Njølstad Tormund, Schulz Anselm, Jensen Kristin, Andersen Hilde K, Martinsen Anne Catrine T
Department of Radiology and Nuclear Medicine, Oslo University Hospital Ullevål, Oslo 0450, Norway.
Department of Radiology, Haukeland University Hospital, Bergen, Norway.
Res Diagn Interv Imaging. 2023 Jan 13;5:100022. doi: 10.1016/j.redii.2023.100022. eCollection 2023 Mar.
To assess image quality of a deep learning reconstruction (DLR) algorithm across dose levels using a semi-anthropomorphic upper-abdominal phantom, and compare with filtered back projection (FBP) and hybrid iterative reconstruction (IR).
CT scans obtained at five dose levels (CTDI 5, 10, 15, 20 and 25 mGy) were reconstructed with FBP, hybrid IR (IR50, IR70 and IR90) and DLR of low (DLL), medium (DLM) and high strength (DLH) in 0.625 mm and 2.5 mm slices. CT number, homogeneity, noise, contrast, contrast-to-noise ratio (CNR), noise texture deviation (NTD; a measure of IR-specific artifacts), noise power spectrum (NPS) and task-based transfer function (TTF) were compared between reconstruction algorithms.
CT numbers were highly consistent across reconstruction algorithms. Image noise was significantly reduced with higher levels of DLR. Noise texture (NPS and NTD) was with DLR maintained at comparable levels to FBP, contrary to increasing levels of hybrid IR. Images reconstructed with DLR of low and high strength in 0.625 mm slices showed similar noise characteristics to 2.5 mm slice FBP and IR50, respectively. Dose-reduction potential based on image noise with IR50 as reference was estimated to 35% for DLM and 74% for DLH.
The novel DLR algorithm demonstrates robust noise reduction with maintained noise texture characteristics despite higher algorithm strength, and may have overcome important limitations of IR. There may be potential for dose reduction and additional benefit from thin-slice reconstruction.
使用半人体模型上腹部模体评估深度学习重建（DLR）算法在不同剂量水平下的图像质量，并与滤波反投影（FBP）和混合迭代重建（IR）进行比较。
对在五个剂量水平（CTDI为5、10、15、20和25 mGy）下获得的CT扫描图像，分别采用FBP、混合IR（IR50、IR70和IR90）以及低强度（DLL）、中等强度（DLM）和高强度（DLH）的DLR算法，重建层厚为0.625 mm和2.5 mm的图像。比较各重建算法之间的CT值、均匀性、噪声、对比度、对比噪声比（CNR）、噪声纹理偏差（NTD；一种衡量IR特定伪影的指标）、噪声功率谱（NPS）和基于任务的传递函数（TTF）。
各重建算法的CT值高度一致。DLR强度越高，图像噪声显著降低。与混合IR强度增加相反，DLR的噪声纹理（NPS和NTD）与FBP保持在相当水平。0.625 mm层厚的低强度和高强度DLR重建图像分别显示出与2.5 mm层厚的FBP和IR50相似的噪声特征。以IR50为参考，基于图像噪声的DLM和DLH的剂量降低潜力估计分别为35%和74%。
新型DLR算法在算法强度较高的情况下仍能实现强大的降噪效果，同时保持噪声纹理特征，可能克服了IR的重要局限性。薄切片重建可能具有降低剂量的潜力和额外益处。
