Bradshaw Tyler J, Tie Xin, Warner Joshua, Hu Junjie, Li Quanzheng, Li Xiang
Department of Radiology, University of Wisconsin-Madison, Madison, Wisconsin;
Department of Radiology, University of Wisconsin-Madison, Madison, Wisconsin.
J Nucl Med. 2025 Feb 3;66(2):173-182. doi: 10.2967/jnumed.124.268072.
Large language models (LLMs) are poised to have a disruptive impact on health care. Numerous studies have demonstrated promising applications of LLMs in medical imaging, and this number will grow as LLMs further evolve into large multimodal models (LMMs) capable of processing both text and images. Given the substantial roles that LLMs and LMMs will have in health care, it is important for physicians to understand the underlying principles of these technologies so they can use them more effectively and responsibly and help guide their development. This article explains the key concepts behind the development and application of LLMs, including token embeddings, transformer networks, self-supervised pretraining, fine-tuning, and others. It also describes the technical process of creating LMMs and discusses use cases for both LLMs and LMMs in medical imaging.
大语言模型（LLMs）有望对医疗保健产生颠覆性影响。众多研究已证明大语言模型在医学成像方面有前景广阔的应用，随着大语言模型进一步演变成能够处理文本和图像的大型多模态模型（LMMs），这一应用数量还会增加。鉴于大语言模型和大型多模态模型在医疗保健中将发挥的重要作用，医生了解这些技术的基本原理很重要，这样他们就能更有效、更负责地使用这些技术，并有助于指导其发展。本文解释了大语言模型开发和应用背后的关键概念，包括令牌嵌入、变压器网络、自监督预训练、微调等。它还描述了创建大型多模态模型的技术过程，并讨论了大语言模型和大型多模态模型在医学成像中的用例。
