A cascade of preconditioned conjugate gradient networks for accelerated magnetic resonance imaging
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Moogyeong | - |
dc.contributor.author | Chung, Wonzoo | - |
dc.date.accessioned | 2022-12-09T07:01:56Z | - |
dc.date.available | 2022-12-09T07:01:56Z | - |
dc.date.created | 2022-12-08 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.issn | 0169-2607 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/146569 | - |
dc.description.abstract | Background and objective: Recent unfolding based compressed sensing magnetic resonance imaging (CS-MRI) methods only reinterpret conventional CS-MRI optimization algorithms and, consequently, inherit the weaknesses of the alternating optimization strategy. In order to avoid the structural complexity of the alternating optimization strategy and achieve better reconstruction performance, we propose to di-rectly optimize the e 1 regularized convex optimization problem using a deep learning approach. Method: In order to achieve direct optimization, a system of equations solving the e 1 regularized optimization problem is constructed from the optimality conditions of a novel primal-dual form proposed for the ef-fective training of the sparsifying transform. The optimal solution is obtained by a cascade of unfold-ing networks of the preconditioned conjugate gradient (PCG) algorithm trained to minimize the mean element-wise absolute difference ( e 1 loss) between the terminal output and ground truth image in an end-to-end manner. The performance of the proposed method was compared with that of U-Net, PD -Net, ISTA-Net+, and the recently proposed projection-based cascaded U-Net, using single-coil knee MR images of the fastMRI dataset. Results: In our experiment, the proposed network outperformed exist-ing unfolding-based networks and the complex version of U-Net in several subsampling scenarios. In particular, when using the random Cartesian subsampling mask with 25 % sampling rate, the proposed model outperformed PD-Net by 0.76 dB, ISTA-Net+ by 0.43 dB, and U-Net by 1.21 dB on the positron density without suppression (PD) dataset in term of peak signal to noise ratio. In comparison with the projection-based cascade U-Net, the proposed algorithm achieved approximately the same performance when the sampling rate was 25 % with only 1.62 % number of network parameters at the cost of a longer reconstruction time (approximately twice). Conclusion: A cascade of unfolding networks of the PCG algo-rithm was proposed to directly optimize the e 1 regularized CS-MRI optimization problem. The proposed network achieved improved reconstruction performance compared with U-Net, PD-Net, and ISTA-Net+, and achieved approximately the same performance as the projection-based cascaded U-Net while using significantly fewer network parameters.(c) 2022 Elsevier B.V. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER IRELAND LTD | - |
dc.subject | INVERSE PROBLEMS | - |
dc.subject | MRI | - |
dc.subject | RECONSTRUCTION | - |
dc.subject | ALGORITHM | - |
dc.title | A cascade of preconditioned conjugate gradient networks for accelerated magnetic resonance imaging | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Chung, Wonzoo | - |
dc.identifier.doi | 10.1016/j.cmpb.2022.107090 | - |
dc.identifier.scopusid | 2-s2.0-85137154597 | - |
dc.identifier.wosid | 000863215400005 | - |
dc.identifier.bibliographicCitation | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, v.225 | - |
dc.relation.isPartOf | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE | - |
dc.citation.title | COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE | - |
dc.citation.volume | 225 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Medical Informatics | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Interdisciplinary Applications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Theory & Methods | - |
dc.relation.journalWebOfScienceCategory | Engineering, Biomedical | - |
dc.relation.journalWebOfScienceCategory | Medical Informatics | - |
dc.subject.keywordPlus | INVERSE PROBLEMS | - |
dc.subject.keywordPlus | MRI | - |
dc.subject.keywordPlus | RECONSTRUCTION | - |
dc.subject.keywordPlus | ALGORITHM | - |
dc.subject.keywordAuthor | Magnetic resonance imaging | - |
dc.subject.keywordAuthor | Compressed sensing | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | Primal -dual | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.