Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
Korean J Radiol. 2024 Nov;25(11):959-981. doi: 10.3348/kjr.2024.0392.
Generative artificial intelligence (AI) has been applied to images for image quality enhancement, domain transfer, and augmentation of training data for AI modeling in various medical fields. Image-generative AI can produce large amounts of unannotated imaging data, which facilitates multiple downstream deep-learning tasks. However, their evaluation methods and clinical utility have not been thoroughly reviewed. This article summarizes commonly used generative adversarial networks and diffusion models. In addition, it summarizes their utility in clinical tasks in the field of radiology, such as direct image utilization, lesion detection, segmentation, and diagnosis. This article aims to guide readers regarding radiology practice and research using image-generative AI by 1) reviewing basic theories of image-generative AI, 2) discussing the methods used to evaluate the generated images, 3) outlining the clinical and research utility of generated images, and 4) discussing the issue of hallucinations.
生成式人工智能（AI）已应用于图像领域，用于图像质量增强、领域迁移以及人工智能建模的训练数据扩充，以应用于各种医学领域。图像生成式 AI 可以生成大量未注释的成像数据，这有利于多种下游深度学习任务。然而，它们的评估方法和临床实用性尚未得到彻底审查。本文总结了常用的生成式对抗网络和扩散模型。此外，它还总结了它们在放射学领域的临床任务中的效用，例如直接图像利用、病变检测、分割和诊断。本文旨在通过以下方式指导读者使用图像生成式 AI 进行放射学实践和研究：1）回顾图像生成式 AI 的基本理论，2）讨论用于评估生成图像的方法，3）概述生成图像的临床和研究效用，以及 4）讨论幻觉问题。
