ACE-Net: AutofoCus-Enhanced Convolutional Network for Field Imperfection Estimation with application to high b-value spiral Diffusion MRI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Mengze, Shah, Zachary, Cao, Xiaozhi, Wang, Nan, Abraham, Daniel, Setsompop, Kawin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916492056985600
author Gao, Mengze
Shah, Zachary
Cao, Xiaozhi
Wang, Nan
Abraham, Daniel
Setsompop, Kawin
author_facet Gao, Mengze
Shah, Zachary
Cao, Xiaozhi
Wang, Nan
Abraham, Daniel
Setsompop, Kawin
contents Spatiotemporal magnetic field variations from B0-inhomogeneity and diffusion-encoding-induced eddy-currents can be detrimental to rapid image-encoding schemes such as spiral, EPI and 3D-cones, resulting in undesirable image artifacts. In this work, a data driven approach for automatic estimation of these field imperfections is developed by combining autofocus metrics with deep learning, and by leveraging a compact basis representation of the expected field imperfections. The method was applied to single-shot spiral diffusion MRI at high b-values where accurate estimation of B0 and eddy were obtained, resulting in high quality image reconstruction without need for additional external calibrations.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14630
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ACE-Net: AutofoCus-Enhanced Convolutional Network for Field Imperfection Estimation with application to high b-value spiral Diffusion MRI
Gao, Mengze
Shah, Zachary
Cao, Xiaozhi
Wang, Nan
Abraham, Daniel
Setsompop, Kawin
Medical Physics
Machine Learning
Image and Video Processing
Spatiotemporal magnetic field variations from B0-inhomogeneity and diffusion-encoding-induced eddy-currents can be detrimental to rapid image-encoding schemes such as spiral, EPI and 3D-cones, resulting in undesirable image artifacts. In this work, a data driven approach for automatic estimation of these field imperfections is developed by combining autofocus metrics with deep learning, and by leveraging a compact basis representation of the expected field imperfections. The method was applied to single-shot spiral diffusion MRI at high b-values where accurate estimation of B0 and eddy were obtained, resulting in high quality image reconstruction without need for additional external calibrations.
title ACE-Net: AutofoCus-Enhanced Convolutional Network for Field Imperfection Estimation with application to high b-value spiral Diffusion MRI
topic Medical Physics
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2411.14630