For a long time, the sensitivity and criticality of data storage, processing, and transmission have hindered the wide utilization of IT and networks in the health care systems. Recently, the high availability, reachability, reliability, efficiency, usability and automation provided by the different cloud computing models paved the way to integrate the e-health systems with these cloud services to improve their efficiencies. However, security and privacy still constitute the main concern in the current models of cloud computing for cloud-based e-health care systems. The convergence and integration of different services with different capabilities and ownerships means high risks on security and privacy of the data, which are not negotiable in e-health care systems. There have been many proposals to solve some of these concerns specifically or among other protocols. In this paper we define differents cenarios for the integration of the e-health systems with the cloud computing systems. We also define the security and privacy requirements for these scenarios as well as the guidelines of the proposed solutions for the presented security and privacy problems.

Recently, cloud computing became an essential part of most IT strategies. However, security and privacy issues are still the two main concerns that limit the widespread use of cloud services since the data is stored in unknown locations and retrieval of data (or part of it) may involve disclosure of sensitive data to unauthorized parties. Many techniques have been proposed to handle this problem, which is known as Privacy-Preserving Data Retrieval (PPDR). These techniques attempt to minimize the sensitive data that needs to be revealed. However, revealing any data to an unauthorized party breaks the security and privacy concepts and also may decrease the efficiency of the data retrieval. In this paper, different requirements are defined to satisfy a high level of security and privacy in a PPDR system. Moreover, a technique that uses anonymous query authentication and multi-server settings is proposed. The technique provides an efficient ranking-based data retrieval by using weighted Term Frequency-Inverse Document Frequency (TF-IDF) vectors. It also satisfies all of the defined security requirements that were completely unsatisfied by the techniques reported in the literature.

Accurate image segmentation in medical and industrial domains remains challenging due to small object sizes, complex textures, and diverse defect morphologies. To address these limitations, we propose Dense121GAN, a conditional generative adversarial network (cGAN) that integrates a pre-trained DenseNet121 as a frozen encoder. The proposed architecture promotes effective feature reuse and stable information flow through residual skip connections. By leveraging transfer learning, Dense121GAN captures rich hierarchical representations and improves training stability, particularly in data-constrained settings. Extensive experiments were conducted using five-fold cross-validation across 16 heterogeneous datasets. Dense121GAN consistently outperformed UNet and ResNet-based generative adversarial networks (GANs) across multiple evaluation metrics, including Intersection over Union (IoU), Dice coefficient (Dice), Matthews Correlation Coefficient (MCC), Cohen’s Kappa, Structural Similarity Index Measure (SSIM), coefficient of determination ( R ² ), and Symmetric Mean Absolute Percentage Error (SMAPE). The model also demonstrated stable training behavior and mitigated common GAN failure modes such as mode collapse. In addition, Dense121GAN achieved faster convergence compared to the evaluated baseline architectures. These results highlight the effectiveness, robustness, and computational efficiency of Dense121GAN. The proposed framework provides a practical and versatile solution for both clinical diagnostic and industrial inspection applications.