Skin Cancer (SC) is among the most hazardous due to its high mortality rate. Therefore, early detection of this disease would be very helpful in the treatment process. Multilevel Thresholding (MLT) is widely used for extracting regions of interest from medical images. Therefore, this paper utilizes the recent Coronavirus Disease Optimization Algorithm (COVIDOA) to address the MLT issue of SC images utilizing the hybridization of Otsu, Kapur, and Tsallis as fitness functions. Various SC images are utilized to validate the performance of the proposed algorithm. The proposed algorithm is compared to the following five meta-heuristic algorithms: Arithmetic Optimization Algorithm (AOA), Sine Cosine Algorithm (SCA), Reptile Search Algorithm (RSA), Flower Pollination Algorithm (FPA), Seagull Optimization Algorithm (SOA), and Artificial Gorilla Troops Optimizer (GTO) to prove its superiority. The performance of all algorithms is evaluated using a variety of measures, such as Mean Square Error (MSE), Peak Signal-To-Noise Ratio (PSNR), Feature Similarity Index Metric (FSIM), and Normalized Correlation Coefficient (NCC). The results of the experiments prove that the proposed algorithm surpasses several competing algorithms in terms of MSE, PSNR, FSIM, and NCC segmentation metrics and successfully solves the segmentation issue.

This research proposes a multi-level predictive algorithm based on the k-means algorithm with multiple adaptations. The research highlights the main limitations of k-means and proposes a set of adaptations that enhance the clustering task results in accuracy with minimal centroid distance error. The study proposes three enhancements in selecting the number of clusters, identifying the initial point, and exploring the contributing features set. Moreover, prediction is performed through a multi-level paradigm targeting performance enhancement by following the partitioning approach. The research experimental study focused on applying the proposed algorithm to the healthcare supply chain as it is one of the most influential factors for health services delivery. The proposed algorithm is applied to a dataset that is offered by USAID which includes 31622 records with 104 attributes. The proposed algorithm aims to predict the valued information in the supply chain progress such as predicted delivery time, predicted delay time, and other vital attributes. The data source is the USAID dataset; however, the research utilized the dataset for multiple objectives in vital aspects prediction of the healthcare supply chain with an average accuracy of 97.45%.

In the era of big data, medical imaging systems create millions of medical images daily. Securing these images during their transmission and storage is a challenging task. Encryption is a practical approach for securing medical images, as it ensures the security of these images while preserving their sensitive contents. Multiple-image encryption is preferable to single-image encryption, in which patches of medical images are encrypted simultaneously. A novel multi-medical image encryption algorithm based on stack representation and block division is proposed. During preprocessing, the medical images are stacked into a 3D cube to prepare for the encryption process. The cube experiences a block division phase, followed by individual confusion and diffusion phases for each block. These phases utilize different keys generated from a Baker chaotic map, incorporating swapping and XOR operations, which result in a fully encrypted cube. The scalability and effectiveness of the proposed algorithm are tested through experiments, revealing its promise as a secure approach for encrypting color and grayscale medical images. The proposed MIE algorithm is robust against various attacks, exhibiting superior performance in terms of speed and security compared to similar methods.

Skin cancer is a widespread and potentially fatal disease that requires accurate diagnosis for effective treatment. A novel method for improving the accuracy of skin cancer detection and classification using a Convolutional Neural Network (CNN) architecture is presented. The proposed approach addresses critical challenges in skin cancer recognition, including lesion segmentation, feature extraction, and merging. The method begins with optimized K-Nearest Neighbors (KNN) for skin lesion segmentation, followed by feature extraction using two advanced deep learning models: Darknet-53 and MobileNet-V2. These extracted features are reduced via an average pooling layer and then fused to classify the lesion into seven categories using a multi-class Support Vector Machine (SVM). The Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are used to evaluate the segmentation performance. In contrast, classification performance was measured using sensitivity, accuracy, specificity, F1 Score, and precision. The proposed method achieved a PSNR of 19.5224 and an SSIM of 0.9754, yielding segmentation and classification metrics of 99.3% accuracy, 85.55% sensitivity, 99.63% specificity, 91.5% precision, and an F1-score of 87.57. Finally, the proposed model outperforms single-learning models in feature extraction and classification.