Training a neural network for Gibbs and noise removal in diffusion MRI.

TitleTraining a neural network for Gibbs and noise removal in diffusion MRI.
Publication TypeJournal Article
Year of Publication2021
AuthorsMuckley MJ, Ades-Aron B, Papaioannou A, Lemberskiy G, Solomon E, Lui YW, Sodickson DK, Fieremans E, Novikov DS, Knoll F
JournalMagn Reson Med
Volume85
Issue1
Pagination413-428
Date Published2021 01
ISSN1522-2594
KeywordsArtifacts, Diffusion Magnetic Resonance Imaging, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Neural Networks, Computer
Abstract

PURPOSE: To develop and evaluate a neural network-based method for Gibbs artifact and noise removal.

METHODS: A convolutional neural network (CNN) was designed for artifact removal in diffusion-weighted imaging data. Two implementations were considered: one for magnitude images and one for complex images. Both models were based on the same encoder-decoder structure and were trained by simulating MRI acquisitions on synthetic non-MRI images.

RESULTS: Both machine learning methods were able to mitigate artifacts in diffusion-weighted images and diffusion parameter maps. The CNN for complex images was also able to reduce artifacts in partial Fourier acquisitions.

CONCLUSIONS: The proposed CNNs extend the ability of artifact correction in diffusion MRI. The machine learning method described here can be applied on each imaging slice independently, allowing it to be used flexibly in clinical applications.

DOI10.1002/mrm.28395
Alternate JournalMagn Reson Med
PubMed ID32662910
PubMed Central IDPMC7722184
Grant ListP30 AG066512 / AG / NIA NIH HHS / United States
P41 EB017183 / EB / NIBIB NIH HHS / United States
R01 NS088040 / NS / NINDS NIH HHS / United States
R01 EB024532 / EB / NIBIB NIH HHS / United States
Related Institute: 
MRI Research Institute (MRIRI)

Weill Cornell Medicine
Department of Radiology
525 East 68th Street New York, NY 10065