Department of Radiology, Seoul National University College of Medicine, and Institute of Radiation Medicine, Seoul National University Medical Research Center, 101 Daehak-ro, Jongno-gu, Seoul, 03080, Republic of Korea.
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, 08826, Republic of Korea.
Eur Radiol. 2021 Jul;31(7):5139-5147. doi: 10.1007/s00330-020-07537-7. Epub 2021 Jan 7.
To compare the image quality between the vendor-agnostic and vendor-specific algorithms on ultralow-dose chest CT.
Vendor-agnostic deep learning post-processing model (DLM), vendor-specific deep learning image reconstruction (DLIR, high level), and adaptive statistical iterative reconstruction (ASiR, 70%) algorithms were employed. One hundred consecutive ultralow-dose noncontrast CT scans (CTDI; mean, 0.33 ± 0.056 mGy) were reconstructed with five algorithms: DLM-stnd (standard kernel), DLM-shrp (sharp kernel), DLIR, ASiR-stnd, and ASiR-shrp. Three thoracic radiologists blinded to the reconstruction algorithms reviewed five sets of 100 images and assessed subjective noise, spatial resolution, distortion artifact, and overall image quality. They selected the most preferred algorithm among five image sets for each case. Image noise and signal-to-noise ratio were measured. Edge-rise-distance was measured at a pulmonary vessel, i.e., the distance between two points where attenuation was 10% and 90% of maximal intravascular intensity. The skewness of attenuation was calculated in homogeneous areas.
DLM-stnd, followed by DLIR, showed the best subjective noise on both lung and mediastinal windows, while DLIR yielded the least measured noise (ps < .0001). Compared to DLM-stnd, DLIR showed inferior subjective spatial resolution on lung window and higher edge-rise-distance (ps < .0001). Additionally, DLIR showed the most frequent distortion artifacts and deviated skewness (ps < .0001). DLM-stnd scored the best overall image quality, followed by DLM-shrp and DLIR (mean score 3.89 ± 0.19, 3.68 ± 0.24, and 3.53 ± 0.33; ps < .001). Two among three readers preferred DLM-stnd on both windows.
Although DLIR provided the best quantitative noise profile, DLM-stnd showed the best overall image quality with fewer artifacts and was preferred by two among three readers.
• A vendor-agnostic deep learning post-processing algorithm applied to ultralow-dose chest CT exhibited the best image quality compared to vendor-specific deep learning algorithm and ASiR techniques. • Two out of three readers preferred a vendor-agnostic deep learning post-processing algorithm in comparison to vendor-specific deep learning algorithm and ASiR techniques. • A vendor-specific deep learning reconstruction algorithm yielded the least image noise, but showed significantly more frequent specific distortion artifacts and increased skewness of attenuation compared to a vendor-agnostic algorithm.
比较超低位剂量胸部 CT 中与供应商无关和与供应商相关算法的图像质量。
使用与供应商无关的深度学习后处理模型（DLM）、与供应商相关的深度学习图像重建（DLIR，高级）和自适应统计迭代重建（ASiR，70%）算法。对 100 例连续的超低剂量非对比 CT 扫描（CTDI；均值，0.33±0.056 mGy）进行了 5 种算法的重建：DLM-stnd（标准核）、DLM-shrp（锐化核）、DLIR、ASiR-stnd 和 ASiR-shrp。3 名胸部放射科医生对重建算法不知情，对 5 组 100 张图像进行了评估，评估了主观噪声、空间分辨率、失真伪影和整体图像质量。他们为每个病例从 5 个图像集中选择了最满意的算法。测量图像噪声和信噪比。在肺血管处测量边缘上升距离，即衰减为最大血管内强度的 10%和 90%的两点之间的距离。在均匀区域计算衰减的偏度。
DLM-stnd 随后是 DLIR，在肺窗和纵隔窗上均显示出最佳的主观噪声，而 DLIR 产生的噪声最小（p<0.0001）。与 DLM-stnd 相比，DLIR 在肺窗上显示出较低的主观空间分辨率和较高的边缘上升距离（p<0.0001）。此外，DLIR 显示出最频繁的失真伪影和偏度偏差（p<0.0001）。DLM-stnd 的整体图像质量得分最高，其次是 DLM-shrp 和 DLIR（平均得分为 3.89±0.19、3.68±0.24 和 3.53±0.33；p<0.001）。3 名读者中有 2 名读者更喜欢在两个窗口使用 DLM-stnd。
尽管 DLIR 提供了最佳的定量噪声分布，但 DLM-stnd 具有较少的伪影，显示出最佳的整体图像质量，并且被 3 名读者中的 2 名读者所喜欢。
• 与供应商特定的深度学习算法和 ASiR 技术相比，应用于超低剂量胸部 CT 的与供应商无关的深度学习后处理算法显示出最佳的图像质量。
• 与供应商特定的深度学习算法和 ASiR 技术相比，3 名读者中有 2 名读者更喜欢与供应商无关的深度学习后处理算法。
• 与供应商无关的深度学习重建算法产生的图像噪声最小，但与供应商无关的算法相比，显示出更频繁的特定失真伪影和衰减偏度增加。
