Application value of combining"dual-low"technique with deep learning image reconstruction in coronary computed tomography angiography
TIAN Xin
ZHANG Min
PENG Hui
REN Zhanli
SHEN Li
YU Yong
YU Nan
Abstract：Objective To explore the application value of combining low tube voltage and low contrast agent dose("dual-low"technique)with a deep learning image reconstruction algorithm in coronary computed tomography angiography(CCTA).Methods A prospective study was conducted on 100 patients who underwent CCTA at the Affiliated Hospital of Shaanxi University of Chinese Medicine from June to September 2024.The patients were randomly divided into group A and group B,with 50 patients in each group.All patients were scanned using a GE Revolution APEX-CT.Group A was scanned with a tube voltage of 120 kV and a contrast agent dose of 0.8 mL/kg,while group B was scanned with a tube voltage of 70 kV and a contrast agent dose of 0.5 mL/kg.After scanning,the radiation dose was calculated for both groups.Group A utilized 50%adaptive statistical iterative reconstruction-V,while group B employed high-strength deep learning image reconstruction.CT values and noise values were measured in the aortic root,proximal left anterior descending artery,proximal left circumflex artery,proximal right coronary artery,and pericardial fat on images from both groups.The signal-to-noise ratio and contrast-to-noise ratio were calculated.Image quality was subjectively scored using a 5-point scale under a double-blind method.Results The radiation dose and contrast agent dose in group B were significantly lower than those in group A(P<0.001).The noise values in group B were lower than those in group A(P<0.05),while the CT values,signal-to-noise ratio,contrast-to-noise ratio,and subjective scores in group B were higher than those in group A(P<0.001).The subjective scores between the two physicians showed good consistency(Kappa value=0.829).Conclusion The application of the"dual-low"technique combined with high-strength deep learning reconstruction in CCTA can significantly reduce radiation dose and contrast agent dose while achieving better image quality.
Keywords：coronary CT angiography"double-low"techniquedeep learning reconstructionimage quality
Publication Date：2025-05-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 609-613 )