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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Eichhorn, Hannah, Spieker, Veronika, Hammernik, Kerstin, Saks, Elisa, Weiss, Kilian, Preibisch, Christine, Schnabel, Julia A.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910499332947968
author Eichhorn, Hannah
Spieker, Veronika
Hammernik, Kerstin
Saks, Elisa
Weiss, Kilian
Preibisch, Christine
Schnabel, Julia A.
author_facet Eichhorn, Hannah
Spieker, Veronika
Hammernik, Kerstin
Saks, Elisa
Weiss, Kilian
Preibisch, Christine
Schnabel, Julia A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_08298
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI
Eichhorn, Hannah
Spieker, Veronika
Hammernik, Kerstin
Saks, Elisa
Weiss, Kilian
Preibisch, Christine
Schnabel, Julia A.
Image and Video Processing
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.
title Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI
topic Image and Video Processing
url https://arxiv.org/abs/2403.08298