Search

Objectives: The aim of this study was to assess the effect of a deep learning (DL)–based reconstruction algorithm on late gadolinium enhancement (LGE) image quality and to evaluate its influence on scar quantification. Methods: Sixty patients (46 ± 17 years, 50% male) with suspected or known cardiomyopathy underwent CMR. Short-axis LGE images were reconstructed using the conventional reconstruction and a DL network (DLRecon) with tunable noise reduction (NR) levels from 0 to 100%. Image quality of standard LGE images and DLRecon images with 75% NR was scored using a 5-point scale (poor to excellent). In 30 patients with LGE, scar size was quantified using thresholding techniques with different standard deviations (SD) above remote myocardium, and using full width at half maximum (FWHM) technique in images with varying NR levels. Results: DLRecon images were of higher quality than standard LGE images (subjective quality score 3.3 ± 0.5 vs. 3.6 ± 0.7, p < 0.001). Scar size increased with increasing NR levels using the SD methods. With 100% NR level, scar size increased 36%, 87%, and 138% using 2SD, 4SD, and 6SD quantification method, respectively, compared to standard LGE images (all p values < 0.001). However, with the FWHM method, no differences in scar size were found (p = 0.06). Conclusions: LGE image quality improved significantly using a DL-based reconstruction algorithm. However, this algorithm has an important impact on scar quantification depending on which quantification technique is used. The FWHM method is preferred because of its independency of NR. Clinicians should be aware of this impact on scar quantification, as DL-based reconstruction algorithms are being used. Key Points: • The image quality based on (subjective) visual assessment and image sharpness of late gadolinium enhancement images improved significantly using a deep learning–based reconstruction algorithm that aims to reconstruct high signal-to-noise images using a denoising technique. • Spe

Objective: To determine the potential impact of on-site CT-derived fractional flow reserve (CT-FFR) on the diagnostic efficiency and effectiveness of coronary CT angiography (CCTA) in patients with obstructive coronary artery disease (CAD) on CCTA. Methods: This observational cohort study included patients with suspected CAD who had been randomized to cardiac CT in the CRESCENT I and II trials. On-site CT-FFR was blindly performed in all patients with at least one ≥ 50% stenosis on CCTA and no exclusion criteria for CT-FFR. We retrospectively assessed the effect of adding CT-FFR to the CT protocol in patients with a stenosis ≥ 50% on CCTA in terms of diagnostic effectiveness, i.e., the number of additional tests required to determine the final diagnosis, reclassification of the initial management strategy, and invasive coronary angiography (ICA) efficiency, i.e., ICA rate without ≥ 50% CAD. Results: Fifty-three patients out of the 372 patients (14%) had at least one ≥ 50% stenosis on CCTA of whom 42/53 patients (79%) had no exclusion criteria for CT-FFR. CT-FFR showed a hemodynamically significant stenosis (≤ 0.80) in 27/53 patients (51%). The availability of CT-FFR would have reduced the number of patients requiring additional testing by 57%-points compared with CCTA alone (37/53 vs. 7/53, p < 0.001). The initial management strategy would have changed for 30 patients (57%, p < 0.001). Reserving ICA for patients with a CT-FFR ≤ 0.80 would have reduced the number of ICA following CCTA by 13%-points (p = 0.016). Conclusion: Implementation of on-site CT-FFR may change management and improve diagnostic efficiency and effectiveness in patients with obstructive CAD on CCTA. Key Points: • The availability of on-site CT-FFR in the diagnostic evaluation of patients with obstructive CAD on CCTA would have significantly reduced the number of patients requiring additional testing compared with CCTA alone. • The implementation of on-site CT-FFR would have changed the initial man