Melanoma Skin Lesions Classification using Deep Convolutional Neural Network with Transfer Learning

Abstract

Skin cancer is basically the unnatural growth of skin tissues and it can be fatal. Lately, it has evolved into one of the most perilous types of other cancers in the human body. Premature detection can help to endure the patient. Detection of skin cancer is quite difficult. At present in medical image diagnosis, the performance of computer vision is quite conducive. Together with the progress in technology and impetuous increment in computer provision, different types of machine learning techniques and deep learning models have arisen for the analysis of medical images particularly skin lesion images. In this study, we propose a deep learning model with some image pre-processing steps that help to categorize skin lesions with a better classification rate than other existing models. Normalization, data reduction, and data augmentation are used in pre-processing steps to classify benign and malignant cancer lesions from the HAM10000 dataset. From the experimental result, the proposed model gained an accuracy of 96.10% in training and 90.93% during testing. This model reduces the execution time and performs well-handled.