Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Holder Codeibi 8JMKD3MGPEW34M/46T9EHH
Identifier8JMKD3MGPEW34M/3U2NAAP
Repositorysid.inpe.br/sibgrapi/2019/09.10.14.50
Last Update2019:09.10.14.50.51 (UTC) administrator
Metadata Repositorysid.inpe.br/sibgrapi/2019/09.10.14.50.51
Metadata Last Update2022:06.14.00.09.36 (UTC) administrator
DOI10.1109/SIBGRAPI.2019.00042
Citation KeySouzaFray:2019:HyFrDe
TitleA Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstruction
FormatOn-line
Year2019
Access Date2024, Apr. 27
Number of Files1
Size3643 KiB
2. Context
Author1 Souza, Roberto
2 Frayne, Richard
Affiliation1 University of Calgary
2 University of Calgary
EditorOliveira, Luciano Rebouças de
Sarder, Pinaki
Lage, Marcos
Sadlo, Filip
e-Mail Addressroberto.medeirosdeso@ucalgary.ca
Conference NameConference on Graphics, Patterns and Images, 32 (SIBGRAPI)
Conference LocationRio de Janeiro, RJ, Brazil
Date28-31 Oct. 2019
PublisherIEEE Computer Society
Publisher CityLos Alamitos
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2019-09-10 14:50:51 :: roberto.medeirosdeso@ucalgary.ca -> administrator ::
2022-06-14 00:09:36 :: administrator -> roberto.medeirosdeso@ucalgary.ca :: 2019
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Version Typefinaldraft
Keywordscompressed sensing
MRI reconstruction
AbstractDecreasing magnetic resonance (MR) image acquisition times can potentially make MR examinations more accessible. Compressed sensing (CS)-based image reconstruction methods decrease MR acquisition time by reconstructing high-quality images from data that were originally sampled at rates inferior to the Nyquist-Shannon sampling theorem. Deep-learning methods have been used to solve the CS MR reconstruction problem. These proposed methods are able to quickly reconstruct images in a single pass using an appropriately trained network. A variety of different network architectures (e.g., U-nets and Residual U-nets) have been proposed to tackle the CS reconstruction problem. A drawback of these architectures is that they typically only work on image domain data. For undersampled data, the images computed by applying the inverse Fast Fourier Transform (iFFT) are aliased. In this work we propose a hybrid architecture, termed W-net, that works both in the k-space (or frequency-domain) and the image (or spatial) domains. Our network is composed of a complex-valued residual U-net in the k-space domain, an iFFT operation, and a real-valued Unet in the image domain. Our experiments demonstrated, using MR raw k-space data, that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the image domain. In this study we compare our method with four previously published deep neural networks and examine their ability to reconstruct images that are subsequently used to generate regional volume estimates. Our technique was ranked second in the quantitative analysis, but qualitative analysis indicated that our reconstruction performed the best in hard to reconstruct regions, such as the cerebellum. All images reconstructed with our method were successfully post-processed, and showed good volumetry agreement compared with the fully sampled reconstruction measures.
Arrangement 1urlib.net > SDLA > Fonds > SIBGRAPI 2019 > A Hybrid Frequency-domain/Image-domain...
Arrangement 2urlib.net > SDLA > Fonds > Full Index > A Hybrid Frequency-domain/Image-domain...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 10/09/2019 11:50 1.2 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/3U2NAAP
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/3U2NAAP
Languageen
Target FileSIBGRAPI_A_Hybrid_Frequency_domain_Image_domain_Deep_Network_for_Magnetic_Resonance_Image_Reconstruction.pdf
User Grouproberto.medeirosdeso@ucalgary.ca
Visibilityshown
Update Permissionnot transferred
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/3UA4FNL
8JMKD3MGPEW34M/3UA4FPS
8JMKD3MGPEW34M/4742MCS
Citing Item Listsid.inpe.br/sibgrapi/2019/10.25.18.30.33 1
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination edition electronicmailaddress group isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url volume
7. Description control
e-Mail (login)roberto.medeirosdeso@ucalgary.ca
update 


Close