Global trends in Artificial Intelligence applications in anatomy: a content-based bibliometric analysis

Aims: This study aims to determine the global and national trends in Artificial Intelligence (AI) applications in the field of anatomy between 2019 and 2024 and to identify the methodological and educational priorities arising from these trends.Methods: The study is based on a bibliometric analysis of publications indexed in the Web of Science (SCI-Expanded) and TR Index databases. Publication year, citation metrics, author and country distributions, and collaboration networks were evaluated. Additionally, all studies were categorized by two researchers using a manual content-based classification system in terms of anatomical focus (radiological anatomy, microanatomy, education) and AI task type (segmentation, classification, text generation, etc.). Inter-coder agreement was assessed qualitatively, and consensus was achieved.Results: A total of 168 studies (155 WoS, 13 TR Index) meeting the inclusion criteria were reviewed. While most studies focused on radiological and microanatomical applications, research on education and large language models (LLMs) was more limited. After 2021, the number of publications rose sharply, with national data (TR Index) reflecting the same upward global trend.Conclusion: During 2019–2024, AI in anatomy research has mainly focused on radiological and microanatomical fields, highlighting the link between imaging methodologies and structural analysis. Educational applications and LLM-based studies remain limited within Anatomy & Morphology journals. Progress will rely on multi-center data sharing and methodological standardization (TRIPOD+AI, CLAIM). This study outlines the thematic evolution of AI–anatomy research, providing a reference for its integration into anatomy and education.