A Hybrid Deep Learning Ensemble for Accurate Skin Cancer Classification

Skin cancer is one of the most common types of cancer worldwide, and early detection is crucial for improving patient survival rates. In this study, we propose a hybrid deep learning ensemble model for the automatic classification of dermoscopic images into benign and malignant categories. The framework integrates multiple deep learning architectures and combines their predictive strengths through a meta-learning approach. Experimental evaluations on a benchmark dataset demonstrated that the proposed ensemble achieved a classification accuracy of 91.7% and a ROC-AUC score of 0.974, outperforming individual models. These results highlight the potential of hybrid ensemble methods as reliable computer-aided diagnostic tools for dermatology, contributing to early and accurate skin cancer detection.