Bibliometric analysis of the application of artificial intelligence in orthopedic imaging

Abstract

Background: With the development of artificial intelligence (AI) and the increasing significance of imaging in orthopedics, the application of AI in the field of orthopedic imaging is becoming increasingly extensive. Previous studies show that the application of AI-based orthopedic imaging may break the traditional model of the field. As a result, relevant research has received attention, and numerous articles have been published. Through bibliometric analysis, this study summarized the knowledge structure of AI-based orthopedic imaging and explored its potential research trends and focal points.

Methods: In this study, literature on AI in the field of orthopedic imaging available in the Web of Science Core Collection (WoSCC) database from 1 January 2007 to 31 December 2024 was analyzed. In order to identify the main research topics and generate visual charts of countries, institutions, authors, and keyword networks, the search results were imported into VOSviewer and CiteSpace.

Results: A total of 3,147 publications were analyzed, revealing a rapid increase in AI research in orthopedic imaging since 2007, with over 90% of studies published after 2017. The United States (US) and China dominate this field, with the US leading in citations and academic influence, and China demonstrating significant growth in productivity. Institutional analysis highlighted Harvard University and Stanford University as key contributors, reflecting their strong academic influence. Keyword analysis identified three main research focuses: (I) advancements in algorithm development, particularly deep learning (DL) methods such as convolutional neural networks (CNNs); (II) applications in orthopedic disease imaging, including osteoarthritis, osteoporosis, and total knee arthroplasty; and (III) innovations in multimodal fusion and three-dimensional (3D) imaging techniques. Emerging trends emphasize integrating imaging data with clinical biomarkers to improve diagnostic accuracy and therapeutic decision-making. These findings provide a comprehensive overview of AI's role in orthopedic imaging, emphasizing areas of high impact and potential future directions for research.

Conclusions: The research on the application of AI in orthopedic imaging is a hot topic and indicates broad research prospects in the future. However, this study suggests that research teams should strengthen collaboration, especially international cooperation. Based on comprehensive analysis, the development of DL algorithms (especially CNNs), the use of AI in processing image data related to orthopedic diseases (segmentation, classification, and feature map extraction), and the expansion of AI imaging applications in different diseases are expected to become hotspots in future research on the application of AI in orthopedic imaging.

Keywords: Bibliometric analysis; artificial intelligence (AI); image; orthopedic.

Figure 1

Flowchart of the publications in the study.

Figure 2

Trends in publication volume and citation count in AI-based orthopedic imaging from 2007 to 2024. AI, artificial intelligence.

Figure 3

Geographic distribution and citation network of AI in orthopedic imaging research by country/region. (A) Geographic distribution of total publication volume by country/region; (B) visualization of country/region citation network over time generated by VOSviewer. AI, artificial intelligence.

Figure 4

Analysis of leading research institutions and funding agencies in AI-based orthopedic imaging. (A) Top 10 research institutions by citation volume; (B) top 10 research institutions by publication volume; (C) collaboration network co-occurrence analysis of research institutions by publication volume visualized with VOSviewer; (D) top 10 funding agencies by publication volume. AI, artificial intelligence; TLS, total link strength.

Figure 5

Citation analysis of journals and disciplinary co-citation in AI-based orthopedic imaging. (A) Co-citation network of different journals visualized with CiteSpace; (B) dual-map overlay of disciplinary co-citation in AI-based orthopedic imaging research visualized with CiteSpace. AI, artificial intelligence.

Figure 6

Visualization of author network and citation metrics. (A) Top 10 authors by publication volume, including citations and TLS; (B) top 10 authors by citation volume, including TLS; (C) co-occurrence network of authors with more than 10 publications visualized with VOSviewer; (D) citation network among highly cited authors visualized with VOSviewer. TLS, total link strength.

Figure 7

Visualization of co-cited references and citation bursts. (A) Clustering of co-cited references visualized with CiteSpace, with the timeline represented by lines of different colors. Nodes on the lines represent cited references; (B) visualization of the top 20 references with the strongest citation bursts in AI-based orthopedic imaging research visualized with CiteSpace. AI, artificial intelligence; WoS, Web of Science.

Figure 8

Visualization of keyword analysis and citation bursts. (A) Frequency and TLS of the top 25 keywords; (B) overlay visualization map of keyword co-occurrence analysis generated with VOSviewer; (C) keyword clustering and timeline visualization created with CiteSpace; (D) visualization of the top 20 keywords with the strongest citation bursts in AI-based orthopedic imaging research visualized with CiteSpace. AI, artificial intelligence; CT, computed tomography; MRI, magnetic resonance imaging; TLS, total link strength; WoS, Web of Science.