The image quality and radiation dose of artificial intelligence-based"three low"coronary CTA
LIU Tie
CHENG Yue
YU Jing
ZHANG Xiaodong
SHEN Wen
Abstract：Objective To investigate the image quality and radiation dose of"three low"(low contrast dosage,contrast flow rate and low radiation dose)of coronary artery CTA(CCTA)based on artificial intelligence(AI)image post-processing.Methods All of 60 patients with suspected coronary artery diseases were prospectively enrolled,with a mean age of(56.3±3.9)years.All patients were randomly divide into two groups,30 patients underwent"three-low"CCTA as the study group,and 30 patients underwent routine CCTA as the control group.Image quality of the main coronary artery[left main artery(LM),left anterior descending artery(LAD),left circumflex artery(LCX),and right coronary artery(RCA)]vessel segments was subjectively scored using a Likert grading scale.Signal-to-noise ratio(SNR)and contrast-to-noise ratio(CNR)of ascending aorta(AA),LM,mid LAD(mLAD),proximal LCX(pLCX),mid RCA(mRCA),distal RCA(dRCA),right ventricle(RV)and right diaphragmatic angle region are calculated by measuring CT values,noise(SD)value of the artery lumen and its surrounding fat.Differences in general data,subjective scores and objective evaluation indices of image quality,and radiation dose between the two groups were compared using the chi-square test or independent sample t-test.Results Subjective scores of image quality in LM,LAD,LCX,RCA were not statistically different(all P>0.05).Compared with the control group,the CT value of the LM,mLAD,pLCX,mRCA,dRCA,in the study group increased significantly by 32.5%,8.6%,11.7%,11.2%,9.2%,and 2.1%,respectively.The differences in SNR and CNR between the two groups were not statistically significant(all P>0.05).The volume CT dose index(CTDIvol),dose length product(DLP),effective radiation dose(ED)of the study group was lower than that of the control group(P<0.05).Conclusion AI-based post-processing images for"three-low"CCTA ensure the quality of CCTA images,reduce radiation dose,and demonstrate good clinical feasibility for screening coronary heart disease.
Keywords：Artificial intelligenceCoronary CT angiographyCoronary artery diseaseImage quality
Publication Date：2024-03-15
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 190-194,203 )