Seven Class Classification of Skin Lesions by using Incremental Convolutional Neural Network in Python

Abstract

Classification of skin lesions in various cancerous type plays a crucial role in diagnosing various, local and gene related, medical conditions in the field of medical science. Classification of these lesions in several cancerous types i.e Melanoma (MEL), Melanomic Neves (NV), Basal Cell Carcinoma (BCC), Actinic Keratosis (AKIEC), Benign Keratosis (BKL), Dermatofibroma (DF),Vascular Lesion (VASC) gives some insight about disease. Skin cancer are most lethal type of cancer but patients have high recovery rates if the disease is discovered in its early stages. Several approaches to automatic detection and diagnosis have been explored by different authors, using various techniques. This paper presents classification of skin lesions in various skin cancers and followed by application of Incremental approach for Convolution Neural Network on dermoscopy images. International Skin Imaging Collaboration (ISIC) 2018 challenge Dataset is used in in this paper. The procedure used in this paper yields an accuracy of 90.26%.