This study’s aim was to assess whether deep learning image reconstruction (DLIR) techniques are non-inferior to ASIR-V for the clinical task of pulmonary nodule detection in chest computed tomography. Up to 6 (range 3–6, mean 4.2) artificial lung nodules (diameter: 3, 5, 8 mm; density: −800, −630, +100 HU) were inserted at different locations in the Kyoto Kagaku Lungman phantom. In total, 16 configurations (10 abnormal, 6 normal) were scanned at 7.6, 3, 1.6 and 0.38 mGy CTDIvol (respectively 0, 60, 80 and 95% dose reduction). Images were reconstructed using 50% ASIR-V and a deep learning-based algorithm with low (DL-L), medium (DL-M) and high (DL-H) strength. Four chest radiologists evaluated 256 series by locating and scoring nodules on a five-point scale. No statistically significant difference was found among the reconstruction algorithms (p = 0.987, average across readers AUC: 0.555, 0.561, 0.557, 0.558 for ASIR-V, DL-L, DL-M, DL-H).

中文翻译：

---

使用基于深度学习的重建算法在胸部 CT 中检测肺结节

本研究的目的是评估深度学习图像重建 (DLIR) 技术在胸部计算机断层扫描中肺结节检测的临床任务中是否不劣于 ASIR-V。多达 6 个（范围 3-6，平均 4.2）人工肺结节（直径：3、5、8 mm；密度：-800、-630、+100 HU）被插入到京都 Kagaku Lungman 模型的不同位置。总共在 7.6、3、1.6 和 0.38 mGy CTDIvol（分别减少 0、60、80 和 95% 剂量）下扫描了 16 种配置（10 种异常，6 种正常）。使用 50% ASIR-V 和具有低 (DL-L)、中 (DL-M) 和高 (DL-H) 强度的基于深度学习的算法重建图像。四位胸部放射科医师通过在五点量表上定位和评分结节来评估 256 个系列。