2019
DOI: 10.1002/jmri.26871
|View full text |Cite
|
Sign up to set email alerts
|

Data‐driven self‐calibration and reconstruction for non‐cartesian wave‐encoded single‐shot fast spin echo using deep learning

Abstract: Background Current self‐calibration and reconstruction methods for wave‐encoded single‐shot fast spin echo imaging (SSFSE) requires long computational time, especially when high accuracy is needed. Purpose To develop and investigate the clinical feasibility of data‐driven self‐calibration and reconstruction of wave‐encoded SSFSE imaging for computation time reduction and quality improvement. Study Type Prospective controlled clinical trial. Subjects With Institutional Review Board approval, the proposed method… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
26
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
7

Relationship

3
4

Authors

Journals

citations
Cited by 24 publications
(26 citation statements)
references
References 26 publications
0
26
0
Order By: Relevance
“…It was observed that such phase differences can cause degradation in the reconstruction performance when compared to reconstructions that use the same set of coil sensitivities across all the contrasts. We anticipate that such behavior is specific to the VN architecture, where real and imaginary feature maps are summed after the convolutional filtering ( kt) and are not being kept as separate channels. The integration of diffusion weighted imaging (DWI) into jVN may be challenging for several reasons: DWI is typically acquired at a smaller matrix size than most structural scans which will require interpolation to match the field of view and resolution of the remaining scans.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…It was observed that such phase differences can cause degradation in the reconstruction performance when compared to reconstructions that use the same set of coil sensitivities across all the contrasts. We anticipate that such behavior is specific to the VN architecture, where real and imaginary feature maps are summed after the convolutional filtering ( kt) and are not being kept as separate channels. The integration of diffusion weighted imaging (DWI) into jVN may be challenging for several reasons: DWI is typically acquired at a smaller matrix size than most structural scans which will require interpolation to match the field of view and resolution of the remaining scans.…”
Section: Discussionmentioning
confidence: 99%
“…With this framework many existing physics‐ and CS ‐based techniques have been outperformed while enabling much shorter reconstruction times . In a recent work such a network was also utilized to reconstruct a highly accelerated Wave acquisition where imperfections of the sinusoidal Wave gradient trajectory were automatically estimated by the network without additional time‐consuming optimizations (eg AutoPSF).…”
Section: Introductionmentioning
confidence: 99%
“…While wave‐encoded SSFSE improves image sharpness and reduces scan time compared to conventional SSFSE, this comes at the cost of the increased computation time necessary for self‐calibration and reconstruction. Chen et al showed that a deep‐learning‐based pipeline of trained self‐calibration and reconstruction neural networks could decrease computation time and perceived noise for clinical abdominal non‐Cartesian wave‐encoded SSFSE imaging while maintaining image contrast and sharpness when compared to conventional self‐calibration and PI‐CS reconstruction 31 …”
Section: Deep Learning In Sparse Samplingmentioning
confidence: 99%
“…There is great interest in applying artificial intelligence to improve MRI image quality, image registration, and workflow [73,[82][83][84] all of which are active areas of investigation.…”
Section: Future Direction: Meeting Challenges Of Mri With New Technologymentioning
confidence: 99%