影像生成式人工智能在放射学中的应用:综合更新
本文综述了影像生成式人工智能中常用的生成对抗网络与扩散模型,总结了其在放射学临床任务(直接图像利用、病灶检测、分割和诊断)中的效用,并讨论了生成图像的评价方法及幻觉问题,旨在为放射学实践与研究提供指导。
要点
- 生成式AI可生成大量无标注影像数据,促进下游深度学习任务。
- 本文总结生成对抗网络与扩散模型及其在放射学临床任务中的效用。
- 本文讨论生成图像的评价方法与幻觉问题,以指导放射学实践与研究。
核心结论
- 本文旨在通过综述影像生成式AI的基础理论、生成图像的评价方法、临床与研究效用及幻觉问题,指导读者在放射学实践与研究中使用影像生成式AI。
研究设计与样本
- 综述类文章,总结了常用的生成对抗网络与扩散模型,并归纳其在放射学临床任务中的效用及生成图像的评价方法。
局限性
- 原文指出生成式AI的评价方法与临床效用尚未被彻底综述。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
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.
引用
- Jung HK, Kim K, Park JE, et al. Image-Based Generative Artificial Intelligence in Radiology: Comprehensive Updates. Korean J Radiol. 2024. PMID: 39473088. doi:10.3348/kjr.2024.0392
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。