Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI

TL;DR

PHIMO is a physics-informed deep learning method that effectively corrects motion artifacts in quantitative brain MRI, reducing scan time by over 40% while maintaining high accuracy in motion correction.

Contribution

The paper introduces PHIMO, a novel physics-informed deep learning approach that detects and excludes motion-corrupted data in MRI, significantly reducing acquisition time compared to existing methods.

Findings

PHIMO effectively detects and excludes intra-scan motion events.

PHIMO achieves comparable motion correction performance to state-of-the-art methods.

PHIMO reduces MRI acquisition time by over 40%.

Abstract

We propose PHIMO, a physics-informed learning-based motion correction method tailored to quantitative MRI. PHIMO leverages information from the signal evolution to exclude motion-corrupted k-space lines from a data-consistent reconstruction. We demonstrate the potential of PHIMO for the application of T2* quantification from gradient echo MRI, which is particularly sensitive to motion due to its sensitivity to magnetic field inhomogeneities. A state-of-the-art technique for motion correction requires redundant acquisition of the k-space center, prolonging the acquisition. We show that PHIMO can detect and exclude intra-scan motion events and, thus, correct for severe motion artifacts. PHIMO approaches the performance of the state-of-the-art motion correction method, while substantially reducing the acquisition time by over 40%, facilitating clinical applicability. Our code is available at https://github.com/HannahEichhorn/PHIMO.