DC Field | Value | Language |
---|---|---|
dc.contributor.author | Oh, Gyutaek | ko |
dc.contributor.author | Sim, Byeongsu | ko |
dc.contributor.author | Chung, HyungJin | ko |
dc.contributor.author | Sunwoo, Leonard | ko |
dc.contributor.author | Ye, Jong Chul | ko |
dc.date.accessioned | 2020-10-08T01:55:14Z | - |
dc.date.available | 2020-10-08T01:55:14Z | - |
dc.date.created | 2020-09-21 | - |
dc.date.created | 2020-09-21 | - |
dc.date.created | 2020-09-21 | - |
dc.date.issued | 2020-08 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, v.6, pp.1285 - 1296 | - |
dc.identifier.issn | 2573-0436 | - |
dc.identifier.uri | http://hdl.handle.net/10203/276486 | - |
dc.description.abstract | Recently, deep learning approaches for accelerated MRI have been extensively studied thanks to their high performance reconstruction in spite of significantly reduced run-time complexity. These neural networks are usually trained in a supervised manner, so matched pairs of subsampled, and fully sampled k-space data are required. Unfortunately, it is often difficult to acquire matched fully sampled k-space data, since the acquisition of fully sampled k-space data requires long scan time, and often leads to the change of the acquisition protocol. Therefore, unpaired deep learning without matched label data has become a very important research topic. In this article, we propose an unpaired deep learning approach using a optimal transport driven cycle-consistent generative adversarial network (OT-cycleGAN) that employs a single pair of generator, and discriminator. The proposed OT-cycleGAN architecture is rigorously derived from a dual formulation of the optimal transport formulation using a specially designed penalized least squares cost. The experimental results show that our method can reconstruct high resolution MR images from accelerated k-space data from both single, and multiple coil acquisition, without requiring matched reference data. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Unpaired Deep Learning for Accelerated MRI Using Optimal Transport Driven CycleGAN | - |
dc.type | Article | - |
dc.identifier.wosid | 000565813700002 | - |
dc.identifier.scopusid | 2-s2.0-85091040922 | - |
dc.type.rims | ART | - |
dc.citation.volume | 6 | - |
dc.citation.beginningpage | 1285 | - |
dc.citation.endingpage | 1296 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING | - |
dc.identifier.doi | 10.1109/TCI.2020.3018562 | - |
dc.contributor.localauthor | Ye, Jong Chul | - |
dc.contributor.nonIdAuthor | Oh, Gyutaek | - |
dc.contributor.nonIdAuthor | Chung, HyungJin | - |
dc.contributor.nonIdAuthor | Sunwoo, Leonard | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Accelerated MRI | - |
dc.subject.keywordAuthor | unpaired deep learning | - |
dc.subject.keywordAuthor | cycleGAN | - |
dc.subject.keywordAuthor | optimal transport | - |
dc.subject.keywordAuthor | penalized least squares (PLS) | - |
dc.subject.keywordPlus | RECONSTRUCTION | - |
dc.subject.keywordPlus | NETWORK | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.