Department of Medical Imaging, CHU Nimes, Medical Imaging Group Nimes, Univ Montpellier, EA 2415, Bd Prof Robert Debré, 30029, Nîmes Cedex 9, France.
Department of Medical Physics, CHU Nimes, Univ Montpellier, Montpellier, France.
Eur Radiol. 2020 Jul;30(7):3951-3959. doi: 10.1007/s00330-020-06724-w. Epub 2020 Feb 25.
To assess the impact on image quality and dose reduction of a new deep learning image reconstruction (DLIR) algorithm compared with a hybrid iterative reconstruction (IR) algorithm.
Data acquisitions were performed at seven dose levels (CTDI : 15/10/7.5/5/2.5/1/0.5 mGy) using a standard phantom designed for image quality assessment. Raw data were reconstructed using the filtered back projection (FBP), two levels of IR (ASiR-V50% (AV50); ASiR-V100% (AV100)), and three levels of DLIR (TrueFidelity™ low, medium, high). Noise power spectrum (NPS) and task-based transfer function (TTF) were computed. Detectability index (d') was computed to model a large mass in the liver, a small calcification, and a small subtle lesion with low contrast.
NPS peaks were higher with AV50 than with all DLIR levels and only higher with DLIR-H than with AV100. The average NPS spatial frequencies were higher with DLIR than with IR. For all DLIR levels, TTF obtained with DLIR was higher than that with IR. d' was higher with DLIR than with AV50 but lower with DLIR-L and DLIR-M than with AV100. d' values were higher with DLIR-H than with AV100 for the small low-contrast lesion (10 ± 4%) and in the same range for the other simulated lesions.
New DLIR algorithm reduced noise and improved spatial resolution and detectability without changing the noise texture. Images obtained with DLIR seem to indicate a greater potential for dose optimization than those with hybrid IR.
• This study assessed the impact on image quality and radiation dose of a new deep learning image reconstruction (DLIR) algorithm as compared with hybrid iterative reconstruction (IR) algorithm. • The new DLIR algorithm reduced noise and improved spatial resolution and detectability without perceived alteration of the texture, commonly reported with IR. • As compared with IR, DLIR seems to open further possibility of dose optimization.
评估与混合迭代重建（IR）算法相比，新的深度学习图像重建（DLIR）算法对图像质量和剂量降低的影响。
使用专为图像质量评估而设计的标准体模，在七个剂量水平（CTDI：15/10/7.5/5/2.5/1/0.5 mGy）上进行数据采集。使用滤波反投影（FBP）、两级 IR（ASiR-V50%（AV50）；ASiR-V100%（AV100））和三级 DLIR（TrueFidelity™低、中、高）重建原始数据。计算噪声功率谱（NPS）和基于任务的传递函数（TTF）。计算可检测性指数（d'）以模拟肝脏中的大肿块、小钙化和低对比度的小细微病变。
与所有 DLIR 水平相比，AV50 的 NPS 峰值更高，仅高于 DLIR-H 与 AV100。与 IR 相比，DLIR 的平均 NPS 空间频率更高。对于所有 DLIR 水平，DLIR 获得的 TTF 高于 IR。与 AV50 相比，DLIR 的 d'更高，但与 AV100 相比，DLIR-L 和 DLIR-M 的 d'更低。对于小的低对比度病变（10±4%），DLIR-H 的 d'值高于 AV100，对于其他模拟病变，d'值在相同范围内。
新的 DLIR 算法降低了噪声并提高了空间分辨率和可检测性，而不会改变噪声纹理。与混合 IR 相比，使用 DLIR 获得的图像似乎显示出更大的剂量优化潜力。
• 本研究评估了与混合迭代重建（IR）算法相比，新的深度学习图像重建（DLIR）算法对图像质量和辐射剂量的影响。
• 与 IR 相比，新的 DLIR 算法降低了噪声，提高了空间分辨率和可检测性，同时不会改变通常与 IR 相关的纹理。
• 与 IR 相比，DLIR 似乎为进一步的剂量优化提供了更多可能性。
