A Comparative Study on the Diagnosis of Skin Cancer using different Models in Deep Learning

Skin cancer is a common form of cancer, and early detection increases survival rates. This paper presents a comparison of the different types of deep learning models used to detect skin cancer. Based on Convolutional Neural Networks (CNN), the skin cancer detection is done. The different networks in CNN are used, namely ResNet18, AlexNet and ResNet50. Transfer learning is a neural network model, which is also used in skin cancer diagonosis. HAM10000 is the skin cancer dataset used and the accuracy obtained in using different models is then compared.