中国组织工程研究

中国组织工程研究 ›› 2026, Vol. 30 ›› Issue (28): 7418-7427.doi: 10.12307/2026.812

• 组织工程相关大数据分析 Big data analysis in tissue engineering • 上一篇    下一篇

人工智能应用于骨科影像诊断的文献计量学分析

岳宇航1，谢良玉2，史刘朋1，尹作震3，曹盛楠3，师  彬3，孙国栋4，5   

  1. 1山东中医药大学医学信息工程学院，山东省济南市  250355；2山东第一医科大学医学信息与人工智能学院，山东省济南市  250117；3山东第一医科大学附属颈肩腰腿痛医院，山东省济南市  250062；4山东第一医科大学第三附属医院(山东省医学科学院附属医院)康复科，山东省济南市  250031；5天津大学医学工程与转化医学研究院，天津市  300072
  • 收稿日期:2025-10-15 修回日期:2025-12-04 出版日期:2026-10-08 发布日期:2026-02-25
  • 通讯作者: 孙国栋，博士，主任医师，教授，山东第一医科大学第三附属医院(山东省医学科学院附属医院)康复科，山东省济南市 250031；天津大学医学工程与转化医学研究院，天津市 300072
  • 作者简介:岳宇航，男，2002年生，山东省菏泽市人，汉族，山东中医药大学在读硕士，主要从事医学图像处理方面的研究。
  • 基金资助:
    山东省自然科学基金(ZR2023QH042)，项目负责人：曹盛楠；山东省高等学校青创科技支持计划(2024KJN012)，项目负责人：曹盛楠；山东省重点研发计划(重大科技创新工程)项目(2022CXG020510)，项目负责人：师彬；济南市临床医学科技创新计划(202328051)，项目负责人：曹盛楠；济南市临床医学科技创新计划(202430007)，项目负责人：孙国栋

Bibliometric analysis of application of artificial intelligence in orthopedic imaging diagnosis

Yue Yuhang1, Xie Liangyu2, Shi Liupeng1, Yin Zuozhen3, Cao Shengnan3, Shi Bin3, Sun Guodong4, 5   

  1. 1School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, Shandong Province, China; 2College of Medical Information and Artificial Intelligence, Shandong First Medical University, Jinan 250117, Shandong Province, China; 3Neck-Shoulder and Lumbocrural Pain Hospital of Shandong First Medical University, Jinan 250062, Shandong Province, China; 4Department of Rehabilitation, Third Affiliated Hospital (Affiliated Hospital of Shandong Academy of Medical Sciences) of Shandong First Medical University, Jinan 250031, Shandong Province, China; 5School of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China
  • Received:2025-10-15 Revised:2025-12-04 Online:2026-10-08 Published:2026-02-25
  • Contact: Sun Guodong, MD, Chief physician, Professor, Department of Rehabilitation, Third Affiliated Hospital (Affiliated Hospital of Shandong Academy of Medical Sciences) of Shandong First Medical University, Jinan 250031, Shandong Province, China; School of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, China
  • About author:Yue Yuhang, MS candidate, School of Medical Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, Shandong Province, China
  • Supported by:
    Natural Science Foundation of Shandong Province, No. ZR2023QH042 (to CSN); Shandong Provincial Higher Education Youth Innovation and Technology Support Program, No. 2024KJN012 (to CSN); Shandong Provincial Key Research and Development Program, No. 2022CXG020510 (to SB); Jinan Municipal Clinical Medical Science and Technology Innovation Program, No. 202328051 (to CSN); Jinan Municipal Clinical Medical Science and Technology Innovation Program, No. 202430007 (to SGD) 

PDF

9

摘要：


文题释义：
人工智能：是一种以智能算法为核心的技术体系，具备多模态感知、数据分析和自主决策能力，能通过环境识别与自适应学习，实现精准高效的医疗服务。特别适用于高精度、个性化医疗场景，提供安全、可靠、柔和的诊疗方案，提升医疗质量与患者体验。
骨科影像：是融合影像技术与智能分析的医学领域，以骨骼肌肉系统健康为核心，全面评估骨骼状态，实现精准诊断与功能评估、风险预测及康复监测，体现多维关怀，倡导全生命周期骨骼健康管理，推动预防为主、治疗为辅的服务模式。

背景：在人工智能应用于骨科影像学的过程中，技术体系呈现清晰的层级关系：机器学习是实现人工智能的主要路径，其分支深度学习中的卷积神经网络，已成为图像分析的核心模型。明确这一技术谱系，有助于通过文献计量学方法系统梳理该领域的研究演进与趋势。
目的：基于文献计量学方法，全面分析人工智能在骨科影像学领域的研究现状与发展趋势，为未来研究提供思路和方法。
方法：通过检索Web of Science核心合集数据库，结合关键词artificial intelligence，deep learning，convolutional neural network，orthopedic imaging，纳入2015-2025年间的相关英文文献共460篇。采用CiteSpace 6.4.R1，VOSviewer 1.6.20和Bibliometrix软件，分别从年度发文量、国家和机构分布、作者合作网络、关键词共现、聚类与突现词演化等维度进行可视化分析。
结果与结论：①近10年来该领域文献数量稳步增长；②中国和美国为主要发文国家，其中美国在被引频次与国际合作影响力方面表现突出；四川大学、加州大学与哈佛大学构成核心合作机构网络；③研究热点主要集中于骨龄评估、图像自动分割、深度学习在骨折检测与骨关节炎诊断中的应用等，相关关键词bone age assessment，automated segmentation，deep learning持续突现，显示出研究重心的演进轨迹；④人工智能在骨科影像学中的研究热度持续攀升，智能分割、疾病分级和多模态数据融合是未来研究的重要方向；⑤此文从宏观层面对该领域进行了系统梳理，为推动人工智能技术在骨科临床实践中的深度融合提供参考；通过文献计量分析构建了人工智能在骨科影像学应用领域研究的知识图谱，系统总结了该领域的研究现状和热点，旨在为未来的相关研究提供参考和指导。

https://orcid.org/0009-0006-3347-0270(岳宇航)


中国组织工程研究杂志出版内容重点：干细胞；骨髓干细胞；造血干细胞；脂肪干细胞；肿瘤干细胞；胚胎干细胞；脐带脐血干细胞；干细胞诱导；干细胞分化；组织工程

关键词: 文献计量学, 人工智能, 骨科影像学, CiteSpace, VOSviewer, Bibliometrix

Abstract: 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: (1) Over the past decade, the volume of scholarly output in this field has shown a consistent upward trajectory. (2) 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. (3) 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. (4) 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. (5) 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.

Key words: bibliometrics, artificial intelligence, orthopedic imaging, CiteSpace, VOSviewer, Bibliometrix

中图分类号: