Through-Plane Super-Resolution With Autoencoders in Diffusion Magnetic Resonance Imaging of the Developing Human Brain.

Details

Serval ID
serval:BIB_BD4D1BDA9F16
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Through-Plane Super-Resolution With Autoencoders in Diffusion Magnetic Resonance Imaging of the Developing Human Brain.
Journal
Frontiers in neurology
Author(s)
Kebiri H., Canales-Rodríguez E.J., Lajous H., de Dumast P., Girard G., Alemán-Gómez Y., Koob M., Jakab A., Bach Cuadra M.
ISSN
1664-2295 (Print)
ISSN-L
1664-2295
Publication state
Published
Issued date
2022
Peer-reviewed
Oui
Volume
13
Pages
827816
Language
english
Notes
Publication types: Journal Article
Publication Status: epublish
Abstract
Fetal brain diffusion magnetic resonance images (MRI) are often acquired with a lower through-plane than in-plane resolution. This anisotropy is often overcome by classical upsampling methods such as linear or cubic interpolation. In this work, we employ an unsupervised learning algorithm using an autoencoder neural network for single-image through-plane super-resolution by leveraging a large amount of data. Our framework, which can also be used for slice outliers replacement, overperformed conventional interpolations quantitatively and qualitatively on pre-term newborns of the developing Human Connectome Project. The evaluation was performed on both the original diffusion-weighted signal and the estimated diffusion tensor maps. A byproduct of our autoencoder was its ability to act as a denoiser. The network was able to generalize fetal data with different levels of motions and we qualitatively showed its consistency, hence supporting the relevance of pre-term datasets to improve the processing of fetal brain images.
Keywords
autoencoders, brain, diffusion-weighted imaging, fetuses, magnetic resonance imaging (MRI), pre-term neonates, super-resolution, unsupervised learning
Pubmed
Web of science
Open Access
Yes
Funding(s)
Swiss National Science Foundation / Projects / 205321-182602
Swiss National Science Foundation / Careers / PZ00P2-185814
Swiss National Science Foundation / Programmes / 185897
Create date
26/05/2022 10:29
Last modification date
01/06/2022 6:39
Usage data