Skin Cancer Classification Using Deep Learning

Abstract

Cancer begins when cells in the body begin to multiply uncontrolled. Cancer can develop in any area of the body and spread to other parts. Cancer of the skin is one of the most prevalent forms of the disease found all over the world, and it can cause substantial years of possible life loss and lost productivity. The primary cause of skin cancer is direct exposure to sunshine. Melanoma is a form of skin cancer, and because it is the most dangerous form of skin cancer, it must be discovered early in order to be effectively treated. It is essential to establish a computer-assisted diagnostic method for early detection. In this report, the proposed approach seeks to differentiate between melanoma and non-melanoma types. Using a dataset containing numerous forms of skin cancer, the system achieved an accuracy of 83% percent on the testing dataset.