Improving the image quality of pediatric chest CT angiography with low radiation dose and contrast volume using deep learning image reconstruction

Background: Chest CT angiography (CTA) is a common clinical examination technique for children. Iterative reconstruction algorithms are often used to reduce image noise but encounter limitations under low dose conditions. Deep learning-based image reconstruction algorithms have been developed to overcome these limitations. We assessed the quantitative and qualitative image quality of thin-slice chest CTA in children acquired with low radiation dose and contrast volume by using a deep learning image reconstruction (DLIR) algorithm. Methods: A total of 33 children underwent chest CTA with 70 kVp and automatic tube current modulation for noise indices of 11-15 based on their age and contrast volume of 0.8-1.2 mL/kg. Images were reconstructed with 50% and 100% adaptive statistical iterative reconstruction-V ( ASIR-V) and highsetting DLIR (DLIR-H) at 0.625 mm slice thickness. Two radiologists evaluated images in consensus for overall image noise, artery margin, and artery contrast separately on a 5-point scale (5, excellent; 4, good; 3, acceptable; 2, sub-acceptable, and 1, not acceptable). The CT value and image noise of the descending aorta and back muscle were measured. Radiation dose and contrast volume was recorded. Results: The volume CT dose index, dose length product, and contrast volume were 1.37 +/- 0.29 mGy, 35.43 +/- 10.59 mGy.cm, and 25.43 +/- 13.32 mL, respectively. The image noises (in HU) of the aorta with DLIR-H ( 19.24 +/- 5.77) and 100% ASIR-V ( 20.45 +/- 6.93) were not significantly different ( P>0.05) and were substantially lower than 50% ASIR-V (29.45 +/- 7.59) (P<0.001). The 100% ASIR-V images had overs-moothed artery margins, but only the DLIR-H images provided acceptable scores on all 3 aspects of the qualitative image quality evaluation. Conclusions: It is feasible to improve the image quality of a low radiation dose and contrast volume chest CTA in children using the high-setting DLIR algorithm.