Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Korea.
Department of Transdisciplinary Studies, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, Korea.
Korean J Radiol. 2020 Oct;21(10):1165-1177. doi: 10.3348/kjr.2020.0020. Epub 2020 Jul 17.
To assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction.
We retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction).
Objective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons.
Application of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.
评估基于深度学习的降噪技术与迭代重建联合应用于冠状动脉 CT 血管造影（CCTA）以进一步降低噪声的可行性。
我们回顾性纳入了 2017 年 3 月至 2018 年 6 月期间连续 82 例接受 CCTA 和有创冠状动脉造影的患者（男/女=60/22；平均年龄 67.0±10.8 岁）。所有纳入患者均行迭代重建的 CCTA（西门子公司的 ADMIRE 3 级）。我们开发了一种基于深度学习的降噪技术（ClariCT.AI，ClariPI），它基于改良的 U 型网络模型设计，用于预测原始图像中低剂量噪声的可能发生情况。通过从原始图像中减去预测噪声来获得降噪图像。客观计算图像噪声、CT 衰减、信噪比（SNR）和对比噪声比（CNR）。边缘上升距离（ERD）作为图像锐度的指标进行测量。两位盲法读者使用 5 分制对图像质量进行主观评分。根据是否存在显著狭窄（≥50%管腔减少）评估 CCTA 的诊断性能。
客观图像质量（原始 vs. 降噪：图像噪声，67.22±25.74 vs. 52.64±27.40；左主干 SNR，21.91±6.38 vs. 30.35±10.46；左主干 CNR，23.24±6.52 vs. 31.93±10.72；均<0.001）和主观图像质量（2.45±0.62 vs. 3.65±0.60，<0.001）在降噪图像中显著改善。降噪图像的平均 ERD 明显小于原始图像（0.98±0.08 vs. 0.09±0.08，<0.001）。关于诊断准确性，配对比较之间没有观察到显著差异。
基于深度学习的技术与迭代重建联合应用可以提高 CCTA 图像的降噪性能，显著改善客观和主观图像质量。
