Your browser doesn't support javascript.
loading
Preliminary application of artificial intelligence-based image optimization in coronary CT angiography / 中华放射学杂志
Chinese Journal of Radiology ; (12): 460-466, 2020.
Article in Chinese | WPRIM | ID: wpr-868299
ABSTRACT

Objective:

To investigate the benefits of artificial intelligence (AI)-based image optimization technique on image quality of coronary CT angiography (CCTA).

Methods:

Sixty patients, who were referred for CCTA, were prospectively enrolled between May and June 2018 in Peking Union Medical College Hospital and were randomly divided into two groups. Group A was scanned with a low tube voltage of 80 kVp and a reduced contrast media volume of lopamiro at 0.7 ml /kg and group B was scanned with a standard 120 kVp tube voltage and an injection of 70 ml lopamiro. According to the different reconstruction methods, group A was divided into two subgroups. The images of group A1 were reconstructed with iterative reconstruction (IR). IR and further AI-based image optimization were used in group A2. Group B was also reconstructed by IR. To evaluate image quality objectively, the mean attenuation of contrast-enhancement values, background noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured and calculated in the region of interests (ROIs) of the aortic root (Ao), left main coronary artery (LM), left anterior descending branch (LAD), left circumflex branch (LCX) and right coronary artery (RCA), respectively. In addition, the subjective evaluation was performed by two radiologists using Likert 4 scale (1 for excellent and 4 for poor) to evaluate the image quality of coronary artery branches and segments. The estimated radiation dose in terms of volume CT dose index (CTDI vol), dose length product (DLP) and effective dose (ED) was recorded and compared between group A and group B. Analyses of the differences between groups were compared with image quality, radiation dose by t test or Wilcoxon signed ranks test, and subjective assessments were compares with χ 2 test.

Results:

In terms of lumen enhancement, compared to group A2, there was no significant difference in CT value of each ROI ( P>0.05); CT value of group A1 and group A2 at Ao was significantly higher than that of group B ( P<0.01), but there was no significant difference in other ROI ( P>0.05). By comparing noise, SNR and CNR, it could be seen that compared to group B, A2 group optimized by AI had a significantly lower noise level at Ao than group B ( P<0.001), and there was no statistical difference in ROI for the rest (all P>0.05).SNR at Ao was significantly higher than that of group B ( P<0.001), and there was no statistical difference in ROI for the rest ( P>0.05).However, the CNR of group A2 was significantly higher than that of group B in all ROI ( P<0.001). Compared to the AI-optimized A2 group, the noise of A2 group was significantly lower than that of A1 group at all ROI, and SNR and CNR were significantly higher than that of A1 group ( P<0.001). The subjective evaluation results of coronary segments showed that image quality of group A2 and group B was significantly better than that of group A1 ( P=0.002,0.038). There was no significant difference between group A2 and group B ( P=0.543). The radiation dose indexes of CTDI vol, DLP and ED in group A were significantly lower than those in group B (all P<0.001). The ED was decreased by 70.4%. Meanwhile, the volume of contrast media in group A was reduced by 37.1% than that that in group B.

Conclusion:

Compared to conventional scanning, CCTA images optimized by AI technology improved subjective and objective image quality.
Full text: Available Index: WPRIM (Western Pacific) Language: Chinese Journal: Chinese Journal of Radiology Year: 2020 Type: Article

Similar

MEDLINE

...
LILACS

LIS

Full text: Available Index: WPRIM (Western Pacific) Language: Chinese Journal: Chinese Journal of Radiology Year: 2020 Type: Article