Quantitative Evaluation of Enhanced Multi-plane Clinical Fetal Diffusion MRI with a Crossing-Fiber Phantom

Kebiri, Hamza; Lajous, Hélène; Alemán‐Gómez, Yasser; Girard, Gabriel; Canales-Rodríguez, Erick Jorge; Tourbier, Sébastien; Pizzolato, Marco; Ledoux, Jean‐Baptiste; Fornari, Eleonora; Jakab, András; Cuadra, Meritxell Bach

doi:10.1007/978-3-030-87615-9_2

Cited by 2 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the limited scanning time to minimize maternal discomfort hampers the acquisition of several orthogonal series, resulting in a trade-off between the number of gradient directions and orthogonal series. Thus, DW-MRI fetal brain protocols are not standardized from one center to another ( Supplementary Table S1 ) and more experiments have to be conducted in this area to design optimal sequences ( 22 , 23 ). Sequence-based super-resolution methods that were applied in adult brains ( 24 – 27 ) could also be explored and adapted to fetal brains such as in Ning et al ( 24 ) that acquire same orientation shifted low-resolution images in the slice encoding direction and in a non-overlapping gradient scheme to reconstruct one high-resolution volume using compressed sensing.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Through-plane super-resolution with autoencoders in diffusion magnetic resonance imaging of the developing human brain

Kebiri

Canales‐Rodríguez

Lajous

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Fetal brain diffusion magnetic resonance images 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 to enhance the through-plane 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 on the estimated diffusion tensor maps. A byproduct of our autoencoder was its ability to act as a denoiser. The network was able to generalize to fetal data with different levels of motion and we qualitatively showed its consistency, hence supporting the relevance of pre-term datasets to improve the processing of fetal brain images.

show abstract

Quantitative Evaluation of Enhanced Multi-plane Clinical Fetal Diffusion MRI with a Crossing-Fiber Phantom

Cited by 2 publications

References 32 publications

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

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

Through-plane super-resolution with autoencoders in diffusion magnetic resonance imaging of the developing human brain

Contact Info

Product

Resources

About