Classification of Skin Lesions Using Deep Convolutional Neural Network

Abstract

The melanoma is a type of skin cancer which develops from melanocytes, responsible to provide the skin color. The severity of melanoma cancer is defined on the basis of different stages which depends upon the depth of penetration and the early detection of melanoma at its prodromal stage is very crucial to stop its advancement. In this work, a novel variant of deep convolutional neural network (DCNN) is developed to perform a binary classification of normal nevus and melanoma by using the dermoscopic images of the PH 2 dataset. Finally, the classification accuracy of the proposed DCNN emerged as the best method to categorize the normal nevus and melanoma with competitive classification accuracy.