Breast cancer is the second leading cause of cancer-related mortality among women. Early detection enables timely treatment, improving survival outcomes. This paper presents a comparative evaluation of federated learning (FL) frameworks for multiclass breast cancer classification using ultrasound images drawn from three datasets: BUSI, BUS-UCLM, and BCMID, which include 600, 38, and 323 patients, respectively. Five state-of-the-art networks were tested, with MobileNet, ResNet and InceptionNet identified as the most effective for FL deployment. Two aggregation strategies, FedAvg and FedProx, were assessed under varying levels of data heterogeneity in two and three client settings. Results from experiments indicate that the FL models outperformed local and centralized training, bypassing the adverse impacts of data isolation and domain shift. In the two-client federations, FL achieving up to 8% higher accuracy and almost 6% higher macro-F1 scores on average that local and centralized training. FedProx on MobileNet maintained a stable performance in the three-client federation with best average accuracy of 73.31%, and macro-F1 of 67.3% despite stronger heterogeneity. Consequently, these results suggest that the proposed multiclass model has the potential to support clinical workflows by assisting in automated risk stratification. If deployed, such a system could allow radiologists to prioritize high-risk patients more effectively. The findings emphasize the potential of federated learning as a scalable, privacy-preserving infrastructure for collaborative medical imaging and breast cancer diagnosis.

Recently, computer vision is playing an important role in many essential human-computer interactive applications, these applications are subject to a “real-time” constraint, and therefore it requires a fast and reliable computational system. Edge Detection is the most used approach for segmenting images based on changes in intensity. There are various kernels used to perform edge detection, such as: Sobel, Robert, and Prewitt, upon which, the most commonly used is Sobel. In this research a novel type of operator cells that perform addition is introduced to achieve computational acceleration. The novel operator cells have been employed in the chosen FPGA Zedboard which is well-suited for real-time image and video processing. Accelerating the Sobel edge detection technique is exploited using different tools such as the High-Level Synthesis tools provided by Vivado. This enhancement shows a significant improvement as it decreases the computational time by 26% compared to the conventional adder cells.

Change detection (CD) in optical remote-sensing images is a critical task for applications such as urban planning, disaster monitoring, and environmental assessment. While UNet-based architecture has demonstrated strong performance in CD tasks, it often struggles with capturing deep hierarchical features due to the limitations of plain convolutional layers. Conversely, ResNet architectures excel at learning deep features through residual connections but may lack precise localization capabilities. To address these challenges, we propose ResUNet++, a novel hybrid architecture that combines the strengths of ResNet and UNet for accurate and robust change detection. ResUNet++ integrates residual blocks into the UNet framework to enhance feature representation and mitigate gradient vanishing problems. Additionally, we introduce a Multi-Scale Feature Fusion (MSFF) module to aggregate features at different scales, improving the detection of both large and small changes. Experimental results on multiple datasets (EGY-CD, S2Looking, and LEVIR-CD) demonstrate that ResUNet++ outperforms state-of-the-art methods, achieving higher precision, recall, and F1-scores while maintaining computational efficiency.

Target detection in remote sensing imaging is impeded by difficulties in obtaining semantic information from diminutive objects and differentiating amongst like targets. This frequently results in inadequate performance from current detection techniques. This study presents IMPROVED-YOLO, an enhanced algorithm based on YOLOv9, specifically tailored for remote sensing imagery. IMPROVED-YOLO integrates a space-to-depth convolution module (SPD-Conv) to augment feature preservation, an attention mechanism in the backbone's final pooling layer for accurate target localization, a bidirectional feature pyramid network (Bi-FPN) for enhanced cross-scale feature fusion, and a decoupled head to optimize classification and regression tasks. Assessments of the VHR-10 and RSOD datasets reveal that IMPROVED-YOLO outperforms its predecessor, attaining mean Average Precision (mAP) scores of 93.5% and 93.9%, respectively, indicating a substantial enhancement over the baseline YOLOv9 algorithm.

Skin Cancer is one of the most common cancers around the world. Detecting it in early stages is essential to improve the patient’s chance of survival. This study introduces a framework designed to improve the classification performance of binary skin cancer classification by tuning the hyperparameters of the MobileNet model using Particle Swarm Optimization (PSO). The optimizer is implemented using two approaches: a traditional sequential PSO and a parallel multi-threaded PSO approach. The ISIC 2018 dataset is used, and the hyperparameters such as the batch size, optimizer selection, and dense layer size were considered for tuning. The findings show that both approaches have achieved a strong classification accuracy between 95% and 97%. The parallel approach, however, has shown 20x up to 46x reduction in the training time, yet this was accompanied by an increase in memory usage, which rose by approximately 20% to 150% compared to the sequential approach, depending on swarm size and iteration count. These findings show the resource trade-off between training time vs memory consumption for applying an optimized Deep Learning Model in clinical settings, especially where computing resources are limited.