An overview of skin cancer classification based on deep learning

Abstract

Skin melanoma is one of the most dangerous diseases in the world. Correct classification of skin lesions in the first step can help create clinical judgment by providing an optimal judgment of the disease. As a result, the odds of treating the spread of cancer early may be increased. However, the automatic classification of skin cancer is tough because of the imbalance in most skin cancer images used in training. Several methods based on deep learning have been broadly used recently in skin cancer classification to resolve the problems in classification and attain acceptable outcomes. Nevertheless, reviews containing the aforementioned borderline difficulties in skin melanoma classification are still rare. Thus, this paper presents a summary of the newest deep learning procedures for classifying skin cancer. This paper starts with a discussion of skin cancer types, followed by the presentation of a public dataset available for skin cancer. Subsequently, some pretrained models of CNN used for classification are highlighted. Finally, some opportunities for skin cancer, such as data imbalance and limitation, generative adversarial network, various data sets, and data augmentation, are summarized.