Abstract
Skin cancer is the most prevalent type of cancer in the world. Melanoma, specifically is among the deadliest variants of cancer, But if detected early, most melanomas can be cured with minor surgery. In this study we propose an innovative melanoma detection pipeline which utilizes en-semble learning to combine the predictive power of several deep convolutional neural network models. All experiments are performed using image data acquired from the Society for Imaging Informatics in Medicine and the International Skin Imaging Collaboration SIIM-ISIC 2020. The proposed approach achieved a high performance with an Area Under Curve (AUC) of 99.02% outperforming many state-of-the-art algorithms.