Artificial intelligence for medical imaging education: bibliometric and visual analysis

Area of Science:

• Bibliometrics
• Medical Education
• Artificial Intelligence
• Medical Imaging

Background:

• Limited quantitative understanding of AI's knowledge structures and collaborations in medical imaging education.
• Need to characterize the transition from technical AI feasibility to pedagogical integration and cross-institutional partnerships.

Purpose of the Study:

• To quantitatively analyze the knowledge structures, collaborative networks, and evolutionary trends of AI in medical imaging education.
• To identify key journals, institutions, and thematic shifts in this interdisciplinary field.

Main Methods:

• Structured literature search in Web of Science and Scopus (2006-2025).
• Bibliometric analyses using CiteSpace, VOSviewer, and Bibliometrix.
• Analysis of citation trends, collaboration networks, keyword bursts, and journal distributions.

Main Results:

• 577 articles retrieved, with exponential growth since 2019.
• US and China are the leading contributors; BMC Medical Education, Insights into Imaging, and Academic Radiology are key journals.
• Keyword analysis shows a shift from foundational algorithms to generative AI, integrating technical, pedagogical, and ethical aspects.

Conclusions:

• Characterized a dual-polar production structure dominated by the US and China.
• Identified an evolving research landscape with generative AI as a new thematic cluster.
• Provides a quantitative baseline for curriculum development, performance benchmarks, and ethical governance in AI for medical imaging education.