The Reform and Application of AI-Driven Multimodal Data Fusion in Undergraduate Medical Imaging Education

Abstract

Medical imaging serves as a critical pillar of clinical diagnosis. Traditional teaching methods predominantly rely on single-modality images, inadequately preparing students for comprehensive decision-making in complex clinical scenarios. In recent years, the rapid advancement of artificial intelligence (AI), particularly multimodal data fusion technologies, has introduced new paradigms for reforming medical imaging education. This paper systematically reviews cutting-edge developments in AI-driven multimodal fusion for disease prediction, precision diagnosis, and clinical management while exploring feasible pathways for integrating these innovations into undergraduate teaching. By incorporating cross-scale data integration, interpretability analysis, and deep learning architectures, we propose a teaching reform framework centered on “clinical problem-driven learning, multimodal data immersion, and AI-assisted reasoning” to enhance medical students’ abilities in synthesizing complex imaging data and advancing clinical thinking.