Detection of Skin Cancer using Convolutional Neural Network

Abstract

Humanity faces a serious threat from skin cancer. Because of Melanoma skin cancer's quick development rate, high treatment costs, and high mortality rate, the importance of early skin cancer diagnosis has increased. Cancer cells are carefully found, and in most cases, treatment takes time. Using image processing and machine learning, this paper suggested an artificial skin cancer diagnosis system. After segmenting the dermoscopic pictures using the feature extraction approach, the characteristics of the damaged skin cells are retrieved. The retrieved features are stratified using a convolutional neural network classifier based on deep learning. After using the publicly accessible data set, an accuracy of 89.5 percent and a training accuracy of 93.7 percent were reached.