Super-resolution deep learning reconstruction at coronary computed tomography angiography to evaluate the coronary arteries and in-stent lumen: An initial experience

Abstract

Abstract The present study aimed to compare the image quality of the coronary arteries and in-stent lumen between super-resolution deep learning reconstruction (SR-DLR) and model-based iterative reconstruction (MBIR). We prospectively enrolled 50 patients (median age, 68 years; interquartile range [IQR], 59–74 years; 34 men) who underwent coronary computed tomography angiography (CCTA) using a 320-detector row CT scanner between January and April 2022. The image noise in the ascending aorta, left atrium, and septal wall of the ventricle was measured, and the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in the proximal coronary arteries were calculated. Of the ten stents, stent strut thickness and luminal diameter were quantitatively evaluated. The image noise on SR-DLR was significantly lower than that on MBIR (median 22.1 HU; IQR, 19.1–24.5 HU vs. 27.4 HU; IQR, 24.1–31.1 HU, p < 0.01), whereas the SNR (median 16.3; IQR, 12.0–22.0 vs. 13.9; IQR, 9.8–19.2, p = 0.03) and CNR (median 25.2; IQR, 16.9–30.8 vs. 19.5; IQR, 14.5–23.7, p < 0.01) on SR-DLR were significantly higher than that on MBIR. Stent struts were significantly thinner (median, 0.66 mm; IQR, 0.61–0.72 mm vs. 0.80 mm; IQR, 0.68–0.86 mm, p < 0.01) and in-stent lumens were significantly larger (median, 1.82 mm; IQR, 1.57–1.95 mm vs. 1.34 mm; IQR, 1.26–1.60 mm, p < 0.01) on SR-DLR than on MBIR. This study’s initial experience with SR-DLR improves the image quality of the coronary arteries and in-stent lumen at CCTA compared with conventional MBIR.