Comparing repeatability metrics for quantitative susceptibility mapping in the head and neck

Quantitative susceptibility mapping (QSM) is a technique that has been demonstrated to be highly repeatable in the brain. As QSM is applied to other parts of the body, it is necessary to investigate metrics for quantifying repeatability, to enable optimization of repeatable QSM reconstruction pipelines beyond the brain.

MRI data were acquired in the head and neck (HN) region in ten healthy volunteers, who underwent six acquisitions across two sessions. QSMs were reconstructed using six representative state-of-the-art techniques. Repeatability of the susceptibility values was compared using voxel-wise metrics (normalized root mean squared error and XSIM) and ROI-based metrics (within-subject and between-subject standard deviation, coefficient of variation (CV), intraclass correlation coefficient (ICC)).

Both within-subject and between-subject variations were smaller than the variation between QSM dipole inversion methods, in most ROIs. autoNDI produced the most repeatable susceptibility values, with ICC > 0.75 in three of six HN ROIs with an average ICC of 0.66 across all ROIs. Joint consideration of standard deviation and ICC offered the best metric of repeatability for comparisons between QSM methods, given typical distributions of positive and negative QSM values.

Repeatability of QSM in the HN region is highly dependent on the dipole inversion method chosen, but the most repeatable methods (autoNDI, QSMnet, TFI) are only moderately repeatable in most HN ROIs.