文献速递心血管CTDSA

基于生成对抗网络的冠状动脉CT血管成像运动伪影去除

Motion artifact removal in coronary CT angiography based on generative adversarial networks.
PubMed 文献 · Eur Radiol · 2022-07-12

纳入313例CCTA扫描患者(同一心动周期不同R-R间期相位有配对运动影响与无运动参考图像)及53例有ICA对比的CCTA病例,用Pix2pix GAN由运动影响图像生成无运动图像;GAN生成图像PSNR、SSIM、DSC、HD中位数分别为26.1、0.860、0.783、4.47,均显著优于运动影响图像(p<0.001),运动伪影减轻评分和整体图像质量评分均为4 vs 1(p<0.001);有ICA对比者中,GAN生成图像识别无狭窄、<50%狭窄、≥50%狭窄的准确率分别为81%、85%、70%,高于运动影响图像的66%、72%、68%。

要点

  • GAN生成图像PSNR、SSIM、DSC、HD中位数分别为26.1、0.860、0.783、4.47,显著优于运动影响图像(p<0.001)。
  • GAN生成图像运动伪影减轻评分4 vs 运动影响图像1(p<0.001),整体图像质量评分4 vs 1(p<0.001)。
  • 有ICA对比者中GAN生成图像识别无、<50%、≥50%狭窄准确率分别为81%、85%、70%。

核心结论

  • 生成对抗网络生成的CCTA图像较运动影响图像大幅改善图像质量和诊断准确率。

研究设计与样本

  • 研究纳入313例CCTA扫描患者,同一心动周期不同R-R间期相位有配对运动影响与无运动参考图像,另纳入53例有ICA对比的CCTA病例;采用Pix2pix图像到图像转换GAN,以运动影响与无运动参考配对训练生成无运动图像。

关键影像表现/征象

  • GAN生成图像PSNR中位数26.1(四分位距24.4-27.5),显著优于运动影响图像(p<0.001)。
  • GAN生成图像SSIM中位数0.860(四分位距0.830-0.882),显著优于运动影响图像(p<0.001)。
  • GAN生成图像DSC中位数0.783(四分位距0.714-0.825),显著优于运动影响图像(p<0.001)。
  • GAN生成图像HD中位数4.47(四分位距3.00-4.47),显著优于运动影响图像(p<0.001)。
  • 患者层面图像质量结果与图像层面相似。

诊断标准与关键数值

  • 有ICA对比者中,GAN生成图像识别无狭窄准确率81%,运动影响图像为66%。
  • 有ICA对比者中,GAN生成图像识别<50%狭窄准确率85%,运动影响图像为72%。
  • 有ICA对比者中,GAN生成图像识别≥50%狭窄准确率70%,运动影响图像为68%。

临床应用与阅片要点

  • 原文结论为GAN生成的CCTA图像较运动影响图像大幅改善图像质量和诊断准确率。

局限性

  • 原文未报告局限性。

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

OBJECTIVES: 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).

METHODS: 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.

RESULTS: 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.

CONCLUSION: Generative adversarial network-generated CCTA images greatly improved the image quality and diagnostic accuracy compared to motion-affected images.

KEY POINTS: • 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.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang, Jiang, Chen, et al. Motion artifact removal in coronary CT angiography based on generative adversarial networks. Eur Radiol. 2022. PMID: 35829786. doi:10.1007/s00330-022-08971-5

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。