Robust Single-Shot T<sub>2</sub> Mapping via Multiple Overlapping-Echo Acquisition and Deep Neural Network

Zhang, Jun; Wu, Jian; Chen, Shaojian; Zhang, Zhiyong; Cai, Shuhui; Cai, Congbo; Zhong, Chen

doi:10.1109/tmi.2019.2896085

Cited by 29 publications

(54 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tremendous progress in the fields of machine learning/deep learning has sparked a huge interest in applying these methods to different MRI applications including image reconstruction [68,69]. However, so far only a few applications exist that target accelerated parameter mapping directly [70][71][72][73]. While these are promising developments, there are also still unsolved questions regarding the stability of machine learning methods [74] and the risk of introducing image features that look real but are not present in the data (hallucinations) [75].…”

Section: Discussionmentioning

confidence: 99%

Physics-based reconstruction methods for magnetic resonance imaging

Wang

Tan

Scholand

et al. 2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Conventional magnetic resonance imaging (MRI) is hampered by long scan times and only qualitative image contrasts that prohibit a direct comparison between different systems. To address these limitations, model-based reconstructions explicitly model the physical laws that govern the MRI signal generation. By formulating image reconstruction as an inverse problem, quantitative maps of the underlying physical parameters can then be extracted directly from efficiently acquired k-space signals without intermediate image reconstruction—addressing both shortcomings of conventional MRI at the same time. This review will discuss basic concepts of model-based reconstructions and report on our experience in developing several model-based methods over the last decade using selected examples that are provided complete with data and code. This article is part of the theme issue ‘Synergistic tomographic image reconstruction: part 1’.

show abstract

Section: Discussionmentioning

confidence: 99%

Physics-based reconstruction methods for magnetic resonance imaging

Wang

Tan

Scholand

et al. 2021

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

show abstract

“…A large parameter space is adapted in the generation of synthesized data to cover the whole parameter space of experimental data as much as possible and make the synthesized data consistent with the experimental data. Our group has successfully realized the T 2 mapping with synthesized data 48,56 . To the best of our knowledge, this is the first study combining the PROPELLER approach with deep neural network to accelerate CEST imaging.…”

Section: Discussionmentioning

confidence: 99%

“…Our group has successfully realized the T 2 mapping with synthesized data. 48,56 To the best of our knowledge, this is the first study combining the PROPELLER approach with deep neural network to accelerate CEST imaging.…”

Section: Discussionmentioning

confidence: 99%

Fast chemical exchange saturation transfer imaging based on PROPELLER acquisition and deep neural network reconstruction

Guo

Rosenberg

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose To develop a method for fast chemical exchange saturation transfer (CEST) imaging. Methods The periodically rotated overlapping parallel lines enhanced reconstruction (PROPELLER) sampling scheme was introduced to shorten the acquisition time. Deep neural network was employed to reconstruct CEST contrast images. Numerical simulation and experiments on a creatine phantom, hen egg, and in vivo tumor rat brain were performed to test the feasibility of this method. Results The results from numerical simulation and experiments show that there is no significant difference between reference images and CEST‐PROPELLER reconstructed images under an acceleration factor of 8. Conclusion Although the deep neural network is trained entirely on synthesized data, it works well on reconstructing experimental data. The proof of concept study demonstrates that the combination of the PROPELLER sampling scheme and the deep neural network enables considerable acceleration of saturated image acquisition and may find applications in CEST MRI.

show abstract

“…The T 2 and M 0 textures of these models were randomly generated. 20,40 21 ). The SMS-OLED was simulated with MRiLab software.…”

Section: Generation Of Training Samplesmentioning

confidence: 99%

Robust Single-Shot T₂ Mapping via Multiple Overlapping-Echo Acquisition and Deep Neural Network

Cited by 29 publications

References 46 publications

Physics-based reconstruction methods for magnetic resonance imaging

Physics-based reconstruction methods for magnetic resonance imaging

Fast chemical exchange saturation transfer imaging based on PROPELLER acquisition and deep neural network reconstruction

A simultaneous multi‐slice T₂ mapping framework based on overlapping‐echo detachment planar imaging and deep learning reconstruction

Contact Info

Product

Resources

About

Robust Single-Shot T2 Mapping via Multiple Overlapping-Echo Acquisition and Deep Neural Network

Cited by 29 publications

References 46 publications

Physics-based reconstruction methods for magnetic resonance imaging

Physics-based reconstruction methods for magnetic resonance imaging

Fast chemical exchange saturation transfer imaging based on PROPELLER acquisition and deep neural network reconstruction

A simultaneous multi‐slice T2 mapping framework based on overlapping‐echo detachment planar imaging and deep learning reconstruction

Contact Info

Product

Resources

About

Robust Single-Shot T₂ Mapping via Multiple Overlapping-Echo Acquisition and Deep Neural Network

A simultaneous multi‐slice T₂ mapping framework based on overlapping‐echo detachment planar imaging and deep learning reconstruction