Automatic Classification of Melanoma Skin Cancer with Deep Convolutional Neural Networks

Melanoma skin cancer is one of the most dangerous types cancer, which, if not diagnosed early, may lead to death. Therefore, an accurate diagnosis needed detect melanoma. Traditionally, a dermatologist utilizes microscope inspect and then provide report on biopsy for diagnosis; however, this process easy requires experience. Hence, there need facilitate while still yielding diagnosis. For purpose, artificial intelligence techniques can assist in carrying out In study, we considered detection melanoma through deep learning based cutaneous image processing. tested several convolutional neural network (CNN) architectures, including DenseNet201, MobileNetV2, ResNet50V2, ResNet152V2, Xception, VGG16, VGG19, GoogleNet, evaluated associated models graphical processing units (GPUs). A dataset consisting 7146 images was processed using these models, compared obtained results. The experimental results showed that GoogleNet obtain highest performance accuracy both training test sets (74.91% 76.08%, respectively).