Clinical feasibility of two cardiac deep learning cine magnetic resonance imaging sequences: Single-breath-hold and free-breathing motion-corrected approaches

TL;DR

This study shows that deep learning can significantly reduce MRI scan time for heart imaging without sacrificing image quality or function measurements.

Contribution

The study introduces and validates two new deep learning-based MRI techniques that drastically shorten scan times while maintaining clinical accuracy.

Findings

Single-BH DL cine reduced acquisition time by 73% compared to traditional methods.

FB-MOCO DL cine reduced acquisition time by 62% with no significant loss in image quality or cardiac function metrics.

Both DL methods showed lower edge sharpness and signal ratios compared to traditional cine sequences.

Abstract

Cine cardiovascular magnetic resonance (CMR) faces the challenges of prolonged examination times and repeated breathhold (BH). This study evaluated the clinical feasibility of deep learning (DL)-accelerated cine sequences, which shorten the acquisition time (AT) while achieving comparable image quality (IQ) and function.

This prospective study included patients who underwent 3T CMR from August 2024 to March 2025. The examination included three cine sequences (2D segmented cine, 2D single-BH DL cine, and 2D free-breathing motion-corrected DL cine [FB-MOCO DL cine]). The actual total AT (including the time for short and long-axis scans, BH instructions, and resting time between BHs) was recorded. The overall IQ, blood pool to myocardium signal ratio (BMC), edge sharpness, three-dimensional volumetric mesh contour quality, biventricular cardiac function parameters, and left ventricular (LV) strain parameters were evaluated. The Friedman test was used to compare the above parameters among the three cine sequences. Correlation analysis and Bland-Altman analysis were used to evaluate the correlation and consistency between the two cine sequences.

Eighty-six patients were evaluated (52.98 ± 14.34 years, 79% 68/86 male). Compared with segmented cine (239.70 [224.55, 260.15])s, the total AT of single-BH DL cine (63.55 [60.98, 66.00])s and FB-MOCO DL cine (90.65 [79.43, 103.80])s decreased by 73% and 62%, respectively. There were no statistically significant differences in overall IQ and biventricular functional parameters among the three cine sequences. The three-dimensional volumetric mesh contour scores of the single-BH DL cine and FB-MOCO DL cine were higher than those of the segmented cine (P<0.001 and 0.04), but the edge sharpness and BMC were lower than those of the segmented cine. The LV strain of the two fast cine sequences was lower than that of the segmented cine.

Compared with traditional segmented cine, DL-accelerated cine enables ventricular imaging in a shorter acquisition time, with preserved IQ and quantitative cardiac function results.

ga1

Figures