Show simple item record

dc.contributor.author
Tezcan, Kerem C.
dc.contributor.author
Baumgartner, Christian F.
dc.contributor.author
Luechinger, Roger
dc.contributor.author
Prüssmann, Klaas P.
dc.contributor.author
Konukoglu, Ender
dc.date.accessioned
2019-08-19T16:11:43Z
dc.date.available
2019-01-14T16:11:29Z
dc.date.available
2019-01-15T06:44:33Z
dc.date.available
2019-01-31T09:40:15Z
dc.date.available
2019-08-19T16:11:43Z
dc.date.issued
2019-07
dc.identifier.issn
0278-0062
dc.identifier.issn
1558-254X
dc.identifier.other
10.1109/tmi.2018.2887072
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/315674
dc.identifier.doi
10.3929/ethz-b-000315674
dc.description.abstract
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data. Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstruction. Leveraging this, recent methods employed DL to learn mappings from undersampled to fully sampled images using paired datasets, including undersampled and corresponding fully sampled images, integrating prior knowledge implicitly. In this article, we propose an alternative approach that learns the probability distribution of fully sampled MR images using unsupervised DL, specifically Variational Autoencoders (VAE), and use this as an explicit prior term in reconstruction, completely decoupling the encoding operation from the prior. The resulting reconstruction algorithm enjoys a powerful image prior to compensate for missing k-space data without requiring paired datasets for training nor being prone to associated sensitivities, such as deviations in undersampling patterns used in training and test time or coil settings. We evaluated the proposed method with T1 weighted images from a publicly available dataset, multicoil complex images acquired from healthy volunteers (N=8) and images with white matter lesions. The proposed algorithm, using the VAE prior, produced visually high quality reconstructions and achieved low RMSE values, outperforming most of the alternative methods on the same dataset. On multi-coil complex data, the algorithm yielded accurate magnitude and phase reconstruction results. In the experiments on images with white matter lesions, the method faithfully reconstructed the lesions.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
IEEE
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
MR imaging
en_US
dc.subject
image reconstruction
en_US
dc.subject
machine learning
en_US
dc.subject
unsupervised learning
en_US
dc.title
MR image reconstruction using deep density priors
en_US
dc.type
Journal Article
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2018-12-17
ethz.journal.title
IEEE Transactions on Medical Imaging
ethz.journal.volume
38
en_US
ethz.journal.issue
7
en_US
ethz.journal.abbreviated
IEEE trans. med. imag.
ethz.pages.start
1633
en_US
ethz.pages.end
1642
en_US
ethz.size
10 p.
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.grant
Improving Priors towards Automated Prescreening of Brain Magnetic Resonance Images
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09579 - Konukoglu, Ender / Konukoglu, Ender
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02631 - Institut für Biomedizinische Technik / Institute for Biomedical Engineering::03628 - Prüssmann, Klaas P. / Prüssmann, Klaas P.
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02652 - Institut für Bildverarbeitung / Computer Vision Laboratory::09579 - Konukoglu, Ender / Konukoglu, Ender
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02631 - Institut für Biomedizinische Technik / Institute for Biomedical Engineering::03628 - Prüssmann, Klaas P. / Prüssmann, Klaas P.
ethz.grant.agreementno
173016
ethz.grant.fundername
SNF
ethz.grant.funderDoi
10.13039/501100001711
ethz.grant.program
Projekte MINT
ethz.relation.isNewVersionOf
handle/20.500.11850/236287
ethz.date.deposited
2019-01-14T16:11:43Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2019-08-19T16:12:25Z
ethz.rosetta.lastUpdated
2022-03-28T23:30:42Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=MR%20image%20reconstruction%20using%20deep%20density%20priors&rft.jtitle=IEEE%20Transactions%20on%20Medical%20Imaging&rft.date=2019-07&rft.volume=38&rft.issue=7&rft.spage=1633&rft.epage=1642&rft.issn=0278-0062&1558-254X&rft.au=Tezcan,%20Kerem%20C.&Baumgartner,%20Christian%20F.&Luechinger,%20Roger&Pr%C3%BCssmann,%20Klaas%20P.&Konukoglu,%20Ender&rft.genre=article&rft_id=info:doi/10.1109/tmi.2018.2887072&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record