Cargando…
An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction
Recent advances in deep learning have contributed greatly to the field of parallel MR imaging, where a reduced amount of k-space data are acquired to accelerate imaging time. In our previous work, we have proposed a deep learning method to reconstruct MR images directly from k-space data acquired wi...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9572393/ https://www.ncbi.nlm.nih.gov/pubmed/36236376 http://dx.doi.org/10.3390/s22197277 |
_version_ | 1784810602693132288 |
---|---|
author | Oh, Changheun Chung, Jun-Young Han, Yeji |
author_facet | Oh, Changheun Chung, Jun-Young Han, Yeji |
author_sort | Oh, Changheun |
collection | PubMed |
description | Recent advances in deep learning have contributed greatly to the field of parallel MR imaging, where a reduced amount of k-space data are acquired to accelerate imaging time. In our previous work, we have proposed a deep learning method to reconstruct MR images directly from k-space data acquired with Cartesian trajectories. However, MRI utilizes various non-Cartesian trajectories, such as radial trajectories, with various numbers of multi-channel RF coils according to the purpose of an MRI scan. Thus, it is important for a reconstruction network to efficiently unfold aliasing artifacts due to undersampling and to combine multi-channel k-space data into single-channel data. In this work, a neural network named ‘ETER-net’ is utilized to reconstruct an MR image directly from k-space data acquired with Cartesian and non-Cartesian trajectories and multi-channel RF coils. In the proposed image reconstruction network, the domain transform network converts k-space data into a rough image, which is then refined in the following network to reconstruct a final image. We also analyze loss functions including adversarial and perceptual losses to improve the network performance. For experiments, we acquired k-space data at a 3T MRI scanner with Cartesian and radial trajectories to show the learning mechanism of the direct mapping relationship between the k-space and the corresponding image by the proposed network and to demonstrate the practical applications. According to our experiments, the proposed method showed satisfactory performance in reconstructing images from undersampled single- or multi-channel k-space data with reduced image artifacts. In conclusion, the proposed method is a deep-learning-based MR reconstruction network, which can be used as a unified solution for parallel MRI, where k-space data are acquired with various scanning trajectories. |
format | Online Article Text |
id | pubmed-9572393 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-95723932022-10-17 An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction Oh, Changheun Chung, Jun-Young Han, Yeji Sensors (Basel) Article Recent advances in deep learning have contributed greatly to the field of parallel MR imaging, where a reduced amount of k-space data are acquired to accelerate imaging time. In our previous work, we have proposed a deep learning method to reconstruct MR images directly from k-space data acquired with Cartesian trajectories. However, MRI utilizes various non-Cartesian trajectories, such as radial trajectories, with various numbers of multi-channel RF coils according to the purpose of an MRI scan. Thus, it is important for a reconstruction network to efficiently unfold aliasing artifacts due to undersampling and to combine multi-channel k-space data into single-channel data. In this work, a neural network named ‘ETER-net’ is utilized to reconstruct an MR image directly from k-space data acquired with Cartesian and non-Cartesian trajectories and multi-channel RF coils. In the proposed image reconstruction network, the domain transform network converts k-space data into a rough image, which is then refined in the following network to reconstruct a final image. We also analyze loss functions including adversarial and perceptual losses to improve the network performance. For experiments, we acquired k-space data at a 3T MRI scanner with Cartesian and radial trajectories to show the learning mechanism of the direct mapping relationship between the k-space and the corresponding image by the proposed network and to demonstrate the practical applications. According to our experiments, the proposed method showed satisfactory performance in reconstructing images from undersampled single- or multi-channel k-space data with reduced image artifacts. In conclusion, the proposed method is a deep-learning-based MR reconstruction network, which can be used as a unified solution for parallel MRI, where k-space data are acquired with various scanning trajectories. MDPI 2022-09-26 /pmc/articles/PMC9572393/ /pubmed/36236376 http://dx.doi.org/10.3390/s22197277 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Oh, Changheun Chung, Jun-Young Han, Yeji An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title | An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title_full | An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title_fullStr | An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title_full_unstemmed | An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title_short | An End-to-End Recurrent Neural Network for Radial MR Image Reconstruction |
title_sort | end-to-end recurrent neural network for radial mr image reconstruction |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9572393/ https://www.ncbi.nlm.nih.gov/pubmed/36236376 http://dx.doi.org/10.3390/s22197277 |
work_keys_str_mv | AT ohchangheun anendtoendrecurrentneuralnetworkforradialmrimagereconstruction AT chungjunyoung anendtoendrecurrentneuralnetworkforradialmrimagereconstruction AT hanyeji anendtoendrecurrentneuralnetworkforradialmrimagereconstruction AT ohchangheun endtoendrecurrentneuralnetworkforradialmrimagereconstruction AT chungjunyoung endtoendrecurrentneuralnetworkforradialmrimagereconstruction AT hanyeji endtoendrecurrentneuralnetworkforradialmrimagereconstruction |