Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany.
Eur Radiol. 2021 Aug;31(8):6087-6095. doi: 10.1007/s00330-021-07714-2. Epub 2021 Feb 25.
To reduce the dose of intravenous iodine-based contrast media (ICM) in CT through virtual contrast-enhanced images using generative adversarial networks.
Dual-energy CTs in the arterial phase of 85 patients were randomly split into an 80/20 train/test collective. Four different generative adversarial networks (GANs) based on image pairs, which comprised one image with virtually reduced ICM and the original full ICM CT slice, were trained, testing two input formats (2D and 2.5D) and two reduced ICM dose levels (-50% and -80%). The amount of intravenous ICM was reduced by creating virtual non-contrast series using dual-energy and adding the corresponding percentage of the iodine map. The evaluation was based on different scores (L1 loss, SSIM, PSNR, FID), which evaluate the image quality and similarity. Additionally, a visual Turing test (VTT) with three radiologists was used to assess the similarity and pathological consistency.
The -80% models reach an SSIM of > 98%, PSNR of > 48, L1 of between 7.5 and 8, and an FID of between 1.6 and 1.7. In comparison, the -50% models reach a SSIM of > 99%, PSNR of > 51, L1 of between 6.0 and 6.1, and an FID between 0.8 and 0.95. For the crucial question of pathological consistency, only the 50% ICM reduction networks achieved 100% consistency, which is required for clinical use.
The required amount of ICM for CT can be reduced by 50% while maintaining image quality and diagnostic accuracy using GANs. Further phantom studies and animal experiments are required to confirm these initial results.
• The amount of contrast media required for CT can be reduced by 50% using generative adversarial networks. • Not only the image quality but especially the pathological consistency must be evaluated to assess safety. • A too pronounced contrast media reduction could influence the pathological consistency in our collective at 80%.
通过生成对抗网络（GAN）使用虚拟对比增强图像来减少 CT 中静脉碘基造影剂（ICM）的剂量。
将 85 例患者的动脉期双能 CT 随机分为 80/20 训练/测试集。基于包含一个虚拟降低 ICM 与原始全 ICM CT 切片的图像对，训练了四种不同的生成对抗网络（GAN），测试了两种输入格式（2D 和 2.5D）和两种降低 ICM 剂量水平（-50%和-80%）。通过使用双能创建虚拟非对比系列并添加相应百分比的碘图，来减少静脉内 ICM 的量。评估基于不同的分数（L1 损失、SSIM、PSNR、FID），这些分数评估图像质量和相似性。此外，还使用三位放射科医生进行了视觉图灵测试（VTT），以评估相似性和病理一致性。
-80%的模型达到了>98%的 SSIM、>48 的 PSNR、7.5 到 8 之间的 L1 和 1.6 到 1.7 之间的 FID。相比之下，-50%的模型达到了>99%的 SSIM、>51 的 PSNR、6.0 到 6.1 之间的 L1 和 0.8 到 0.95 之间的 FID。对于病理一致性这一关键问题，只有 50%的 ICM 降低网络达到了 100%的一致性，这是临床使用所必需的。
使用 GAN 可以将 CT 所需的 ICM 量减少 50%，同时保持图像质量和诊断准确性。需要进一步的体模研究和动物实验来证实这些初步结果。
使用生成对抗网络（GAN）可以将 CT 所需的造影剂量减少 50%。
为了评估安全性，不仅要评估图像质量，还要评估特别是病理一致性。
在我们的 80%的患者中，造影剂的过度降低可能会影响病理一致性。
