Fink Anna, Rau Alexander, Reisert Marco, Bamberg Fabian, Russe Maximilian F
Department of Diagnostic and Interventional Radiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Breisacher Str 64, 79106 Freiburg, Germany.
Department of Neuroradiology, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
Radiol Artif Intell. 2025 Jul;7(4):e240790. doi: 10.1148/ryai.240790.
Large language models (LLMs) hold substantial promise in addressing the growing workload in radiology, but recent studies also reveal limitations, such as hallucinations and opacity in sources for LLM responses. Retrieval-augmented generation (RAG)-based LLMs offer a promising approach to streamline radiology workflows by integrating reliable, verifiable, and customizable information. Ongoing refinement is critical in order to enable RAG models to manage large amounts of input data and to engage in complex multiagent dialogues. This report provides an overview of recent advances in LLM architecture, including few-shot and zero-shot learning, RAG integration, multistep reasoning, and agentic RAG, and identifies future research directions. Exemplary cases demonstrate the practical application of these techniques in radiology practice. Artificial Intelligence, Deep Learning, Natural Language Processing, Tomography, x-Ray © RSNA, 2025.
大语言模型（LLMs）在应对放射学日益增长的工作量方面具有巨大潜力，但最近的研究也揭示了其局限性，例如大语言模型回复中的幻觉和信息来源不透明。基于检索增强生成（RAG）的大语言模型通过整合可靠、可验证和可定制的信息，为简化放射学工作流程提供了一种很有前景的方法。持续改进对于使RAG模型能够管理大量输入数据并参与复杂的多智能体对话至关重要。本报告概述了大语言模型架构的最新进展，包括少样本和零样本学习、RAG整合、多步推理和智能体RAG，并确定了未来的研究方向。示例案例展示了这些技术在放射学实践中的实际应用。人工智能、深度学习、自然语言处理、断层扫描、X射线 © RSNA，2025年
