2D-MSLGE reconstructed with deep-learning noise reduction significantly reduced acquisition time compared to 2D-SSLGE (median 123 s vs 540 s, p<0.001) while maintaining similar image quality.
Observational (n=60)
Does 2D-MSLGE reconstructed with NR reduce scan time and maintain image quality compared to 2D-SSLGE reconstructed with NR in patients with non-ischemic cardiomyopathy?
2D-MSLGE with deep-learning noise reduction significantly reduces scan time while maintaining image quality and accurate LGE quantification compared to standard 2D-SSLGE in patients with non-ischemic cardiomyopathy.
Absolute Event Rate: 123% vs 540%
p-value: p=<0.001
OBJECTIVE Although two-dimensional (2D) single-segmented late gadolinium enhancement (2D-SSLGE) sequences are the gold standard for LGE acquisition, 2D multi-segmented LGE (2D-MSLGE) and artificial intelligence reconstruction deep-learning noise reduction (NR) show a potential to improve image quality and reduce scan times. Thus, this study aimed to assess the feasibility of 2D-MSLGE reconstructed with NR in patients with non-ischemic cardiomyopathy (NICM). MATERIAL AND METHODS This study prospectively enrolled 60 patients (39 men, mean age, 57.7 ± 16.5 years) with NICM. Subjective overall image quality was evaluated using a 5-point Likert scale. Artifact visibility was also scored. LGE mass was manually quantified using a semi-automated grayscale threshold with a cutoff value of 5 standard deviations. RESULTS The median actual acquisition time of 2D-MSLGE reconstructed with NR (123 s; range, 81-246) was significantly shorter than that of 2D-SSLGE reconstructed with NR (540 s; range, 420-720 s, p < 0.001). There was no significant difference in overall image quality between 2D-MSLGE reconstructed with NR and 2D-SSLGE reconstructed with NR (median, 3.0; IQR, 3.0-3.0 vs. 3.0; IQR, 3.0-4.0, p = 0.197). Image noise was significantly reduced in 2D-MSLGE reconstructed with NR (3.0; 3.0-4.0) compared with that in 2D-SSLGE reconstructed with NR (3.0; 2.0-4.0, p = 0.026). No significant difference was found in the LGE mass between 2D-MSLGE reconstructed with NR (16.9%; 10.9-25.1) and 2D-SSLGE reconstructed with NR (17.3%; 11.4-27.0, p = 0.939). CONCLUSIONS 2D-MSLGE images reconstructed with NR could be acquired at shorter scan times and provide accurate LGE in patients with NICM.
Orii et al. (Mon,) conducted a observational in non-ischemic cardiomyopathy (n=60). 2D multi-segmented late gadolinium enhancement (2D-MSLGE) with noise reduction vs. 2D single-segmented late gadolinium enhancement (2D-SSLGE) with noise reduction was evaluated on actual acquisition time (seconds) (p=<0.001). 2D-MSLGE reconstructed with deep-learning noise reduction significantly reduced acquisition time compared to 2D-SSLGE (median 123 s vs 540 s, p<0.001) while maintaining similar image quality.