IEEE Trans Med Imaging. 2023 Jun;42(6):1799-1808. doi: 10.1109/TMI.2023.3241454. Epub 2023 Jun 1.
In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.
近年来，生成对抗网络（GANs）在医学成像中的潜在应用，如医学图像合成、恢复、重建、转换以及客观图像质量评估等方面，受到了极大的关注。尽管在生成高分辨率、感知逼真的图像方面取得了令人瞩目的进展，但目前尚不清楚现代 GAN 是否可靠地学习了对下游医学成像应用有意义的统计信息。在这项工作中，研究了最先进的 GAN 学习与客观图像质量评估相关的典型随机图像模型（SIM）统计信息的能力。结果表明，尽管所采用的 GAN 成功地学习了所考虑的特定医学 SIM 的几个基本的一阶和二阶统计信息，并生成了具有高感知质量的图像，但它未能正确地学习与这些 SIM 相关的几个图像特定统计信息，这凸显了迫切需要根据客观的图像质量衡量标准来评估医学图像 GAN。
