Cited 0 times in
Deep Learning Cross-Phase Style Transfer for Motion Artifact Correction in Coronary Computed Tomography Angiography
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 장혁재 | - |
dc.date.accessioned | 2021-09-29T00:24:30Z | - |
dc.date.available | 2021-09-29T00:24:30Z | - |
dc.date.issued | 2020-04 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/183814 | - |
dc.description.abstract | Motion artifacts may occur in coronary computed tomography angiography (CCTA) due to the heartbeat and impede the clinician's diagnosis of coronary arterial diseases. Thus, motion artifact correction of the coronary artery is required to quantify the risk of disease more accurately. We present a novel method based on deep learning for motion artifact correction in CCTA. Because the image of the coronary artery without motion (the ground-truth data required in supervised deep learning) is medically unattainable, we apply a style transfer method to 2D image patches cropped from full-phase 4D computed tomography (CT) to synthesize these images. We then train a convolutional neural network (CNN) for motion artifact correction using this synthetic ground-truth (SynGT). During testing, the output motion-corrected 2D image patches of the trained network are reinserted into the 3D CT volume with volumetric interpolation. The proposed method is evaluated using both phantom and clinical data. A phantom study demonstrates comparable results to other methods in quantitative performance and outperforms those methods in computation time. For clinical data, a quantitative analysis based on metric measurements is presented that confirms the correction of motion artifacts. Moreover, an observer study finds that by applying the proposed method, motion artifacts are markedly reduced, and boundaries of the coronary artery are much sharper, with a strong inter-observer agreement (κ = 0.78). Finally, evaluations using commercial software on the original and resulting CT volumes of the proposed method reveal a considerable increase in tracked coronary artery length. | - |
dc.description.statementOfResponsibility | open | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.title | Deep Learning Cross-Phase Style Transfer for Motion Artifact Correction in Coronary Computed Tomography Angiography | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Internal Medicine (내과학교실) | - |
dc.contributor.googleauthor | Sunghee Jung | - |
dc.contributor.googleauthor | Soochahn Lee | - |
dc.contributor.googleauthor | Byunghwan Jeon | - |
dc.contributor.googleauthor | Yeonggul Jang | - |
dc.contributor.googleauthor | Hyuk-Jae Chang | - |
dc.identifier.doi | 10.1109/ACCESS.2020.2991445 | - |
dc.contributor.localId | A03490 | - |
dc.relation.journalcode | J03454 | - |
dc.identifier.eissn | 2169-3536 | - |
dc.subject.keyword | Computed tomography | - |
dc.subject.keyword | deep learning | - |
dc.subject.keyword | image restoration | - |
dc.subject.keyword | motion correction and analysis | - |
dc.subject.keyword | coronary angiography | - |
dc.contributor.alternativeName | Chang, Hyuck Jae | - |
dc.contributor.affiliatedAuthor | 장혁재 | - |
dc.citation.volume | 8 | - |
dc.citation.number | 4 | - |
dc.citation.startPage | 81849 | - |
dc.citation.endPage | 81863 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, Vol.8(4) : 81849-81863, 2020-04 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.