Enhancing Brain Tumor Segmentation Accuracy through Scalable Federated Learning with Advanced Data Privacy and Security Measures

Mathematics, Год журнала: 2023, Номер 11(19), С. 4189 - 4189

Опубликована: Окт. 7, 2023

Brain tumor segmentation in medical imaging is a critical task for diagnosis and treatment while preserving patient data privacy security. Traditional centralized approaches often encounter obstacles sharing due to regulations security concerns, hindering the development of advanced AI-based applications. To overcome these challenges, this study proposes utilization federated learning. The proposed framework enables collaborative learning by training model on distributed from multiple institutions without raw data. Leveraging U-Net-based architecture, renowned its exceptional performance semantic tasks, emphasizes scalability approach large-scale deployment experimental results showcase remarkable effectiveness learning, significantly improving specificity 0.96 dice coefficient 0.89 with increase clients 50 100. Furthermore, outperforms existing convolutional neural network (CNN)- recurrent (RNN)-based methods, achieving higher accuracy, enhanced performance, increased efficiency. findings research contribute advancing field image upholding

Язык: Английский

---

Advancing Federated Learning Through Novel Mechanism for Privacy Preservation in Healthcare Applications

IEEE Access, Год журнала: 2023, Номер 11, С. 83562 - 83579

Опубликована: Янв. 1, 2023

The landscape of healthcare data collaboration heralds an era profound transformation, underscoring exceptional potential to elevate the quality patient care and expedite advancement medical research. formidable challenge, however, lies in safeguarding sensitive information's privacy security - a monumental task that creates significant obstacles. This paper presents innovative approach designed address these challenges through implementation privacy-preserving federated learning models, effectively pioneering novel path this intricate field Our proposed solution enables institutions collectively train machine models on decentralized data, concurrently preserving confidentiality individual data. During model aggregation phase, mechanism enforces protection by integrating cutting-edge methodologies, including secure multi-party computation differential privacy. To substantiate efficacy solution, we conduct array comprehensive simulations evaluations with concentrated focus accuracy, computational efficiency, preservation. results obtained corroborate our methodology surpasses competing approaches providing superior utility ensuring robust guarantees. encapsulates feasibility serving as compelling testament its practicality effectiveness. Through work, underscore harnessing collective intelligence while maintaining paramount protection, thereby affirming promise new horizon collaborative informatics.

Язык: Английский

---

Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds

PLoS ONE, Год журнала: 2024, Номер 19(3), С. e0296352 - e0296352

Опубликована: Март 12, 2024

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by overlapping symptoms (such fever, cough, sore throat, etc.). Additionally, researchers make use X-rays (CXR), cough sounds, computed tomography (CT) scans diagnose disorders. The present study aims classify nine different disorders, including LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for classifications extracting features from images. Furthermore, proposed CNN employed several new approaches max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), multiple-way data generation (MWDG). scalogram method is utilized transform sounds coughing into visual representation. Before beginning model has been developed, SMOTE approach used calibrate CXR CT well sound images (CSI) CXR, scan, CSI training evaluating come 24 publicly available benchmark illness datasets. classification performance compared with seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, Inception-V3, in addition state-of-the-art (SOTA) classifiers. effectiveness further demonstrated results ablation experiments. was successful achieving an accuracy 99.01%, making it superior both SOTA As result, capable offering significant support radiologists other professionals.

Язык: Английский

---

Federated learning with deep convolutional neural networks for the detection of multiple chest diseases using chest x-rays

Multimedia Tools and Applications, Год журнала: 2024, Номер 83(23), С. 63017 - 63045

Опубликована: Янв. 10, 2024

Язык: Английский

---

A Blockchain-Empowered Federated Learning-based Framework for Data Privacy in Lung Disease Detection System

Computers in Human Behavior, Год журнала: 2024, Номер 158, С. 108302 - 108302

Опубликована: Май 20, 2024

Язык: Английский

---

Blockchain, artificial intelligence, and healthcare: the tripod of future—a narrative review

Artificial Intelligence Review, Год журнала: 2024, Номер 57(9)

Опубликована: Авг. 8, 2024

Abstract The fusion of blockchain and artificial intelligence (AI) marks a paradigm shift in healthcare, addressing critical challenges securing electronic health records (EHRs), ensuring data privacy, facilitating secure transmission. This study provides comprehensive analysis the adoption AI within spotlighting their role fortifying security transparency leading trajectory for promising future realm healthcare. Our study, employing PRISMA model, scrutinized 402 relevant articles, narrative to explore review includes architecture blockchain, examines applications with without integration, elucidates interdependency between blockchain. major findings include: (i) it protects transfer, digital records, security; (ii) enhances EHR COVID-19 transmission, thereby bolstering healthcare efficiency reliability through precise assessment metrics; (iii) addresses like security, decentralized computing, forming robust tripod. revolutionize by EHRs, enhancing security. Private reflects sector’s commitment improved accessibility. convergence promises enhanced disease identification, response, overall efficacy, key sector challenges. Further exploration advanced features integrated enhance outcomes, shaping global delivery guaranteed innovation.

