Six-Dimensional Closed-Loop Composite Talent Cultivation System for AI-Driven Medical Imaging Professionals

Abstract

Addressing key challenges in interdisciplinary talent cultivation—including fragmented medical-engineering knowledge frameworks for relevant majors in local universities, students’ inadequate capacity to deploy AI algorithms for practical scenarios, disrupted innovation chains, and insufficient integration of industry and education—this paper proposes a six-stage closed-loop talent cultivation framework. This framework consists of six interconnected and progressive phases: fundamental AI knowledge acquisition, academic competition training, research project-enabled capability cultivation, large-scale innovation project incubation, clinical outcome validation, and high-quality dissertation completion. This framework sequentially consolidates students’ foundational AI literacy, enables systematic hands-on engineering practice, grants students access to state-of-the-art research resources and authentic clinical data, supports the full-cycle development of innovative research outputs, facilitates the clinical translation of research findings, and guarantees the completion of high-quality academic dissertations. Simultaneously, it feeds exemplary research and practical achievements back into undergraduate teaching, thereby constructing a self-sustaining cyclical educational ecosystem. Two years of practical teaching reform implementation has verified that the proposed framework can comprehensively improve students’ interdisciplinary core competencies and provide a reproducible and scalable practical paradigm for talent cultivation in the medical-engineering interdisciplinary domain under the background of the New Engineering Education initiative.