SuCor: Susceptibility Distortion Correction via Parameter-Free and Self-Regularized Optimal Transport
This work addresses distortion correction in MRI imaging for medical and research applications, presenting an incremental improvement over existing methods like FSL TOPUP.
The paper tackles susceptibility-induced geometric distortions in echo planar imaging by proposing SuCor, a method using optimal transport for distortion correction, which achieves a mean volumetric mutual information of 0.341 with a T1 reference image, outperforming FSL TOPUP at 0.317 and running in about 12 seconds on a single CPU core.
We present SuCor, a method for correcting susceptibility induced geometric distortions in echo planar imaging (EPI) using optimal transport (OT) along the phase encoding direction. Given a pair of reversed phase encoding EPI volumes, we model each column of the distortion field as a Wasserstein-2 barycentric displacement between the opposing-polarity intensity profiles. Regularization is performed in the spectral domain using a bending-energy penalty whose strength is selected automatically via the Morozov discrepancy principle, requiring no manual tuning. On a human connectome project (HCP) dataset with left-right/right-left b0 EPI pairs and a co-registered T1 structural reference, SuCor achieves a mean volumetric mutual information of 0.341 with the T1 image, compared to 0.317 for FSL TOPUP, while running in approximately 12 seconds on a single CPU core.