen by a specialist to prevent vision impairment include screening and optical coherence tomography examinations; however, the number of devices and ophthalmologists is insufficient to cover the diabetic population. To address this, computational methods have been developed for rapid early-damage detection. This work presents an algorithm for ocular macula identification using simple image processing techniques for a low computational cost. The proposed algorithm achieved an Euclidean distance of 8.162 <span><math><mo>±</mo></math></span> 6.774 px (1.496 <span><math><mo>±</mo></math></span> 1.190% Relative error) in a processing time of 0.458 <span><math><mo>±</mo></math></span> 0.874 s across four databases, demonstrating competitive accuracy (100%) and speed on low-resource hardware.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100212"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144851776","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

Retraction notice to “Advancing Clinical Decision Support: The Role of Artificial Intelligence Across Six Domains” Computer Methods and Programs in Biomedicine Update, Volume 5, 2024 100142 《推进临床决策支持：人工智能在六个领域的作用》计算机方法和程序在生物医学更新，第5卷，2024 100142

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100204

Mohamed Khalifa , Mona Albadawy , Usman Iqbal

引用次数: 0

ECgMLP: A novel gated MLP model for enhanced endometrial cancer diagnosis ECgMLP：一种增强子宫内膜癌诊断的新型门控MLP模型

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100181

Md. Alif Sheakh , Sami Azam , Mst. Sazia Tahosin , Asif Karim , Sidratul Montaha , Kayes Uddin Fahim , Niusha Shafiabady , Mirjam Jonkman , Friso De Boer

Endometrial cancеr is the fourth fastеst-growing cancеr among women worldwide, affecting the uterus's lining. This research proposes a novel approach called ECgMLP for the automated diagnosis of endometrial cancer by analyzing histopathological images. Several preprocessing techniques are employed to increase the quality of the images, including normalization, Non-Local Means denoising, and alpha-beta enhancement. Effective segmentation is achieved through a combination of Otsu thresholding, morphological operations, distance transformations, and the watershed approach to identify major regions of interest. Through a sequence of blocks, the ECgMLP architecture processes input images to remove unimportant patterns. Model hyperparameters are improved via ablation research. The evaluations show a maximum accuracy of 99.26 % for identifying multi-class histopathological categories of endometrial tissue, which is higher than the previous best technique. The proposed model offers an automated, correct diagnosis, enhancing clinical processes. This proposition could be added to the current tools for finding endometrial cancer early, leading to better patient outcomes.

子宫内膜癌是全球妇女中生长速度第四快的癌症，主要影响子宫内膜。这项研究提出了一种名为 ECgMLP 的新方法，用于通过分析组织病理学图像自动诊断子宫内膜癌。该方法采用了多种预处理技术来提高图像质量，包括归一化、非局部均值去噪和α-β增强。通过结合大津阈值、形态学运算、距离变换和分水岭方法来识别主要感兴趣区，从而实现有效的分割。通过一系列块，ECgMLP 架构处理输入图像以去除不重要的模式。通过消融研究改进了模型超参数。评估结果显示，识别子宫内膜组织多类组织病理学类别的最高准确率为 99.26%，高于之前的最佳技术。所提出的模型可提供自动、正确的诊断，从而改善临床过程。这一建议可被添加到现有的早期发现子宫内膜癌的工具中，从而为患者带来更好的治疗效果。

{"title":"ECgMLP: A novel gated MLP model for enhanced endometrial cancer diagnosis","authors":"Md. Alif Sheakh , Sami Azam , Mst. Sazia Tahosin , Asif Karim , Sidratul Montaha , Kayes Uddin Fahim , Niusha Shafiabady , Mirjam Jonkman , Friso De Boer","doi":"10.1016/j.cmpbup.2025.100181","DOIUrl":"10.1016/j.cmpbup.2025.100181","url":null,"abstract":"<div><div>Endometrial cancеr is the fourth fastеst-growing cancеr among women worldwide, affecting the uterus's lining. This research proposes a novel approach called ECgMLP for the automated diagnosis of endometrial cancer by analyzing histopathological images. Several preprocessing techniques are employed to increase the quality of the images, including normalization, Non-Local Means denoising, and alpha-beta enhancement. Effective segmentation is achieved through a combination of Otsu thresholding, morphological operations, distance transformations, and the watershed approach to identify major regions of interest. Through a sequence of blocks, the ECgMLP architecture processes input images to remove unimportant patterns. Model hyperparameters are improved via ablation research. The evaluations show a maximum accuracy of 99.26 % for identifying multi-class histopathological categories of endometrial tissue, which is higher than the previous best technique. The proposed model offers an automated, correct diagnosis, enhancing clinical processes. This proposition could be added to the current tools for finding endometrial cancer early, leading to better patient outcomes.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100181"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Caputo fractional-order model with MCMC for rabies transmission dynamics 狂犬病传播动力学的MCMC Caputo分数阶模型

