Division of Mechanical and Biomedical Engineering, Graduate Program in System Health Science and Engineering, Ewha Womans University, Seoul, Republic of Korea.
Department of Cyber Security, Ewha Womans University, Seoul, Republic of Korea.
PLoS One. 2022 Sep 9;17(9):e0274308. doi: 10.1371/journal.pone.0274308. eCollection 2022.
Deep neural networks have shown great improvements in low-dose computed tomography (CT) denoising. Early algorithms were primarily optimized to obtain an accurate image with low distortion between the denoised image and reference full-dose image at the cost of yielding an overly smoothed unrealistic CT image. Recent research has sought to preserve the fine details of denoised images with high perceptual quality, which has been accompanied by a decrease in objective quality due to a trade-off between perceptual quality and distortion. We pursue a network that can generate accurate and realistic CT images with high objective and perceptual quality within one network, achieving a better perception-distortion trade-off. To achieve this goal, we propose a stationary wavelet transform-assisted network employing the characteristics of high- and low-frequency domains of the wavelet transform and frequency subband-specific losses defined in the wavelet domain. We first introduce a stationary wavelet transform for the network training procedure. Then, we train the network using objective loss functions defined for high- and low-frequency domains to enhance the objective quality of the denoised CT image. With this network design, we train the network again after replacing the objective loss functions with perceptual loss functions in high- and low-frequency domains. As a result, we acquired denoised CT images with high perceptual quality using this strategy while minimizing the objective quality loss. We evaluated our algorithms on the phantom and clinical images, and the quantitative and qualitative results indicate that ours outperform the existing state-of-the-art algorithms in terms of objective and perceptual quality.
深度神经网络在低剂量计算机断层扫描（CT）去噪方面取得了显著的进展。早期的算法主要是通过优化来获得准确的图像，以降低去噪图像与参考全剂量图像之间的失真，同时牺牲了过于平滑的不真实 CT 图像。最近的研究旨在通过保留高质量感知的去噪图像的细节来实现，这伴随着由于感知质量和失真之间的权衡而导致的客观质量下降。我们追求一种能够在一个网络中生成具有高客观和感知质量的准确和真实 CT 图像的网络，实现更好的感知-失真权衡。为了实现这一目标，我们提出了一种基于平稳小波变换辅助的网络，利用小波变换的高频和低频域的特性以及在小波域中定义的频率子带特定损失。我们首先为网络训练过程引入了平稳小波变换。然后，我们使用针对高频和低频域定义的客观损失函数来训练网络，以提高去噪 CT 图像的客观质量。通过这种网络设计，我们在高频和低频域中用感知损失函数替换客观损失函数后再次训练网络。因此，我们通过这种策略获得了具有高感知质量的去噪 CT 图像，同时最小化了客观质量损失。我们在幻影和临床图像上评估了我们的算法，定量和定性结果表明，在客观和感知质量方面，我们的算法优于现有的最先进算法。
