Feasibility Study of Optimizing Abdominal Contrast-enhanced Image Quality Based on Artificial Intelligence Triggering Technology
Objective To assess the feasibility of artificial intelligence triggered techniques to Optimise Abdominal Enhanced CT Image Quality.Methods A prospective study included 100 patients undergoing contrast-enhanced abdominal CT scans,who were randomly divided into two groups(Group A,Group B,each with n=50).Group A used traditional fixed-delay time bolus tracking technique,while Group B used artificial intelligence triggering technique.The remaining scanning protocols were consistent.Quantitative parameters(CT value,SD value,SNR,CNR)and qualitative parameters(overall image quality and diagnostic confidence)of the two groups of patients were compared.Results In the arterial phase,the CT values of images in Group B were higher(P＜0.05),with no significant difference in noise(P＞0.05).The SNR and CNR values in Group B were also higher,with only the aorta(pSNR=0.546;pCNR=0.114)and pancreas(pCNR=0.052)showing no statistical difference.In the venous phase,the CT values of images in Group B were higher,but only the portal vein showed a difference(P=0.025).There was no statistical difference in SD value,SNR,and CNR between the two groups(P＞0.05).There was also no statistical difference in the overall subjective image quality score(P=1.000)and diagnostic confidence(P=0.917)between the two groups.Conclusion Compared to conventional fixed-delay time bolus tracking technique,artificial intelligence triggering technique can significantly improve the objective image quality of contrast-enhanced abdominal CT scans while ensuring sufficient image quality for diagnosis.
万方数据
维普
