Deep learning super-resolution reconstruction of low-resolution cine images decreased acquisition times by 42% (57.5 vs 98.7 seconds) compared to standard resolution without affecting volumetric results or image quality.
Cross-Sectional (n=30)
Single-blind
No
Does low-resolution bSSFP cine CMR reconstructed with a deep learning super-resolution algorithm reduce acquisition times without affecting volumetric results or image quality compared to standard-resolution bSSFP cine CMR?
Deep-learning super-resolution reconstruction of low-resolution cine CMR images significantly reduces acquisition times by up to 42% while preserving diagnostic image quality and volumetric accuracy.
Absolute Event Rate: 57.5% vs 98.7%
p-value: p=<0.0001
Abstract Objectives To compare standard-resolution balanced steady-state free precession (bSSFP) cine images with cine images acquired at low resolution but reconstructed with a deep learning (DL) super-resolution algorithm. Materials and methods Cine cardiovascular magnetic resonance (CMR) datasets (short-axis and 4-chamber views) were prospectively acquired in healthy volunteers and patients at normal (cine NR : 1.89 × 1.96 mm 2 , reconstructed at 1.04 × 1.04 mm 2 ) and at a low-resolution (2.98 × 3.00 mm 2 , reconstructed at 1.04 × 1.04 mm 2 ). Low-resolution images were reconstructed using compressed sensing DL denoising and resolution upscaling (cine DL ). Left ventricular ejection fraction (LVEF), end-diastolic volume index (LVEDVi), and strain were assessed. Apparent signal-to-noise (aSNR) and contrast-to-noise ratios (aCNR) were calculated. Subjective image quality was assessed on a 5-point Likert scale. Student’s paired t -test, Wilcoxon matched-pairs signed-rank-test, and intraclass correlation coefficient (ICC) were used for statistical analysis. Results Thirty participants were analyzed (37 ± 16 years; 20 healthy volunteers and 10 patients). Short-axis views whole-stack acquisition duration of cine DL was shorter than cine NR (57.5 ± 8.7 vs 98.7 ± 12.4 s; p < 0.0001). No differences were noted for: LVEF (59 ± 7 vs 59 ± 7%; ICC: 0.95 95% confidence interval: 0.94, 0.99; p = 0.17), LVEDVi (85.0 ± 13.5 vs 84.4 ± 13.7 mL/m 2 ; ICC: 0.99 0.98, 0.99; p = 0.12), longitudinal strain (−19.5 ± 4.3 vs −19.8 ± 3.9%; ICC: 0.94 0.88, 0.97; p = 0.52), short-axis aSNR (81 ± 49 vs 69 ± 38; p = 0.32), aCNR (53 ± 31 vs 45 ± 27; p = 0.33), or subjective image quality (5.0 IQR 4.9, 5.0 vs 5.0 IQR 4.7, 5.0; p = 0.99). Conclusion Deep-learning reconstruction of cine images acquired at a lower spatial resolution led to a decrease in acquisition times of 42% with shorter breath-holds without affecting volumetric results or image quality. Key Points Question Cine CMR acquisitions are time-intensive and vulnerable to artifacts . Findings Low-resolution upscaled reconstructions using DL super-resolution decreased acquisition times by 35–42% without a significant difference in volumetric results or subjective image quality . Clinical relevance DL super-resolution reconstructions of bSSFP cine images acquired at a lower spatial resolution reduce acquisition times while preserving diagnostic accuracy, improving the clinical feasibility of cine imaging by decreasing breath hold duration . Graphical Abstract
Kravchenko et al. (Wed,) conducted a cross-sectional in Clinical indications for contrast-enhanced CMR or healthy volunteers (n=30). Deep learning super-resolution reconstruction of low-resolution bSSFP cine images vs. Standard normal-resolution bSSFP cine images was evaluated on Short-axis views whole-stack acquisition duration (seconds) (p=<0.0001). Deep learning super-resolution reconstruction of low-resolution cine images decreased acquisition times by 42% (57.5 vs 98.7 seconds) compared to standard resolution without affecting volumetric results or image quality.