Department of Radiology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Haining Rd.100, Shanghai, 200080, China.
Shukun (Beijing) Technology Co, Ltd., Jinhui Bd, Qiyang Rd, Beijing, 100102, China.
Eur Radiol. 2023 Jan;33(1):43-53. doi: 10.1007/s00330-022-08971-5. Epub 2022 Jul 12.
Coronary motion artifacts affect the diagnostic accuracy of coronary CT angiography (CCTA), especially in the mid right coronary artery (mRCA). The purpose is to correct CCTA motion artifacts of the mRCA using a GAN (generative adversarial network).
We included 313 patients with CCTA scans, who had paired motion-affected and motion-free reference images at different R-R interval phases in the same cardiac cycle and included another 53 CCTA cases with invasive coronary angiography (ICA) comparison. Pix2pix, an image-to-image conversion GAN, was trained by the motion-affected and motion-free reference pairs to generate motion-free images from the motion-affected images. Peak signal-to-noise ratio (PSNR), structural similarity (SSIM), Dice similarity coefficient (DSC), and Hausdorff distance (HD) were calculated to evaluate the image quality of GAN-generated images.
At the image level, the median of PSNR, SSIM, DSC, and HD of GAN-generated images were 26.1 (interquartile: 24.4-27.5), 0.860 (0.830-0.882), 0.783 (0.714-0.825), and 4.47 (3.00-4.47), respectively, significantly better than the motion-affected images (p < 0.001). At the patient level, the image quality results were similar. GAN-generated images improved the motion artifact alleviation score (4 vs. 1, p < 0.001) and overall image quality score (4 vs. 1, p < 0.001) than those of the motion-affected images. In patients with ICA comparison, GAN-generated images achieved accuracy of 81%, 85%, and 70% in identifying no, < 50%, and ≥ 50% stenosis, respectively, higher than 66%, 72%, and 68% for the motion-affected images.
Generative adversarial network-generated CCTA images greatly improved the image quality and diagnostic accuracy compared to motion-affected images.
• A generative adversarial network greatly reduced motion artifacts in coronary CT angiography and improved image quality. • GAN-generated images improved diagnosis accuracy of identifying no, < 50%, and ≥ 50% stenosis.
冠状动脉运动伪影会影响冠状动脉 CT 血管造影（CCTA）的诊断准确性，尤其是在右冠状动脉中段（mRCA）。本研究旨在使用生成对抗网络（GAN）校正 mRCA 的 CCTA 运动伪影。
我们纳入了 313 例 CCTA 扫描患者，这些患者在同一心动周期的不同 R-R 间期相位均有配对的受运动影响和不受运动影响的参考图像，另外还纳入了 53 例有经导管冠状动脉造影（ICA）比较的 CCTA 病例。Pix2pix 是一种图像到图像的转换 GAN，通过受运动影响和不受运动影响的参考对进行训练，以便从受运动影响的图像中生成不受运动影响的图像。计算峰值信噪比（PSNR）、结构相似性（SSIM）、Dice 相似系数（DSC）和 Hausdorff 距离（HD）来评估 GAN 生成图像的质量。
在图像水平上，GAN 生成图像的 PSNR、SSIM、DSC 和 HD 的中位数分别为 26.1（四分位间距：24.4-27.5）、0.860（0.830-0.882）、0.783（0.714-0.825）和 4.47（3.00-4.47），明显优于受运动影响的图像（p<0.001）。在患者水平上，图像质量结果相似。与受运动影响的图像相比，GAN 生成图像的运动伪影缓解评分（4 分比 1 分，p<0.001）和整体图像质量评分（4 分比 1 分，p<0.001）均有所提高。在有 ICA 比较的患者中，GAN 生成图像在识别无狭窄、<50%狭窄和≥50%狭窄的准确率分别为 81%、85%和 70%，高于受运动影响图像的 66%、72%和 68%。
与受运动影响的图像相比，生成对抗网络生成的 CCTA 图像大大改善了图像质量和诊断准确性。
• 生成对抗网络极大地减少了冠状动脉 CT 血管造影中的运动伪影，提高了图像质量。• GAN 生成的图像提高了识别无狭窄、<50%狭窄和≥50%狭窄的诊断准确性。
