Yuan Lu, Jin Kai, Shao An, Feng Jia, Shi Caiping, Ye Juan, Grzybowski Andrzej
Department of Ophthalmology, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Hangzhou, China.
Eye Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
Clin Dermatol. 2024 Nov-Dec;42(6):570-584. doi: 10.1016/j.clindermatol.2024.09.012. Epub 2024 Sep 10.
Bibliometric methods were used to analyze publications on the use of artificial intelligence (AI) in skin cancer from 2010 to 2022, aiming to explore current publication trends and future directions. A comprehensive search using four terms, "artificial intelligence," "machine learning," "deep learning," and "skin cancer," was performed in the Web of Science database for original English language publications on AI in skin cancer from 2010 to 2022. We visually analyzed publication, citation, and coupling information, focusing on authors, countries and regions, publishing journals, institutions, and core keywords. The analysis of 989 publications revealed a consistent year-on-year increase in publications from 2010 to 2022 (0.51% versus 33.57%). The United States, India, and China emerged as the leading contributors. IEEE Access was identified as the most prolific journal in this area. Key journals and influential authors were highlighted. Examination of the top 10 most cited publications highlights the significant potential of AI in oncology. Co-citation network analysis identified four primary categories of classical literature on AI in skin tumors. Keyword analysis indicated that "melanoma," "classification," and "deep learning" were the most prevalent keywords, suggesting that deep learning for melanoma diagnosis and grading is the current research focus. The term "pigmented skin lesions" showed the strongest burst and longest duration, whereas "texture" was the latest emerging keyword. AI represents a rapidly growing area of research in skin cancer with the potential to significantly improve skin cancer management. Future research will likely focus on machine learning and deep learning technologies for screening and diagnostic purposes.
采用文献计量学方法分析2010年至2022年关于人工智能（AI）在皮肤癌中应用的出版物，旨在探索当前的出版趋势和未来方向。在科学网数据库中，使用“人工智能”“机器学习”“深度学习”和“皮肤癌”这四个术语，对2010年至2022年关于皮肤癌中AI的原始英文出版物进行了全面检索。我们直观地分析了出版、引用和耦合信息，重点关注作者、国家和地区、出版期刊、机构以及核心关键词。对989篇出版物的分析显示，2010年至2022年出版物数量逐年持续增加（从0.51%增至33.57%）。美国、印度和中国成为主要贡献者。《IEEE接入》被确定为该领域发文量最多的期刊。突出了关键期刊和有影响力的作者。对引用次数最多的前10篇出版物的审查突出了AI在肿瘤学中的巨大潜力。共引网络分析确定了皮肤肿瘤中AI经典文献的四个主要类别。关键词分析表明，“黑色素瘤”“分类”和“深度学习”是最常见的关键词，这表明用于黑色素瘤诊断和分级的深度学习是当前的研究重点。“色素沉着性皮肤病变”一词的爆发强度最强且持续时间最长而“纹理”是最新出现的关键词。AI是皮肤癌研究中一个快速发展的领域，有可能显著改善皮肤癌的管理。未来的研究可能会集中在用于筛查和诊断目的的机器学习和深度学习技术上。
