DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luu, Huan Minh | ko |
dc.contributor.author | Kim, Dong-Hyun | ko |
dc.contributor.author | Kim, Jae-Woong | ko |
dc.contributor.author | Choi, Seung Hong | ko |
dc.contributor.author | Park, Sung-Hong | ko |
dc.date.accessioned | 2021-07-14T00:10:42Z | - |
dc.date.available | 2021-07-14T00:10:42Z | - |
dc.date.created | 2021-07-12 | - |
dc.date.issued | 2020-08-12 | - |
dc.identifier.citation | 2020 ISMRM & SMRT Virtual Conference & Exhibition, pp.3132 | - |
dc.identifier.uri | http://hdl.handle.net/10203/286679 | - |
dc.description.abstract | Quantitative magnetization transfer (qMT) imaging overcomes the drawbacks of traditional MT imaging by producing more quantitative parameters. However, data acquisition and processing can be time-consuming, which limits its usage. In this study, an artificial neural network, qMTNet, is proposed to accelerate both the acquisition and fitting of qMT data. For data acquired from both conventional and inter-slice acquisition strategies, our approach demonstrated consistent fitting results with those from a previous dictionary-driven fitting method. The network reduces the time for both data acquisition and qMT fitting by a factor of 3 and 5000 times, respectively, compared to the conventional methods. | - |
dc.language | English | - |
dc.publisher | International Society for Magnetic Resonance in Medicine | - |
dc.title | qMTNet: Accelerated Quantitative Magnetization Transfer Imaging with Neural Networks | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 3132 | - |
dc.citation.publicationname | 2020 ISMRM & SMRT Virtual Conference & Exhibition | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual | - |
dc.contributor.localauthor | Park, Sung-Hong | - |
dc.contributor.nonIdAuthor | Luu, Huan Minh | - |
dc.contributor.nonIdAuthor | Kim, Dong-Hyun | - |
dc.contributor.nonIdAuthor | Kim, Jae-Woong | - |
dc.contributor.nonIdAuthor | Choi, Seung Hong | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.