Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm
Noise and spatial resolution properties of a commercially available deep learning-based CT reconstruction algorithm
复制标题
DOI：
10.1002/mp.14319
复制
发表时间：
2020-07-06
期刊：
影响因子：
3.8
通讯作者：
Samei, Ehsan
中科院分区：
文献类型：
--
作者：
Solomon, Justin;Lyu, Peijei;Samei, Ehsan
目的研究一种基于深度学习的CT重建算法的噪声和空间分辨率特性。方法进行两种体模实验。第一个使用多尺寸图像质量体模(水星v3.0，杜克大学)，在五个辐射剂量水平(CTDIvol0.9、1.2、3.6、7.0和22.3mGy五个辐射剂量水平)下使用固定管电流技术在商用CT扫描仪(GE Revise CT)上成像。图像重建采用常规(FBP)、迭代(GE ASIR-V)和基于深度学习(GE True Fidelity)的重建算法。测量每个剂量水平和体模尺寸的噪声功率谱(NPS)、高对比度(空气-聚乙烯界面)和中等对比度(水-聚乙烯界面)任务传递函数(TTF)，并分别以平均噪声频率(f(Av))和TTF降至50%(f(50%))的频率来总结。第二个实验使用带有低对比度杆和肺纹理切片的定制体模来评估低对比度TTF和噪声的空间分布。模型在5个剂量水平(CTDIvol1.0、2.1、3.0、6.0和10.0mGy5个剂量水平)进行成像，每个剂量重复扫描20次，并用相同的重建算法重建图像。根据AAPM TG233方法，通过从重复图像集合生成空间噪声图并计算噪声不均匀指数ETA来评估局部噪声的平稳性。所有的测量结果都在算法中进行了比较。结果与FBP相比，ASIR-V(100%设置)和True Fidelity(高设置)的噪声幅度分别降低了74+/-6%和68+/-4%(+/-一个标准差)。ASIR-V的噪声频率含量显著低于FBP，NPS f(Av)比FBP低55+/-4%，而True Fidelity的噪声频率含量仅略有不同，NPS f(Av)比FBP低9+/-5%。在所有辐射剂量水平下，ASIR-V和True Fidelity都在肺纹理背景中显示了局部非平稳噪声，血管高对比度边缘附近的噪声较高，而均匀区域的噪声较低。在1.0mGy剂量水平下，ASIR-V和True Fidelity的ETA值分别比FBP高314%和271%。在所有剂量水平和模体大小的所有算法之间，高对比度空间分辨率相似(
Purpose To characterize the noise and spatial resolution properties of a commercially available deep learning-based computed tomography (CT) reconstruction algorithm. Methods Two phantom experiments were performed. The first used a multisized image quality phantom (Mercury v3.0, Duke University) imaged at five radiation dose levels (CTDIvol: 0.9, 1.2, 3.6, 7.0, and 22.3 mGy) with a fixed tube current technique on a commercial CT scanner (GE Revolution CT). Images were reconstructed with conventional (FBP), iterative (GE ASiR-V), and deep learning-based (GE True Fidelity) reconstruction algorithms. Noise power spectrum (NPS), high-contrast (air-polyethylene interface), and intermediate-contrast (water-polyethylene interface) task transfer functions (TTF) were measured for each dose level and phantom size and summarized in terms of average noise frequency (f(av)) and frequency at which the TTF was reduced to 50% (f(50%)), respectively. The second experiment used a custom phantom with low-contrast rods and lung texture sections for the assessment of low-contrast TTF and noise spatial distribution. The phantom was imaged at five dose levels (CTDIvol: 1.0, 2.1, 3.0, 6.0, and 10.0 mGy) with 20 repeated scans at each dose, and images reconstructed with the same reconstruction algorithms. The local noise stationarity was assessed by generating spatial noise maps from the ensemble of repeated images and computing a noise inhomogeneity index,eta, following AAPM TG233 methods. All measurements were compared among the algorithms. Results Compared to FBP, noise magnitude was reduced on average (+/- one standard deviation) by 74 +/- 6% and 68 +/- 4% for ASiR-V (at "100%" setting) and True Fidelity (at "High" setting), respectively. The noise texture from ASiR-V had substantially lower noise frequency content with 55 +/- 4% lower NPS f(av)compared to FBP while True Fidelity had only marginally different noise frequency content with 9 +/- 5% lower NPS f(av)compared to FBP. Both ASiR-V and True Fidelity demonstrated locally nonstationary noise in a lung texture background at all radiation dose levels, with higher noise near high-contrast edges of vessels and lower noise in uniform regions. At the 1.0 mGy dose level eta values were 314% and 271% higher in ASiR-V and True Fidelity compared to FBP, respectively. High-contrast spatial resolution was similar between all algorithms for all dose levels and phantom sizes (