Язык: Английский

---

Blockchain and explainable-AI integrated system for Polycystic Ovary Syndrome (PCOS) detection

PeerJ Computer Science, Год журнала: 2025, Номер 11, С. e2702 - e2702

Опубликована: Фев. 28, 2025

In the modern era of digitalization, integration with blockchain and machine learning (ML) technologies is most important for improving applications in healthcare management secure prediction analysis health data. This research aims to develop a novel methodology securely storing patient medical data analyzing it PCOS prediction. The main goals are leverage Hyperledger Fabric immutable, private integrate Explainable Artificial Intelligence (XAI) techniques enhance transparency decision-making. innovation this study unique technology ML XAI, solving critical issues security model interpretability healthcare. With Caliper tool, blockchain’s performance evaluated enhanced. suggested AI-based system Polycystic Ovary Syndrome detection (EAIBS-PCOS) demonstrates outstanding records 98% accuracy, 100% precision, 98.04% recall, resultant F1-score 99.01%. Such quantitative measures ensure success proposed delivering dependable intelligible predictions diagnosis, therefore making great addition literature while serving as solid solution near future.

Язык: Английский

---

2D-CNN Architecture for Accurate Classification of COVID-19 Related Pneumonia on X-Ray Images

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(1)

Опубликована: Янв. 1, 2024

In the wake of COVID-19 pandemic, use medical imaging, particularly X-ray radiography, has become integral to rapid and accurate diagnosis pneumonia induced by virus. This research paper introduces a novel two-dimensional Convolutional Neural Network (2D-CNN) architecture specifically tailored for classification related in images. Leveraging advancements deep learning, our model is designed distinguish between viral pneumonia, typical COVID-19, other types as well healthy lung imagery. The proposed 2D-CNN characterized its depth unique layer arrangement, which optimizes feature extraction from images, thus enhancing model's diagnostic precision. We trained using substantial dataset comprising thousands annotated including those patients diagnosed with types, individuals no infection. enabled learn wide range radiographic features associated different conditions. Our demonstrated exceptional performance, achieving high accuracy, sensitivity, specificity preliminary tests. results indicate that not only outperforms existing models but also provides valuable tool healthcare professionals early detection differentiation pneumonia. capability crucial prompt appropriate treatment, potentially reducing pandemic's burden on systems. Furthermore, design allows easy integration into imaging workflows, offering practical efficient solution frontline facilities. contributes ongoing efforts combat procedures through application artificial intelligence imaging.

Язык: Английский

---

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

Computers, materials & continua/Computers, materials & continua (Print), Год журнала: 2024, Номер 79(2), С. 2169 - 2186

Опубликована: Янв. 1, 2024

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security, authentication, law enforcement, and surveillance.Deep learning (DL) models, notably convolutional neural networks (CNNs), have shown promising results the field of FR.However CNNs are easily fooled since they do not encode position orientation correlations between features.Hinton et al. envisioned Capsule Networks as a more robust design capable retaining pose information spatial to recognize objects like brain does.Lower-level capsules hold 8-dimensional vectors attributes position, hue, texture, so on, which routed higher-level via new routing by agreement algorithm.This provides capsule with viewpoint invariance, previously evaded CNNs.This research presents FR model based on that was tested using LFW dataset, COMSATS face own acquired photos cameras measuring 128 × pixels, 40 30 pixels.The trained outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy performing well unseen faces been blurred or rotated.Additionally, suggested outperformed recently released approaches high 92.47%.Based this previous results, perform better than deeper unobserved altered data because their special equivariance properties.

Язык: Английский

---

Trustworthy AI Guidelines in Biomedical Decision-Making Applications: A Scoping Review

Big Data and Cognitive Computing, Год журнала: 2024, Номер 8(7), С. 73 - 73

Опубликована: Июль 1, 2024

Recently proposed legal frameworks for Artificial Intelligence (AI) depart from some of concepts regarding ethical and trustworthy AI that provide the technical grounding safety risk. This is especially important in high-risk applications, such as those involved decision-making support systems biomedical domain. Frameworks span diverse requirements, including human agency oversight, robustness safety, privacy data governance, transparency, fairness, societal environmental impact. Researchers practitioners who aim to transition experimental models software market medical devices or use them actual practice face challenge deploying processes, best practices, controls are conducive complying with requirements. While checklists general guidelines have been aim, a gap exists between practices. paper reports first scoping review on topic specific domain attempts consolidate existing practices they appear academic literature subject.

Язык: Английский

---