DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, Yoseob | ko |
dc.contributor.author | Ye, Jong Chul | ko |
dc.date.accessioned | 2018-07-24T01:38:19Z | - |
dc.date.available | 2018-07-24T01:38:19Z | - |
dc.date.created | 2018-06-25 | - |
dc.date.created | 2018-06-25 | - |
dc.date.created | 2018-06-25 | - |
dc.date.created | 2018-06-25 | - |
dc.date.issued | 2018-06 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON MEDICAL IMAGING, v.37, no.6, pp.1418 - 1429 | - |
dc.identifier.issn | 0278-0062 | - |
dc.identifier.uri | http://hdl.handle.net/10203/243705 | - |
dc.description.abstract | X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using large receptive field neural networks such as U-Net have demonstrated impressive performance for sparse-view CT reconstruction. However, theoretical justification is still lacking. Inspired by the recent theory of deep convolutional framelets, themain goal of this paper is, therefore, to reveal the limitation of U-Net and propose new multi-resolution deep learning schemes. In particular, we show that the alternative U-Net variants such as dual frame and tight frame U-Nets satisfy the so-called frame condition which makes them better for effective recovery of high frequency edges in sparse-view CT. Using extensive experiments with real patient data set, we demonstrate that the new network architectures provide better reconstruction performance. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | LOW-DOSE CT | - |
dc.subject | HANKEL MATRIX ALOHA | - |
dc.subject | NEURAL-NETWORK | - |
dc.subject | IMAGE-RECONSTRUCTION | - |
dc.subject | PENALTY | - |
dc.title | Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT | - |
dc.type | Article | - |
dc.identifier.wosid | 000434302700012 | - |
dc.identifier.scopusid | 2-s2.0-85045199120 | - |
dc.type.rims | ART | - |
dc.citation.volume | 37 | - |
dc.citation.issue | 6 | - |
dc.citation.beginningpage | 1418 | - |
dc.citation.endingpage | 1429 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON MEDICAL IMAGING | - |
dc.identifier.doi | 10.1109/TMI.2018.2823768 | - |
dc.contributor.localauthor | Ye, Jong Chul | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep learning | - |
dc.subject.keywordAuthor | U-Net | - |
dc.subject.keywordAuthor | convolutional neural network (CNN) | - |
dc.subject.keywordAuthor | convolution framelets | - |
dc.subject.keywordAuthor | frame condition | - |
dc.subject.keywordPlus | LOW-DOSE CT | - |
dc.subject.keywordPlus | HANKEL MATRIX ALOHA | - |
dc.subject.keywordPlus | NEURAL-NETWORK | - |
dc.subject.keywordPlus | IMAGE-RECONSTRUCTION | - |
dc.subject.keywordPlus | PENALTY | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.