aSchool of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Shandong Province, Jinan, 250355, ChinabCollege of Medical Information and Artificial Intelligence, Shandong First Medical University, Shandong Province, Jinan, 250117, ChinadDepartment of Rehabilitation, Third Affiliated Hospital (Affiliated Hospital of Shandong Academy of Medical Sciences) of Shandong First Medical University, Shandong Province, Jinan, 250031, ChinacNeck-Shoulder and Lumbocrural Pain Hospital of Shandong First Medical University, Shandong Province, Jinan, 250062, ChinaeSchool of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, 300072, China
BACKGROUND: In the process of applying artificial intelligence to orthopedic imaging, the technical system exhibits a clear hierarchical structure: machine learning is the primary pathway to achieving artificial intelligence, while convolutional neural networks, a branch of deep learning, have become the core model for image analysis. Clarifying this technological lineage aids in systematically organizing the research evolution and trends in this field through bibliometric methods. OBJECTIVE: To...更多
BACKGROUND: In the process of applying artificial intelligence to orthopedic imaging, the technical system exhibits a clear hierarchical structure: machine learning is the primary pathway to achieving artificial intelligence, while convolutional neural networks, a branch of deep learning, have become the core model for image analysis. Clarifying this technological lineage aids in systematically organizing the research evolution and trends in this field through bibliometric methods. OBJECTIVE: To conduct a comprehensive analysis of the current research landscape and developmental trends of artificial intelligence within the field of orthopedic imaging, utilizing bibliometric methodologies, providing ideas and methods for future research. METHODS: A systematic search was performed on the Web of Science Core Collection database using a combination of keywords: artificial intelligence, deep learning, convolutional neural network, orthopedic imaging. A total of 460 English-language publications from 2015 to 2025 were included in the analysis. Bibliometric tools, including CiteSpace 6.4.R1, VOSviewer1.6.20, and Bibliometrix R-package, were employed to perform a multi-dimensional visualization analysis. The analysis covered annual publication trends, geographc and institutional contributions, author collaboration networks, keyword co-occurrence, clustering patterns, and the evolution of burst terms. RESULTS AND CONCLUSION: Over the past decade, the volume of scholarly output in this field has shown a consistent upward trajectory. China and the USA emerged as the most prolific contributors in terms of publication count, while the USA demonstrated superior performance in citation impact and international collaborative engagement. Key academic institutions, including Sichuan University, the University of California, and Harvard University, formed a central collaborative network. Research foci were primarily concentrated on areas such as bone age assessment, automated image segmentation, and the application of deep learning techniques in fracture detection and osteoarthritis diagnosis. Keywords such as bone age assessment, automated segmentation, and deep learning exhibited persistent bursts, reflecting the dynamic shifts in research emphasis over time. The academic interest in artificial intelligence within orthopedic imaging continues to grow significantly. Emerging areas such as intelligent segmentation, disease classification, and multimodal data integration represent promising directions for future investigation. This paper provides a systematic bibliometric overview of the field from a macro perspective, providing a reference for promoting the deep integration of artificial intelligence technology in orthopedic clinical practice. Through bibliometric analysis, a knowledge graph of research on the application of artificial intelligence in orthopedic imaging was constructed, systematically summarizing the current research status and hotspots in this field, aiming to provide reference and guidance for future related research.收起