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100206

Jufren Zakayo Ndendya , Joshua A. Mwasunda , Stephen Edward , Nyimvua Shaban Mbare

Rabies continues to pose a severe public health threat, particularly in regions with high interactions between humans and infected dog populations. This study develops a fractional-order mathematical model using the Caputo derivative to capture the memory and hereditary effects in rabies transmission dynamics. The model incorporates key intervention strategies, including public health education, treatment, and culling of stray and infected dogs, to evaluate their effectiveness in controlling rabies outbreaks. The Markov Chain Monte Carlo (MCMC) method is utilized for parameter estimation, enhancing model precision and predictive accuracy. Stability analysis demonstrates that the disease-free equilibrium is locally asymptotically stable when effective reproduction number

R_{e} < 1

. Numerical simulations reveal that fractional-order model provides a more flexible and realistic representation of rabies spread compared to classical integer-order model. The results highlight the significant impact of public health education, treatment and targeted culling in reducing infection rates. The findings offer crucial insights for policymakers and public health officials in designing optimal intervention strategies to achieve sustainable rabies control.

狂犬病继续构成严重的公共卫生威胁，特别是在人与受感染犬群高度互动的地区。本研究开发了一个分数阶数学模型，利用卡普托导数来捕捉狂犬病传播动力学中的记忆和遗传效应。该模型纳入了主要的干预策略，包括公共卫生教育、治疗和扑杀流浪狗和感染狗，以评估其控制狂犬病爆发的有效性。采用马尔可夫链蒙特卡罗（MCMC）方法进行参数估计，提高了模型精度和预测精度。稳定性分析表明，当有效繁殖数为1时，无病平衡是局部渐近稳定的。数值模拟结果表明，与传统的整阶模型相比，分数阶模型能更灵活、更真实地描述狂犬病的传播。研究结果强调了公共卫生教育、治疗和有针对性的扑杀在降低感染率方面的重大影响。这些发现为决策者和公共卫生官员设计最佳干预策略以实现可持续的狂犬病控制提供了重要见解。

{"title":"A Caputo fractional-order model with MCMC for rabies transmission dynamics","authors":"Jufren Zakayo Ndendya , Joshua A. Mwasunda , Stephen Edward , Nyimvua Shaban Mbare","doi":"10.1016/j.cmpbup.2025.100206","DOIUrl":"10.1016/j.cmpbup.2025.100206","url":null,"abstract":"<div><div>Rabies continues to pose a severe public health threat, particularly in regions with high interactions between humans and infected dog populations. This study develops a fractional-order mathematical model using the Caputo derivative to capture the memory and hereditary effects in rabies transmission dynamics. The model incorporates key intervention strategies, including public health education, treatment, and culling of stray and infected dogs, to evaluate their effectiveness in controlling rabies outbreaks. The Markov Chain Monte Carlo (MCMC) method is utilized for parameter estimation, enhancing model precision and predictive accuracy. Stability analysis demonstrates that the disease-free equilibrium is locally asymptotically stable when effective reproduction number <span><math><mrow><msub><mrow><mi>R</mi></mrow><mrow><mi>e</mi></mrow></msub><mo><</mo><mn>1</mn></mrow></math></span>. Numerical simulations reveal that fractional-order model provides a more flexible and realistic representation of rabies spread compared to classical integer-order model. The results highlight the significant impact of public health education, treatment and targeted culling in reducing infection rates. The findings offer crucial insights for policymakers and public health officials in designing optimal intervention strategies to achieve sustainable rabies control.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100206"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694924","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

