Image Quality of 1.5 T MRI Using Dual‐Type Deep Learning Reconstruction for Pancreatic Cystic Lesions: An Exploratory Comparison With Conventional 3 T MRI Without Deep Learning Reconstruction
Masaki Tsuda,
Taiki Nozaki,
Koji Sumi,
Minobu Kamo,
Ippei Ozaki,
Fumio Morimura,
Eugene Nishi,
Yohsuke Suyama,
Hiroaki Sugiura,
Hiromi Edo Journal of Magnetic Resonance Imaging
· Wiley
· 2026-11-16
· DOI: 10.1002/jmri.70493
Аннотация
Journal of Magnetic Resonance Imaging, Volume 64, Issue 6, Page 1559-1570, December 2026.
Masaki Tsuda, Taiki Nozaki, Koji Sumi, Minobu Kamo, Ippei Ozaki, Fumio Morimura et al. Image Quality of 1.5 T MRI Using Dual‐Type Deep Learning Reconstruction for Pancreatic Cystic Lesions: An Exploratory Comparison With Conventional 3 T MRI Without Deep Learning Reconstruction. // Journal of Magnetic Resonance Imaging. – 2026. – DOI: 10.1002/jmri.70493. – URL: https://onlinelibrary.wiley.com/doi/10.1002/jmri.70493?af=R
Masaki Tsuda, Taiki Nozaki, Koji Sumi, Minobu Kamo, Ippei Ozaki, Fumio Morimura, Eugene Nishi, Yohsuke Suyama, Hiroaki Sugiura, & Hiromi Edo (2026). Image Quality of 1.5 T MRI Using Dual‐Type Deep Learning Reconstruction for Pancreatic Cystic Lesions: An Exploratory Comparison With Conventional 3 T MRI Without Deep Learning Reconstruction. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.70493
Masaki Tsuda, et al. “Image Quality of 1.5 T MRI Using Dual‐Type Deep Learning Reconstruction for Pancreatic Cystic Lesions: An Exploratory Comparison With Conventional 3 T MRI Without Deep Learning Reconstruction.” Journal of Magnetic Resonance Imaging, 2026. doi:10.1002/jmri.70493.
@article{Tsuda2026,
title = {Image Quality of 1.5 T MRI Using Dual‐Type Deep Learning Reconstruction for Pancreatic Cystic Lesions: An Exploratory Comparison With Conventional 3 T MRI Without Deep Learning Reconstruction},
author = {Tsuda, Masaki and Nozaki, Taiki and Sumi, Koji and Kamo, Minobu and Ozaki, Ippei and Morimura, Fumio and Nishi, Eugene and Suyama, Yohsuke and Sugiura, Hiroaki and Edo, Hiromi},
journal = {Journal of Magnetic Resonance Imaging},
year = {2026},
doi = {10.1002/jmri.70493},
url = {https://onlinelibrary.wiley.com/doi/10.1002/jmri.70493?af=R}
}
Purpose To develop a fast, general‐purpose framework for voxelwise noise characterization in iterative MRI reconstructions, recovering the image‐domain noise variance, the primary quantity from which SNR, ‐factor, and related...
ABSTRACT Purpose To develop a computationally viable autofocus method for estimating 3D rigid motion in MR imaging. Theory and Methods The proposed method, REACT, assumes a piecewise‐constant motion trajectory and estimates the rigid...
ABSTRACT Purpose To improve magnetic resonance fingerprinting (MRF) T 2 encoding by combining phase‐based T 2 encoding with optimal experiment design. Methods Six hundred–timepoint MRF sequences with jointly optimized flip angle (FA)...
ABSTRACT Innominate artery stenosis is an uncommon but clinically significant cause of cerebrovascular insufficiency with complex and often underrecognized hemodynamic manifestations. We present two cases highlighting the diagnostic...