Back to all papers

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.

August 29, 2026pubmed logopapers

Authors

Ren Z,Wang T,Shen L,Zhang M,Han D,Yu N,Ren Z

Affiliations (4)

  • Affiliated Hospital of Shaanxi University of Chinese Medicine, Weiyang western road-2#, 712000, Xianyang, Shaanxi, China.
  • Shaanxi Fashion Engineering University, No.1 of Tongwen Road, Fengxi New City of Xixian New Area, 712046, Xi'an, Shaanxi, China.
  • Shaanxi University of Chinese Medicine, Xixian Avenue of Xixian New Area, 712000, Xi'an, Shaanxi, China.
  • Affiliated Hospital of Shaanxi University of Chinese Medicine, Weiyang western road-2#, 712000, Xianyang, Shaanxi, China. [email protected].

Abstract

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). 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. 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. Combining DLIR‑H with VMIs, especially 40 keV, in DECTPA leads to reduced contrast and radiation doses while improving image quality.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.