Smart product service systems for remote patient monitoring under uncertainty: A hierarchical framework from a healthcare provider perspective 不确定性下用于远程患者监测的智能产品服务系统：从医疗保健提供者的角度来看的分层框架

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2024.100174

Yeneneh Tamirat Negash , Faradilah Hanum , Liria Salome Calahorrano Sarmiento

Background

This study contributes to the integration of smart product service systems (smart PSSs) for remote patient monitoring (RPM). Integrating smart PSSs into RPM improves service delivery by enabling personalized care plans and shaping a patient-centered workflow for intelligent RPM. However, a gap exists in identifying intelligent RPM attributes and understanding their interrelationships. In addition, prior studies of RPM have yielded mixed results, with some studies demonstrating positive impacts and others showing no effect or even negative consequences on patient health. This inconsistency highlights the need for further investigation into how RPM systems are designed and utilized.

Objectives

First, the proposed intelligent RPM development criteria are validated through a qualitative assessment. Second, the interrelationships among intelligent RPM attributes are analyzed. Finally, the driving factors of intelligent RPM development are identified.

Methods

A hybrid methodology that combines the fuzzy Delphi method (FDM), the fuzzy decision-making trial and evaluation laboratory (FDEMATEL), and an analytical network process (ANP) is introduced to establish a hierarchical model of intelligent RPM attributes. Thirty healthcare industry experts specializing in chronic disease management participated in the study. Linguistic variables were utilized to manage the uncertainty inherent in expert opinions.

Results

The cause group encompassed operational efficiency, enhanced analytics, and sustainable service management, whereas the effect group comprised patient satisfaction and platform technology. The driving criteria included personalized treatment plans, real-time monitoring, mobile app development, and accessibility.

Conclusion

This study advances the understanding of how smart PSSs can be integrated into healthcare delivery. The developed hierarchical framework provides a roadmap for healthcare providers to implement and optimize intelligent RPM systems.

背景本研究有助于将智能产品服务系统（smart PSS）整合到远程患者监护（RPM）中。将智能产品服务系统集成到 RPM 中，可实现个性化护理计划，并为智能 RPM 塑造以患者为中心的工作流程，从而改善服务的提供。然而，在确定智能 RPM 属性和了解其相互关系方面还存在差距。此外，先前对 RPM 的研究结果不一，有些研究显示了积极影响，有些研究则显示对患者健康没有影响，甚至有负面影响。目标首先，通过定性评估验证所提出的智能 RPM 开发标准。其次，分析智能 RPM 属性之间的相互关系。方法采用模糊德尔菲法（FDM）、模糊决策试验和评估实验室（FDEMATEL）以及分析网络过程（ANP）相结合的混合方法，建立智能 RPM 属性的分层模型。30 位专门从事慢性病管理的医疗行业专家参与了研究。结果原因组包括运营效率、增强分析和可持续服务管理，而影响组包括患者满意度和平台技术。驱动标准包括个性化治疗方案、实时监控、移动应用开发和可及性。所开发的分层框架为医疗机构实施和优化智能 RPM 系统提供了路线图。

