In Vitro Study of the Precision and Accuracy of Measurement of the Vascular Inner Diameter on Computed Tomography Angiography Using Deep Learning Image Reconstruction: Comparison With Filtered Back Projection and Iterative Reconstruction.

OBJECTIVE: This study aimed to compare the performance of deep learning image reconstruction (DLIR) with that of standard filtered back projection (FBP) and adaptive statistical iterative reconstruction V (ASiR-V) for measurement of the vascular diameter on computed tomography (CT) angiography model. METHODS: We used 6 vascular models of 3 wall thicknesses. We used DLIR, FBP, and ASiR-V for reconstruction, and compared the accuracy and precision of vascular diameter measurement, as well as the image noise, among the 3 reconstruction methods. RESULTS: Image noise was in the order of FBP > ASiR-V > DLIR. The vascular diameters measured using DLIR and ASiR-V were comparable with, or significantly closer to, the actual diameter than those measured using FBP. The precision of the diameter measurement using DLIR was comparable with or significantly superior to that using FBP/ASiR-V. CONCLUSIONS: Use of DLIR, as compared with FBP or ASiR-V, for image reconstruction can improve the precision and accuracy of vascular diameter measurement.

Effect of energy level on the spatial resolution and noise frequency characteristics of virtual monochromatic images: a phantom experiment using four types of CT scanners.

PURPOSE: The purpose of the study is to evaluate the effect of energy level on the modulation transfer functions (MTF) and noise power spectra (NPS) of virtual monochromatic images (VMIs) obtained using four types of computed-tomographic (CT) scanners: Revolution, SOMATOM, IQon, and Aquilion. MATERIALS AND METHODS: VMIs were obtained at 70, 60, and 50 kiloelectron volts (keV), and also at the lowest keV available in each scanner. We evaluated the MTF and NPS in the VMIs obtained at each keV. RESULTS: No significant effect of the energy level on the MTF was observed in IQon, whereas the spatial resolution decreased as the energy level decreased in the other types of scanners. The NPS curves tended to increase as the energy levels decreased with three types of scanners other than Aquilion. CONCLUSION: The spatial resolution and noise frequency characteristics of VMIs may be affected by the energy level, and the effects of energy level on these characteristics differ depending on the type of CT scanners.