Physics-driven synthetic data learning for biomedical magnetic resonance: The imaging physics-based data synthesis paradigm for artificial intelligence

Q Yang, Z Wang, K Guo, C Cai… - IEEE Signal Processing …, 2023 - ieeexplore.ieee.org
Deep learning (DL) has driven innovation in the field of computational imaging. One of its
bottlenecks is unavailable or insufficient training data. This article reviews an emerging …

Review and prospect: deep learning in nuclear magnetic resonance spectroscopy

D Chen, Z Wang, D Guo, V Orekhov… - Chemistry–A European …, 2020 - Wiley Online Library
Since the concept of deep learning (DL) was formally proposed in 2006, it has had a major
impact on academic research and industry. Nowadays, DL provides an unprecedented way …

Accelerated MR spectroscopic imaging—a review of current and emerging techniques

W Bogner, R Otazo, A Henning - NMR in Biomedicine, 2021 - Wiley Online Library
Over more than 30 years in vivo MR spectroscopic imaging (MRSI) has undergone an
enormous evolution from theoretical concepts in the early 1980s to the robust imaging …

DeepSENSE: Learning coil sensitivity functions for SENSE reconstruction using deep learning

X Peng, BP Sutton, F Lam… - Magnetic resonance in …, 2022 - Wiley Online Library
Purpose To improve the estimation of coil sensitivity functions from limited auto‐calibration
signals (ACS) in SENSE‐based reconstruction for brain imaging. Methods We propose to …

Quantification of MR spectra by deep learning in an idealized setting: Investigation of forms of input, network architectures, optimization by ensembles of networks, and …

R Rizzo, M Dziadosz, SP Kyathanahally… - Magnetic resonance …, 2023 - Wiley Online Library
Purpose The aims of this work are (1) to explore deep learning (DL) architectures,
spectroscopic input types, and learning designs toward optimal quantification in MR …

Denoising single MR spectra by deep learning: Miracle or mirage?

M Dziadosz, R Rizzo… - Magnetic resonance in …, 2023 - Wiley Online Library
Purpose The inherently poor SNR of MRS measurements presents a significant hurdle to its
clinical application. Denoising by machine or deep learning (DL) was proposed as a …

Model‐informed unsupervised deep learning approaches to frequency and phase correction of MRS signals

A Shamaei, J Starcukova, I Pavlova… - Magnetic Resonance …, 2023 - Wiley Online Library
Purpose A supervised deep learning (DL) approach for frequency and phase correction
(FPC) of MRS data recently showed encouraging results, but obtaining transients with labels …

[HTML][HTML] Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data

A Shamaei, J Starcukova, Z Starcuk Jr - Computers in Biology and Medicine, 2023 - Elsevier
Purpose While the recommended analysis method for magnetic resonance spectroscopy
data is linear combination model (LCM) fitting, the supervised deep learning (DL) approach …

Machine learning-enabled high-resolution dynamic deuterium MR spectroscopic imaging

Y Li, Y Zhao, R Guo, T Wang, Y Zhang… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
Deuterium magnetic resonance spectroscopic imaging (DMRSI) has recently been
recognized as a potentially powerful tool for noninvasive imaging of brain energy …

Deep tomographic image reconstruction: yesterday, today, and tomorrow—editorial for the 2nd special issue “Machine Learning for Image Reconstruction”

G Wang, M Jacob, X Mou, Y Shi… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
As a follow-up to the first IEEE Transactions on Medical Imaging (TMI) special issue on the
theme of deep tomographic reconstruction, the second special issue is assembled to reflect …