Department of Urology, Chung-Ang University Hospital, Chung-Ang University College of Medicine, Seoul 06973, Republic of Korea.
Department of Radiology, Chung-Ang University Hospital, Chung-Ang University College of Medicine, Seoul 06973, Republic of Korea.
Medicina (Kaunas). 2023 Sep 17;59(9):1677. doi: 10.3390/medicina59091677.
We attempted to determine the optimal radiation dose to maintain image quality using a deep learning application in a physical human phantom. Three 5 × 5 × 5 mm uric acid stones were placed in a physical human phantom in various locations. Three tube voltages (120, 100, and 80 kV) and four current-time products (100, 70, 30, and 15 mAs) were implemented in 12 scans. Each scan was reconstructed with filtered back projection (FBP), statistical iterative reconstruction (IR, iDose), and knowledge-based iterative model reconstruction (IMR). By applying deep learning to each image, we took 12 more scans. Objective image assessments were calculated using the standard deviation of the Hounsfield unit (HU). Subjective image assessments were performed by one radiologist and one urologist. Two radiologists assessed the subjective assessment and found the stone under the absence of information. We used this data to calculate the diagnostic accuracy. Objective image noise was decreased after applying a deep learning tool in all images of FBP, iDose, and IMR. There was no statistical difference between iDose and deep learning-applied FBP images (10.1 ± 11.9, 9.5 ± 18.5 HU, = 0.583, respectively). At a 100 kV-30 mAs setting, deep learning-applied FBP obtained a similar objective noise in approximately one third of the radiation doses compared to FBP. In radiation doses with settings lower than 100 kV-30 mAs, the subject image assessment (image quality, confidence level, and noise) showed deteriorated scores. Diagnostic accuracy was increased when the deep learning setting was lower than 100 kV-30 mAs, except for at 80 kV-15 mAs. At the setting of 100 kV-30 mAs or higher, deep learning-applied FBP did not differ in image quality compared to IR. At the setting of 100 kV-30 mAs, the radiation dose can decrease by about one third while maintaining objective noise.
我们试图在人体物理模型中使用深度学习应用来确定维持图像质量的最佳辐射剂量。 将三个 5×5×5mm 的尿酸结石分别放置在人体物理模型的不同位置。共进行了 12 次扫描，采用了 3 种管电压（120、100 和 80kV）和 4 种电流时间乘积（100、70、30 和 15mAs）。每次扫描均采用滤波反投影（FBP）、统计迭代重建（IR，iDose）和基于知识的迭代模型重建（IMR）进行重建。通过将深度学习应用于每个图像，我们又进行了 12 次扫描。通过标准偏差（HU）计算客观图像评估。由一位放射科医生和一位泌尿科医生进行主观图像评估。两位放射科医生对主观评估进行了评估，并在没有信息的情况下找到了结石。我们使用此数据计算了诊断准确性。 在所有 FBP、iDose 和 IMR 图像中应用深度学习工具后，客观图像噪声均降低。iDose 和应用深度学习的 FBP 图像之间没有统计学差异（10.1±11.9、9.5±18.5HU，=0.583）。在 100kV-30mAs 设置下，与 FBP 相比，应用深度学习的 FBP 获得了约三分之一的辐射剂量下相似的客观噪声。在低于 100kV-30mAs 的辐射剂量下，主观图像评估（图像质量、置信度和噪声）的评分恶化。当深度学习设置低于 100kV-30mAs 时，诊断准确性增加，但在 80kV-15mAs 时除外。 在 100kV-30mAs 或更高的设置下，应用深度学习的 FBP 在图像质量上与 IR 没有差异。在 100kV-30mAs 的设置下，辐射剂量可以减少约三分之一，同时保持客观噪声。
