DeepSkin: Robust Skin Cancer Classification Using Convolutional Neural Network Algorithm

Abstract

Classification of skin cancer is a growing research topic with significant challenges in the image processing. Learning algorithms for classifying a kind of skin cancer have been presented in recent articles to accelerate the diagnosis process with a rapid and accurate diagnosis. However, effective detection of skin cancer requires extensive graphical data. Inspired by deep learning successful results in computer vision, A Convolutional Neural Network (CNN) is proposed in this study to build a skin cancer classification model. We conduct this experiment by collecting massive skin cancer datasets, conducting pre-processing, training models, and evaluating the performance. Based on the experiment result, the benign and malignant classification model can obtain a good accuracy with a slight loss. Therefore, the results obtained reached an accuracy of 54%.