Measuring signal-to-noise ratio in partially parallel imaging MRI

To assess five different methods of signal-to-noise ratio (SNR) measurement for partially parallel imaging (PPI) acquisitions.

Measurements were performed on a spherical phantom and three volunteers using a multichannel head coil a clinical 3T MRI system to produce echo planar, fast spin echo, gradient echo, and balanced steady state free precession image acquisitions. Two different PPI acquisitions, generalized autocalibrating partially parallel acquisition algorithm and modified sensitivity encoding with acceleration factors (R) of 2-4, were evaluated and compared to nonaccelerated acquisitions. Five standard SNR measurement techniques were investigated and Bland-Altman analysis was used to determine agreement between the various SNR methods. The estimated g-factor values, associated with each method of SNR calculation and PPI reconstruction method, were also subjected to assessments that considered the effects on SNR due to reconstruction method, phase encoding direction, and R-value.

Only two SNR measurement methods produced g-factors in agreement with theoretical expectations (g ≥ 1). Bland-Altman tests demonstrated that these two methods also gave the most similar results relative to the other three measurements. R-value was the only factor of the three we considered that showed significant influence on SNR changes.

Non-signal methods used in SNR evaluation do not produce results consistent with expectations in the investigated PPI protocols. Two of the methods studied provided the most accurate and useful results. Of these two methods, it is recommended, when evaluating PPI protocols, the image subtraction method be used for SNR calculations due to its relative accuracy and ease of implementation.