Generative adversarial networks (GANs) and their extensions have carved open many exciting ways to tackle well known and challenging medical image analysis problems such as medical image de-noising, reconstruction, segmentation, data simulation, detection or classification. Furthermore, their ability to synthesize images at unprecedented levels of realism also gives hope that the chronic scarcity of labeled data in the medical field can be resolved with the help of these generative models. In this review paper, a broad overview of recent literature on GANs for medical applications is given, the shortcomings and opportunities of the proposed methods are thoroughly discussed, and potential future work is elaborated. We review the most relevant papers published until the submission date. For quick access, essential details such as the underlying method, datasets, and performance are tabulated. An interactive visualization that categorizes all papers to keep the review alive is available at http://livingreview.in.tum.de/GANs_for_Medical_Applications/.

生成对抗网络 (GAN) 及其扩展开辟了许多令人兴奋的方法来解决众所周知且具有挑战性的医学图像分析问题，例如医学图像去噪、重建、分割、数据模拟、检测或分类。此外，它们以前所未有的逼真度合成图像的能力也让人们希望借助这些生成模型可以解决医学领域标记数据的长期稀缺问题。在这篇综述论文中，对用于医学应用的 GAN 的近期文献进行了广泛的概述，彻底讨论了所提出方法的缺点和机会，并详细阐述了未来的潜在工作。我们审查在提交日期之前发表的最相关的论文。为了快速访问，表中列出了基本的方法、数据集和性能等基本细节。可在 http://livingreview.in.tum.de/GANs_for_Medical_Applications/ 上获得对所有论文进行分类以保持评论活跃的交互式可视化。