Comparison of 1H MR Spectroscopy, 3-point DIXON, and Multi-echo Gradient Echo for Measuring Hepatic Fat Fraction

Abstract

We evaluated and compared the reproducibility, diagnostic accuracy, and sequence dependency of the fat fraction (FF) determined by 3-point Dixon (DIXON) and multi-echo gradient-echo (MEGE) methods to those of the FF determined by magnetic resonance spectroscopy (MRS). Our study included 98 volunteers, ten of whom underwent scanning twice to evaluate sequence reproducibility. We compared the FFs determined by the DIXON and MEGE methods to that by MRS as the gold standard, calculated sensitivity and specificity for each image analysis method at a threshold value of 6.25% of spectroscopic value, and used Pearson's correlation coefficient and Bland-Altman analysis to compare agreement among the repeated measurements and FF values with the 3 methods, in 98 volunteers. There was no significant difference in repeated scans in any sequence with Wilcoxon's t-test. Each correlation coefficient (r) exceeded 0.930 for the repeated measurements of all 3 sequences. Sensitivity of DIXON was 82% and specificity, 96%; sensitivity of MEGE was 70% and specificity, 99%. The FFs determined by DIXON and MEGE correlated well with that by MRS (r=0.920) but showed significant difference (paired t-test, P<0.001). The mean difference between the FF determined by DIXON and that by MEGE were 0.93 and -1.16, respectively. The slope of the regression lines as determined by DIXON was -0.655 (P<0.001) and that by MEGE was -0.527 (P<0.001). When the FF by MRS was less than 6.25%, the FF values by DIXON and MEGE were significantly higher; when the spectroscopic value was greater than 6.25%, their values were significantly lower. We demonstrated the high reproducibility of each FF measurement using MRS, DIXON, and MEGE. Compared to MRS, both DIXON and MEGE showed high sensitivity and specificity for determining FF. The FFs by DIXON and MEGE showed sequence dependency because DIXON had proportional and additional errors, and MEGE had a proportional error.