Feasibility of Free-breathing Deep Learning-reconstructed Single-Shot Cine MRI in Participants with Arrhythmia: Comparison with Conventional Segmented Cine MRI.

AI-CS single-shot cine had better image quality compared with bSSFP cine, particularly in participants with arrhythmia.

• European Cardiovascular Magnetic Resonance Registry score: 0.32 ± 0.68 for bSSFP cine vs 0.05 ± 0.22 for AI-CS single-shot cine (P < .001) in arrhythmia participants
• AI-CS showed fewer mistrigger events and cardiac motion artifacts compared to bSSFP
• Study included 25 healthy volunteers (mean age 37.88 ± 16.76 years; 18 female) and 45 participants with suspected arrhythmia (mean age 53.21 ± 15.45 years; 20 female)
• Imaging was performed on a 1.5-T scanner between September 1, 2023, and September 28, 2024

Scan time was significantly reduced with AI-CS single-shot cine compared to conventional bSSFP cine.

• AI-CS scan time: 10 seconds ± 2 vs bSSFP scan time: 132 seconds ± 8 (P < .001)
• AI-CS is a free-breathing sequence while bSSFP is a segmented (breath-held) sequence
• This represents an approximately 13-fold reduction in scan time

AI-CS showed good to excellent agreement with bSSFP for biventricular volume and LV mass measurements.

• LV volumetric parameters measured included LV end-diastolic volume, end-systolic volume, stroke volume, ejection fraction, and mass
• Strain parameters measured included peak strain in radial, longitudinal, and circumferential directions and time to peak strain SD
• Agreement was characterized as 'good to excellent' for biventricular volume and LV mass measurements
• Comparisons were made using Wilcoxon signed rank tests

In cases where bSSFP failed, AI-CS provided ejection fraction values comparable to those obtained by echocardiography.

• AI-CS ejection fraction: 37.50% ± 5.28 vs echocardiography ejection fraction: 31.70% ± 6.43
• z = -1.864; P = .06, indicating no statistically significant difference between AI-CS and echocardiography measurements
• This finding specifically applied to cases in which bSSFP cine failed to provide adequate imaging

The study prospectively recruited participants including those with suspected arrhythmias to undergo both bSSFP and AI-CS single-shot short-axis cine imaging.

• Recruitment period: September 1, 2023, to September 28, 2024
• Both sequences were performed on all participants on a 1.5-T scanner
• AI-CS uses retrospective ECG gating combined with deep learning-enhanced compressed sensing
• Short-axis cine imaging was the primary acquisition plane for both sequences