A Bibliometric Review of Deep Learning Approaches in Skin Cancer Research

Early detection of skin cancer is crucial for successful treatment. Various methods have been developed for this purpose, including traditional machine learning, deep learning, and hybrid approaches. This study aims to provide an overview and highlight developments in the use of deep learning for early skin cancer diagnosis. This study searches for publications in the Scopus database from 2019 to 2024. The search string is used to find articles by their abstracts, titles, and keywords. The search string includes several public datasets used for experiments, like HAM and ISIC. This ensures the papers found are relevant. Some filters are applied based on the year, document type, source type, and language. The analysis found 1,697 articles. The most common were journals and conference proceedings. Affiliations are predominantly from the department of dermatology and the faculty of computer science. Beyond the statistical discussions, this paper also highlights the ten most cited references and reviews specific bibliometric studies related to early skin cancer diagnosis. Bibliometric analysis provides a systematic method for identifying relevant research studies. Advanced software like VOSviewer and Bibliometrix help to assist this study. Given the growth in the past five years, interest in deep learning for skin cancer detection should rise.