A New Deep Learning Model for Skin Cancer Classification

Abstract

Cancer is a group of diseases that damage tissues by the uncontrolled proliferation of cells. The difficulty of distinguishing skin cancer, which is a common type of cancer, without technical support necessitates studies that can help specialists in the diagnosis phase. In this study, a deep learning model with 7 convolution layers and 3 neural layers was designed to classify the HAM10000 dataset, which consists of 7 classes and includes dermoscopic images. The accuracy rate for the test data of the proposed model was calculated as 99.01%. This result shows that the proposed model can help experts in diagnosing skin cancer.