Department of Radiology, Kangwon National University Hospital, Kangwon National University School of Medicine, Chuncheon, Republic of Korea.
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul, Republic of Korea.
Eur Radiol. 2020 Dec;30(12):6779-6787. doi: 10.1007/s00330-020-07020-3. Epub 2020 Jun 29.
This study determined the effect of dose reduction and kernel selection on quantifying emphysema using low-dose computed tomography (LDCT) and evaluated the efficiency of a deep learning-based kernel conversion technique in normalizing kernels for emphysema quantification.
A sample of 131 participants underwent LDCT and standard-dose computed tomography (SDCT) at 1- to 2-year intervals. LDCT images were reconstructed with B31f and B50f kernels, and SDCT images were reconstructed with B30f kernels. A deep learning model was used to convert the LDCT image from a B50f kernel to a B31f kernel. Emphysema indices (EIs), lung attenuation at 15th percentile (perc15), and mean lung density (MLD) were calculated. Comparisons among the different kernel types for both LDCT and SDCT were performed using Friedman's test and Bland-Altman plots.
All values of LDCT B50f were significantly different compared with the values of LDCT B31f and SDCT B30f (p < 0.05). Although there was a statistical difference, the variation of the values of LDCT B50f significantly decreased after kernel normalization. The 95% limits of agreement between the SDCT and LDCT kernels (B31f and converted B50f) ranged from - 2.9 to 4.3% and from - 3.2 to 4.4%, respectively. However, there were no significant differences in EIs and perc15 between SDCT and LDCT converted B50f in the non-chronic obstructive pulmonary disease (COPD) participants (p > 0.05).
The deep learning-based CT kernel conversion of sharp kernel in LDCT significantly reduced variation in emphysema quantification, and could be used for emphysema quantification.
• Low-dose computed tomography with smooth kernel showed adequate performance in quantifying emphysema compared with standard-dose CT. • Emphysema quantification is affected by kernel selection and the application of a sharp kernel resulted in a significant overestimation of emphysema. • Deep learning-based kernel normalization of sharp kernel significantly reduced variation in emphysema quantification.
本研究旨在探讨剂量降低和核选择对低剂量计算机断层扫描（LDCT）定量肺气肿的影响，并评估基于深度学习的核转换技术在标准化肺气肿定量核方面的效率。
本研究纳入了 131 名参与者，他们在 1 至 2 年的时间间隔内接受了 LDCT 和标准剂量计算机断层扫描（SDCT）检查。LDCT 图像采用 B31f 和 B50f 核重建，SDCT 图像采用 B30f 核重建。使用深度学习模型将 LDCT 图像从 B50f 核转换为 B31f 核。计算肺气肿指数（EI）、15 百分位数肺衰减（perc15）和平均肺密度（MLD）。采用 Friedman 检验和 Bland-Altman 图比较不同核类型的 LDCT 和 SDCT。
LDCT B50f 的所有值与 LDCT B31f 和 SDCT B30f 的值均存在显著差异（p<0.05）。虽然存在统计学差异，但核归一化后 LDCT B50f 值的变化明显减小。SDCT 与 LDCT 核（B31f 和转换的 B50f）之间的 95%一致性界限分别为-2.9%至 4.3%和-3.2%至 4.4%。然而，在非慢性阻塞性肺疾病（COPD）患者中，SDCT 与 LDCT 转换的 B50f 之间的 EI 和 perc15 无显著差异（p>0.05）。
基于深度学习的 CT 核转换技术可显著降低 LDCT 中锐利核肺气肿定量的变异性，可用于肺气肿定量。
与标准剂量 CT 相比，采用平滑核的低剂量 CT 定量肺气肿的性能良好。
肺气肿定量受核选择的影响，应用锐利核会导致肺气肿的显著高估。
基于深度学习的锐利核归一化可显著降低肺气肿定量的变异性。
