Comparison of Improved Unidirectional Dual Velocity-Encoding MRI Methods

Background In phase-contrast (PC) MRI, several dual velocity encoding methods have been proposed to robustly increase velocity-to-noise ratio (VNR), including a standard dual-VENC (SDV), an optimal dual-VENC (ODV), and bi- and triconditional methods. Purpose To develop a correction method for the ODV approach and to perform a comparison between methods. Study Type Case-control study. Population Twenty-six volunteers. Field Strength/Sequence 1.5 T phase-contrast MRI with VENCs of 50, 75, and 150 cm/second. Assessment Since we acquired single-VENC protocols, we used the background phase from high-VENC (VENCH) to reconstruct the low-VENC (VENCL) phase. We implemented and compared the unwrapping methods for different noise levels and also developed a correction of the ODV method. Statistical Tests Shapiro-Wilk's normality test, two-way analysis of variance with homogeneity of variances was performed using Levene's test, and the significance level was adjusted by Tukey's multiple post hoc analysis with Bonferroni (P < 0.05). Results Statistical analysis revealed no extreme outliers, normally distributed residuals, and homogeneous variances. We found statistically significant interaction between noise levels and the unwrapping methods. This implies that the number of non-unwrapped pixels increased with the noise level. We found that for beta = VENCL/VENCH = 1/2, unwrapping methods were more robust to noise. The post hoc test showed a significant difference between the ODV corrected and the other methods, offering the best results regarding the number of unwrapped pixels. Data Conclusions All methods performed similarly without noise, but the ODV corrected method was more robust to noise at the price of a higher computational time. Level of Evidence 4 Technical Efficacy Stage 1

Automated summary

This study developed a correction method for the ODV approach and compared it with other methods. Statistical analysis showed significant differences in the impact of unwrapping methods on noise levels, with unwrapping methods being more robust to noise for beta = VENCL/VENCH = 1/2. The ODV corrected method performed better in terms of noise robustness but had a longer computational time.