Feasibility of reducing radiation dose and contrast dose while improving image quality in dual-energy CT pulmonary angiography : Use of low-energy virtual monochromatic images with deep learning image reconstruction algorithm.

BACKGROUND: We explored the feasibility of reducing both radiation and contrast doses while improving image quality using low-energy virtual monochromatic images (VMIs) in dual-energy computed tomography (CT) pulmonary angiography (DECTPA) with deep learning image reconstruction at a high setting (DLIR-H). MATERIALS AND METHODS: A total of 60 patients scheduled for CTPA were randomly divided into two groups: group A (n = 30) with 120 kV, contrast dose of 0.8 mL/kg, and adaptive statistical iterative reconstruction‑V (ASIR-V) at a 60% strength level, and group B (n = 30) with dual-energy CT (DECT), contrast dose of 0.6 mL/kg, and DLIR‑H at 40 keV, 50 keV, 60 keV and 70 keV VMIs. The CT and standard deviation (SD) values of the pulmonary arteries were measured to calculate the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Image quality was subjectively scored blindly by two radiologists using a five-point scale. RESULTS: There were no differences in general patient demographics between the two groups (all p > 0.05). In group B, the contrast and radiation doses decreased by 29.6% and 53.1%, respectively, compared to group A (p < 0.05). Compared to group A, group B had significantly higher CT and SNR values for the 40 keV-60 keV VMIs and higher CNR for the 40 keV-70 keV VMIs (all p < 0.05), with similar image noise at 60 keV. The two radiologists had substantial agreement in subjective scoring (kappa > 0.80). There were significantly higher scores for the 40 keV-60 keV VMIs in group B compared to group A (all p < 0.05), with the 40 keV VMIs having the highest scores. CONCLUSION: Combining DLIR‑H with VMIs, especially 40 keV, in DECTPA leads to reduced contrast and radiation doses while improving image quality.