AUTHOR=Wu Yinhao , Chen Bin , Zeng An , Pan Dan , Wang Ruixuan , Zhao Shen 

TITLE=Skin Cancer Classification With Deep Learning: A Systematic Review

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.893972

DOI=10.3389/fonc.2022.893972

ISSN=2234-943X

ABSTRACT=Skin cancer is one of the most common diseases in the world. Correctly classifying skin lesions at an early stage could aid clinical decision-making by providing an accurate disease diagnosis, potentially increasing the chances of cure before cancer spreads. However, achieving automatic skin cancer classification is difficult because the majority of skin disease images used for model training are unbalanced and in short supply; meanwhile, the ability for domain adaptation and anti-interference are issues that cannot be overlooked. Recently, many deep learning-based methods have been widely used in skin cancer classification tasks to solve the above issues and achieved satisfactory results. Nonetheless, reviews that include the above-mentioned frontier problems in skin cancer classification are still scarce. In this paper, we aim to present a comprehensive review of the deep learning-based methods for the task of skin cancer classification. We begin with an overview of three types of dermatological images, followed by a list of publicly available datasets relating to skin cancer diseases. Following that, we look at some of the most popular deep learning algorithms and their applications in skin cancer classification. As a highlight of this paper, we next summarize several frontier problems, such as data imbalance, a lack of labeled data, domain adaptation, image noises, model efficiency, and corresponding solutions in the classification task. The main purpose of this article is to provide readers with a systematic and conceptual review of the latest works on  skin cancer classification with deep learning methods. Given the growing popularity of deep learning, there are still many challenges to overcome as well as chances to pursue in the future.