Abstract

Malignant skin lesions, commonly referred to as skin cancer, represent a leading cause of global mortality. The integration of advanced deep learning methodologies facilitates the early diagnosis of these lesions, thereby offering a vital pathway to decrease associated mortality rates. For the automated categorization of dermoscopic images, deep convolutional neural networks (CNNs) have consistently exhibited performance superior to that of traditional machine learning algorithms. The current research focuses on the development of a highly precise ensemble classifier built upon foundational CNN architectures for the purpose of classifying skin lesions. To ensure the broad generalizability of the proposed model, strategic enhancements in diversity were implemented to bolster both systemic resilience and accuracy. Specifically, this necessary variance was introduced at both the dataset and the algorithmic classifier levels. The comprehensive ISIC 2018 challenge dataset, encompassing more than 13,000 dermoscopic images, was utilized across the training, validation, and testing phases. Experimental outcomes indicate that the developed ensemble framework attained an accuracy rate of 90.15%, successfully surpassing baseline CNN configurations and comparable contemporary classifiers in terms of overall accuracy and robust performance.