Deep learning corrects artifacts in RASER MRI profiles.

Autor: Becker M; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Arvidsson F; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Bertilson J; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Aslanikashvili E; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Korvink JG; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Jouda M; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany., Lehmkuhl S; Institute of Microstructure Technology, Karlsruhe Institute of Technology, Hermann-von-Helmholtz-Platz 1, Eggenstein-Leopoldshafen 76344, Germany. Electronic address: soeren.lehmkuhl@kit.edu.
Jazyk: angličtina
Zdroj: Magnetic resonance imaging [Magn Reson Imaging] 2025 Jan; Vol. 115, pp. 110247. Date of Electronic Publication: 2024 Oct 24.
DOI: 10.1016/j.mri.2024.110247
Abstrakt: A newly developed magnetic resonance imaging (MRI) approach is based on "Radiowave amplification by the stimulated emission of radiation" (RASER). RASER MRI potentially allows for higher resolution, is inherently background-free, and does not require radio-frequency excitation. However, RASER MRI can be "nearly unusable" as heavy distortions from nonlinear effects can occur. In this work, we show that deep learning (DL) reduces such artifacts in RASER images. We trained a two-step DL pipeline on purely synthetic data, which was generated based on a previously published, theoretical model for RASER MRI. A convolutional neural network was trained on 630'000 1D RASER projections, and a U-net on 2D random images. The DL pipeline generalizes well when applied from synthetic to experimental RASER MRI data.
Competing Interests: Declaration of competing interest J.G.K. is a shareholder of Voxalytic GmbH. The other authors declare no competing interests.
(Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: