2021
DOI: 10.1002/mrm.29033
|View full text |Cite
|
Sign up to set email alerts
|

Partial Fourier reconstruction of complex MR images using complex‐valued convolutional neural networks

Abstract: Purpose To provide a complex‐valued deep learning approach for partial Fourier (PF) reconstruction of complex MR images. Methods Conventional PF reconstruction methods, such as projection onto convex sets (POCS), uses low‐resolution image phase information from the central symmetrically sampled k‐space for image reconstruction. However, this smooth phase constraint undermines the phase estimation accuracy in presence of rapid local phase variations, causing image artifacts and limiting the extent of PF reconst… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 14 publications
(8 citation statements)
references
References 43 publications
0
8
0
Order By: Relevance
“…Several recent works have also demonstrated the advantages and significance of building complex-valued networks for DL MR reconstruction. 35,[37][38][39] It is desirable for DL networks to be able to operate on complex-valued data. And it is worth noting that the nonlinear activation function can be complex-valued as well.…”
Section: Complex-valued Mr Imagesmentioning
confidence: 99%
“…Several recent works have also demonstrated the advantages and significance of building complex-valued networks for DL MR reconstruction. 35,[37][38][39] It is desirable for DL networks to be able to operate on complex-valued data. And it is worth noting that the nonlinear activation function can be complex-valued as well.…”
Section: Complex-valued Mr Imagesmentioning
confidence: 99%
“…With such artifact patterns embedded in training input data but not output/target data, deep learning is highly effective in learning and removing the semiglobal, physics-dictated artifacts for high-resolution MRI, as already demonstrated for high-field MRI by relatively simple convolution neural networks. 46,47 It is possible to expand our proposed model to remove other important MRI artifacts, such as partial Fourier image reconstruction artifacts, 48,49 to accelerate ULF MRI data acquisition or improve its image quality for a given scan time.…”
Section: Three-dimensional Superresolution With Noise and Artifact Su...mentioning
confidence: 99%
“…DL powers a paradigm shift and has shown promise in various high-field MR image reconstruction tasks, including artifact reduction, denoising, and reconstruction from undersampled k-space data (25)(26)(27)(28)(29)(30). This derives from the exceptional feature extraction capability of deep neural network from historical data.…”
Section: Introductionmentioning
confidence: 99%