Show simple item record

dc.contributor.authorLiu, Xinwen
dc.contributor.authorWang, Jing
dc.contributor.authorSun, Hongfu
dc.contributor.authorChandra, Shekhar S
dc.contributor.authorCrozier, Stuart
dc.contributor.authorLiu, Feng
dc.date.accessioned2021-01-14T03:35:45Z
dc.date.available2021-01-14T03:35:45Z
dc.date.issued2021
dc.identifier.issn0730-725X
dc.identifier.doi10.1016/j.mri.2020.12.019
dc.identifier.urihttp://hdl.handle.net/10072/401058
dc.description.abstractMulti-contrast (MC) Magnetic Resonance Imaging (MRI) of the same patient usually requires long scanning times, despite the images sharing redundant information. In this work, we propose a new iterative network that utilizes the sharable information among MC images for MRI acceleration. The proposed network has reinforced data fidelity control and anatomy guidance through an iterative optimization procedure of Gradient Descent, leading to reduced uncertainties and improved reconstruction results. Through a convolutional network, the new method incorporates a learnable regularization unit that is capable of extracting, fusing, and mapping shareable information among different contrasts. Specifically, a dilated inception block is proposed to promote multi-scale feature extractions and increase the receptive field diversity for contextual information incorporation. Lastly, an optimal MC information feeding protocol is built through the design of a complementary feature extractor block. Comprehensive experiments demonstrated the superiority of the proposed network, both qualitatively and quantitatively.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherElsevier
dc.relation.ispartofpagefrom159
dc.relation.ispartofpageto168
dc.relation.ispartofjournalMagnetic Resonance Imaging
dc.relation.ispartofvolume77
dc.subject.fieldofresearchBiomedical Engineering
dc.subject.fieldofresearchClinical Sciences
dc.subject.fieldofresearchCognitive Sciences
dc.subject.fieldofresearchcode0903
dc.subject.fieldofresearchcode1103
dc.subject.fieldofresearchcode1702
dc.subject.keywordsDeep learning
dc.subject.keywordsImage reconstruction
dc.subject.keywordsMagnetic resonance imaging (MRI)
dc.subject.keywordsMulti-contrast
dc.titleOn the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationLiu, X; Wang, J; Sun, H; Chandra, SS; Crozier, S; Liu, F, On the regularization of feature fusion and mapping for fast MR multi-contrast imaging via iterative networks, Magnetic Resonance Imaging, 2021, 77 pp. 159-168
dcterms.dateAccepted2020-12-29
dc.date.updated2021-01-14T03:32:15Z
gro.description.notepublicThis publication has been entered as an advanced online version in Griffith Research Online.
gro.hasfulltextNo Full Text
gro.griffith.authorWang, Jing


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record