Saved in:
Bibliographic Details
Main Authors: Ito, Satoshi, Sato, Yuki, Endo, Naoya, Ouchi, Shohei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.00220
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929260146458624
author Ito, Satoshi
Sato, Yuki
Endo, Naoya
Ouchi, Shohei
author_facet Ito, Satoshi
Sato, Yuki
Endo, Naoya
Ouchi, Shohei
contents Simultaneous multislice (SMS) imaging is a one of the acceleration technique of magnetic resonance imaging. SMS requires accurate sensitivity distributions in the slice plane for each receiving coil. This requirement is difficult to satisfy in practice, limiting the applications of this imaging technique. Here, images are reconstructed by applying deep learning and amplitude modulation to each slice image. Simulation experiments show that image reconstruction can be achieved for both real- and complex-valued images. Image quality tends to decrease with increasing number of simultaneously acquired images. It is also shown that a larger difference in the phase modulation coefficients between slices tends to increase the quality of the reconstructed images. Simulation experiments and initial MR imaging experiments show promising results for this method.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep-learning-based Magnetic Resonance Simultaneous Multislice Imaging Using Holographic Image Decoding
Ito, Satoshi
Sato, Yuki
Endo, Naoya
Ouchi, Shohei
Medical Physics
Simultaneous multislice (SMS) imaging is a one of the acceleration technique of magnetic resonance imaging. SMS requires accurate sensitivity distributions in the slice plane for each receiving coil. This requirement is difficult to satisfy in practice, limiting the applications of this imaging technique. Here, images are reconstructed by applying deep learning and amplitude modulation to each slice image. Simulation experiments show that image reconstruction can be achieved for both real- and complex-valued images. Image quality tends to decrease with increasing number of simultaneously acquired images. It is also shown that a larger difference in the phase modulation coefficients between slices tends to increase the quality of the reconstructed images. Simulation experiments and initial MR imaging experiments show promising results for this method.
title Deep-learning-based Magnetic Resonance Simultaneous Multislice Imaging Using Holographic Image Decoding
topic Medical Physics
url https://arxiv.org/abs/2403.00220