EUVIMEDEUVIMED entdecken
Crossref

Research on Teaching Strategies for Medical Image Processing Courses Enabled by Generative AI

Curriculum and Teaching Methodology · 2026 · 9 (3)

DOI: 10.23977/curtm.2026.090313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Curriculum and Teaching Methodology, 2026.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of artificial intelligence technology, medical imaging is gradually shifting from traditional image reading to AI-centered assisted diagnosis, quantitative analysis, and intelligent workflows. Medical Image Processing, as a fundamental course supporting clinical applications of AI, plays an important role in interdisciplinary medical-engineering education. This course is typically offered to both medical and engineering students, whose differences in knowledge structure, thinking patterns, and language systems often lead to learning gaps and reduced teaching efficiency. This paper proposes a bidirectional knowledge-complementary teaching strategy for medical-engineering integration using generative artificial intelligence as a teaching support tool. It adopts "medical context – engineering context – unified expression" as the core bridge. Without replacing the teacher's dominant role, generative AI is involved in concept explanation, terminology alignment, and learning feedback, helping engineering students understand clinical contexts and diagnostic logic, and helping medical students understand AI algorithms and evaluation systems. By analyzing teaching challenges, designing classroom activities, and summarizing implementation experience, this paper examines the strategy's value in reducing interdisciplinary barriers, promoting a shared language, and improving classroom interaction. It also discusses potential risks and governance approaches of generative AI in education. Practice shows that, with proper regulation and evaluation mechanisms, generative AI can serve as an effective interdisciplinary bridge in Medical Image Processing courses, providing a transferable model for medical-engineering teaching reform.

Zitieren

APA

(2026). Research on Teaching Strategies for Medical Image Processing Courses Enabled by Generative AI. Curriculum and Teaching Methodology, 9(3). https://doi.org/10.23977/curtm.2026.090313

Vancouver

Research on Teaching Strategies for Medical Image Processing Courses Enabled by Generative AI. Curriculum and Teaching Methodology. 2026;9(3). doi:10.23977/curtm.2026.090313

BibTeX
@article{euvimed2026,
  title = {Research on Teaching Strategies for Medical Image Processing Courses Enabled by Generative AI},
  journal = {Curriculum and Teaching Methodology},
  year = {2026},
  volume = {9},
  number = {3},
  doi = {10.23977/curtm.2026.090313}
}
Kostenlos starten →