{"title":"Smart product service systems for remote patient monitoring under uncertainty: A hierarchical framework from a healthcare provider perspective","authors":"Yeneneh Tamirat Negash , Faradilah Hanum , Liria Salome Calahorrano Sarmiento","doi":"10.1016/j.cmpbup.2024.100174","DOIUrl":"10.1016/j.cmpbup.2024.100174","url":null,"abstract":"<div><h3>Background</h3><div>This study contributes to the integration of smart product service systems (smart PSSs) for remote patient monitoring (RPM). Integrating smart PSSs into RPM improves service delivery by enabling personalized care plans and shaping a patient-centered workflow for intelligent RPM. However, a gap exists in identifying intelligent RPM attributes and understanding their interrelationships. In addition, prior studies of RPM have yielded mixed results, with some studies demonstrating positive impacts and others showing no effect or even negative consequences on patient health. This inconsistency highlights the need for further investigation into how RPM systems are designed and utilized.</div></div><div><h3>Objectives</h3><div>First, the proposed intelligent RPM development criteria are validated through a qualitative assessment. Second, the interrelationships among intelligent RPM attributes are analyzed. Finally, the driving factors of intelligent RPM development are identified.</div></div><div><h3>Methods</h3><div>A hybrid methodology that combines the fuzzy Delphi method (FDM), the fuzzy decision-making trial and evaluation laboratory (FDEMATEL), and an analytical network process (ANP) is introduced to establish a hierarchical model of intelligent RPM attributes. Thirty healthcare industry experts specializing in chronic disease management participated in the study. Linguistic variables were utilized to manage the uncertainty inherent in expert opinions.</div></div><div><h3>Results</h3><div>The cause group encompassed operational efficiency, enhanced analytics, and sustainable service management, whereas the effect group comprised patient satisfaction and platform technology. The driving criteria included personalized treatment plans, real-time monitoring, mobile app development, and accessibility.</div></div><div><h3>Conclusion</h3><div>This study advances the understanding of how smart PSSs can be integrated into healthcare delivery. The developed hierarchical framework provides a roadmap for healthcare providers to implement and optimize intelligent RPM systems.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100174"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A review and systematic guide to counteracting medical data scarcity for AI applications 人工智能应用中应对医疗数据稀缺的综述和系统指南

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100220

Fabian Gröger , Ludovic Amruthalingam , Simone Lionetti , Alexander A. Navarini , Fabian Ille , Marc Pouly

Artificial intelligence has the potential to improve the scalability, objectivity, and precision of the overall healthcare system. Such improvements are possible due to the growth of medical databases and the progress of deep learning approaches, which enable automated analysis of both structured and unstructured data. While the overall size of medical datasets continues to increase, data scarcity remains problematic due to challenges in the medical domain, such as rare diseases, difficult and expensive annotation, and restricted population coverage. Machine learning models trained without appropriate measures to counteract this scarcity are often biased and unreliable in real-world settings. This paper will systematically examine the different challenges arising from medical data scarcity, their implications, and state-of-the-art mitigation approaches. It includes studies from the general machine learning community and describes how their findings translate to medical applications. This review is meant as a practical resource for researchers who want to develop reliable machine learning models for medical applications when data is scarce.

人工智能有潜力提高整个医疗保健系统的可扩展性、客观性和准确性。由于医疗数据库的增长和深度学习方法的进步，这种改进成为可能，深度学习方法可以自动分析结构化和非结构化数据。虽然医疗数据集的总体规模不断增加，但由于医疗领域的挑战，例如罕见疾病、困难和昂贵的注释以及人口覆盖范围有限，数据稀缺性仍然存在问题。没有适当措施来抵消这种稀缺性的机器学习模型在现实世界中往往是有偏见和不可靠的。本文将系统地研究医疗数据稀缺所带来的不同挑战，其影响以及最先进的缓解方法。它包括来自一般机器学习社区的研究，并描述了他们的发现如何转化为医学应用。这篇综述旨在为那些希望在数据稀缺的情况下为医疗应用开发可靠的机器学习模型的研究人员提供实用资源。

{"title":"A review and systematic guide to counteracting medical data scarcity for AI applications","authors":"Fabian Gröger , Ludovic Amruthalingam , Simone Lionetti , Alexander A. Navarini , Fabian Ille , Marc Pouly","doi":"10.1016/j.cmpbup.2025.100220","DOIUrl":"10.1016/j.cmpbup.2025.100220","url":null,"abstract":"<div><div>Artificial intelligence has the potential to improve the scalability, objectivity, and precision of the overall healthcare system. Such improvements are possible due to the growth of medical databases and the progress of deep learning approaches, which enable automated analysis of both structured and unstructured data. While the overall size of medical datasets continues to increase, data scarcity remains problematic due to challenges in the medical domain, such as rare diseases, difficult and expensive annotation, and restricted population coverage. Machine learning models trained without appropriate measures to counteract this scarcity are often biased and unreliable in real-world settings. This paper will systematically examine the different challenges arising from medical data scarcity, their implications, and state-of-the-art mitigation approaches. It includes studies from the general machine learning community and describes how their findings translate to medical applications. This review is meant as a practical resource for researchers who want to develop reliable machine learning models for medical applications when data is scarce.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100220"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145227202","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