AUTHOR=Yi Yan , Xu Cheng , Xu Min , Yan Jing , Li Yan-Yu , Wang Jian , Yang Si-Jie , Guo Yu-Bo , Wang Yun , Li Yu-Mei , Jin Zheng-Yu , Wang Yi-Ning 

TITLE=Diagnostic Improvements of Deep Learning–Based Image Reconstruction for Assessing Calcification-Related Obstructive Coronary Artery Disease

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 8 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2021.758793

DOI=10.3389/fcvm.2021.758793

ISSN=2297-055X

ABSTRACT=Objectives: The objective of this study was to explore the diagnostic value of deep learning–based image reconstruction (DLR) and hybrid iterative reconstruction (HIR) for calcification-related obstructive coronary artery disease (CAD) evaluation by using coronary CT angiography (CCTA) images and subtraction CCTA images. 
Methods: 42 consecutive patients with known or suspected CAD who underwent coronary CTA on a 320-rows CT scanner and subsequent invasive coronary angiography (ICA), which was used as the reference standard, were enrolled. The DLR and HIR images were reconstructed as CTADLR and CTAHIR, and based on which the corresponding subtraction CCTA images were established as CTAsDLR and CTAsHIR, respectively. Qualitative and quantitative images quality comparison were performed. Diagnostic performance on lesion level was assessed and compared among the four CCTA approaches (CTADLR, CTAHIR, CTAsDLR and CTAsHIR). 
Results: There were 166 lesions of 86 vessels in 42 patients (32 men and 10 women; 62.9±9.3years) finally enrolled for analysis. The qualitative and quantitative image quality of CTAsDLR and CTADLR were superior to those of CTAsHIR and CTAHIR, respectively. The diagnostic accuracy of CTAsDLR, CTADLR, CTAsHIR and CTAHIR to identify calcification-related obstructive diameter stenosis were 83.73%, 69.28%, 75.30% and 65.66%, respectively. The false positive rate of CTAsDLR , CTADLR, CTAsHIR and CTAHIR for luminal diameter stenosis ≥50% were 15%, 31%, 24% and 34%, respectively. The sensititive and specificity to identify ≥50%  luminal diameter stenosis were 90.91% and 83.23% for CTAsDLR.
Conclusion: Our study showed that CTAsDLR has optimal image quality and diagnostic performance for calcification-related obstructive CAD evaluation, especially in reducing the false-positive rate. The deep learning–based image reconstruction combined with subtraction coronary CTA provided incremental value in calcification-related stenosis detecting.