GDCNet: Calibrationless geometric distortion correction of echo planar imaging data using deep learning

arXiv:2402.18777v1 Announce Type: cross
Abstract: Functional magnetic resonance imaging techniques benefit from echo-planar imaging's fast image acquisition but are susceptible to inhomogeneities in the main magnetic field, resulting in geometric distortion and signal loss artifacts in the images. Traditional methods leverage a field map or voxel displacement map for distortion correction. However, voxel displacement map estimation requires additional sequence acquisitions, and the accuracy of the estimation influences correction performance. This work implements a novel approach called GDCNet, which estimates a …

abstract acquisition arxiv benefit cs.cv data deep learning echo eess.iv functional image images imaging loss map signal type voxel