There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 3348 | - |
dc.citation.number | 12 | - |
dc.citation.startPage | 3337 | - |
dc.citation.title | IEEE TRANSACTIONS ON MEDICAL IMAGING | - |
dc.citation.volume | 40 | - |
dc.contributor.author | Yoo, Jaejun | - |
dc.contributor.author | Jin, Kyong Hwan | - |
dc.contributor.author | Gupta, Harshit | - |
dc.contributor.author | Yerly, Jerome | - |
dc.contributor.author | Stuber, Matthias | - |
dc.contributor.author | Unser, Michael | - |
dc.date.accessioned | 2023-12-21T15:06:43Z | - |
dc.date.available | 2023-12-21T15:06:43Z | - |
dc.date.created | 2021-08-17 | - |
dc.date.issued | 2021-12 | - |
dc.description.abstract | We propose a novel unsupervised deep-learning-based algorithm for dynamic magnetic resonance imaging (MRI) reconstruction. Dynamic MRI requires rapid data acquisition for the study of moving organs such as the heart. We introduce a generalized version of the deep-image-prior approach, which optimizes the weights of a reconstruction network to fit a sequence of sparsely acquired dynamic MRI measurements. Our method needs neither prior training nor additional data. In particular, for cardiac images, it does not require the marking of heartbeats or the reordering of spokes. The key ingredients of our method are threefold: 1) a fixed low-dimensional manifold that encodes the temporal variations of images; 2) a network that maps the manifold into a more expressive latent space; and 3) a convolutional neural network that generates a dynamic series of MRI images from the latent variables and that favors their consistency with the measurements in k-space. Our method outperforms the state-of-the-art methods quantitatively and qualitatively in both retrospective and real fetal cardiac datasets. To the best of our knowledge, this is the first unsupervised deep-learning-based method that can reconstruct the continuous variation of dynamic MRI sequences with high spatial resolution. | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON MEDICAL IMAGING, v.40, no.12, pp.3337 - 3348 | - |
dc.identifier.doi | 10.1109/TMI.2021.3084288 | - |
dc.identifier.issn | 0278-0062 | - |
dc.identifier.scopusid | 2-s2.0-85107231796 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/53566 | - |
dc.identifier.wosid | 000724511900008 | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Time-Dependent Deep Image Prior for Dynamic MRI | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.type.docType | Article in Press | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Magnetic resonance imaging | - |
dc.subject.keywordAuthor | Manifolds | - |
dc.subject.keywordAuthor | Unsupervised learning | - |
dc.subject.keywordAuthor | unsupervised learning | - |
dc.subject.keywordAuthor | accelerated MRI | - |
dc.subject.keywordAuthor | Image reconstruction | - |
dc.subject.keywordAuthor | Imaging | - |
dc.subject.keywordAuthor | Electronics packaging | - |
dc.subject.keywordAuthor | Heuristic algorithms | - |
dc.subject.keywordPlus | Convolutional neural networks | - |
dc.subject.keywordPlus | Data acquisition | - |
dc.subject.keywordPlus | Deep learning | - |
dc.subject.keywordPlus | Learning algorithms | - |
dc.subject.keywordPlus | Dynamic magnetic resonance imaging (MRI) | - |
dc.subject.keywordPlus | High spatial resolution | - |
dc.subject.keywordPlus | Learning-based algorithms | - |
dc.subject.keywordPlus | Learning-based methods | - |
dc.subject.keywordPlus | Low-dimensional manifolds | - |
dc.subject.keywordPlus | Rapid data acquisition | - |
dc.subject.keywordPlus | Reconstruction networks | - |
dc.subject.keywordPlus | State-of-the-art methods | - |
dc.subject.keywordPlus | Magnetic resonance imaging | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.