Classification of Skin Cancer Images with Convolutional Neural Network Architectures

Abstract

The skin, in which our body is completely covered, both provides the heat balance of our body and protects our body against external factors. Skin cancers, which occur as a result of the uncontrolled proliferation of cells on the skin surface, are one of the most common types of cancer in the world. Early detection of skin cancers means early treatment of the disease. With early diagnosis, patients can be cured earlier and mortality rates can be reduced. The hardest part of skin cancer diagnosis is that skin lesions are very similar to each other. Therefore, it is of great importance that skin cancer can be diagnosed and classified as benign or malignant tumor. In this study, Convolutional Neural Network networks are used to determine whether skin cancer is benign or malignant. Separate results are obtained with Alexnet, Resnet50, Densenet201 and Googlenet. Then the performance rates of the models used have been compared. The highest accuracy rate is achieved with the Resnet50 model with 83.49%. This rate is an important value for early diagnosis and treatment of the disease.