Effectiveness of Data Augmentation for classification of Melanoma using Deep Convolutional Neural Network

Abstract

The melanoma is a type of skin cancer which develops from melanocytes, responsible to provide the skin colour. 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, the data augmentation methods are applied on the dermoscopic images of PH2 database to deal with the data imbalance problem. Finally, A novel 13-layer deep convolutional neural network (DCNN) is designed and trained with two groups of datasets and it is observed that the obtained accuracy for augmented dataset with no class imbalance achieved a competitive percentage of accuracy in comparison to the non-augmented dataset with class imbalance.