Back to Search Start Over

Deep-learning-based Magnetic Resonance Simultaneous Multislice Imaging Using Holographic Image Decoding

Authors :
Ito, Satoshi
Sato, Yuki
Endo, Naoya
Ouchi, Shohei
Publication Year :
2024

Abstract

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.

Subjects

Subjects :
Physics - Medical Physics

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2403.00220
Document Type :
Working Paper