Cited 7 times in
Wavelet subband-specific learning for low-dose computed tomography denoising
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김진성 | - |
dc.date.accessioned | 2023-03-21T07:27:14Z | - |
dc.date.available | 2023-03-21T07:27:14Z | - |
dc.date.issued | 2022-09 | - |
dc.identifier.uri | https://ir.ymlib.yonsei.ac.kr/handle/22282913/193385 | - |
dc.description.abstract | Deep neural networks have shown great improvements in low-dose computed tomography (CT) denoising. Early algorithms were primarily optimized to obtain an accurate image with low distortion between the denoised image and reference full-dose image at the cost of yielding an overly smoothed unrealistic CT image. Recent research has sought to preserve the fine details of denoised images with high perceptual quality, which has been accompanied by a decrease in objective quality due to a trade-off between perceptual quality and distortion. We pursue a network that can generate accurate and realistic CT images with high objective and perceptual quality within one network, achieving a better perception-distortion trade-off. To achieve this goal, we propose a stationary wavelet transform-assisted network employing the characteristics of high- and low-frequency domains of the wavelet transform and frequency subband-specific losses defined in the wavelet domain. We first introduce a stationary wavelet transform for the network training procedure. Then, we train the network using objective loss functions defined for high- and low-frequency domains to enhance the objective quality of the denoised CT image. With this network design, we train the network again after replacing the objective loss functions with perceptual loss functions in high- and low-frequency domains. As a result, we acquired denoised CT images with high perceptual quality using this strategy while minimizing the objective quality loss. We evaluated our algorithms on the phantom and clinical images, and the quantitative and qualitative results indicate that ours outperform the existing state-of-the-art algorithms in terms of objective and perceptual quality. | - |
dc.description.statementOfResponsibility | open | - |
dc.format | application/pdf | - |
dc.language | English | - |
dc.publisher | Public Library of Science | - |
dc.relation.isPartOf | PLOS ONE | - |
dc.rights | CC BY-NC-ND 2.0 KR | - |
dc.subject.MESH | Algorithms | - |
dc.subject.MESH | Image Processing, Computer-Assisted / methods | - |
dc.subject.MESH | Neural Networks, Computer* | - |
dc.subject.MESH | Radiation Dosage | - |
dc.subject.MESH | Signal-To-Noise Ratio | - |
dc.subject.MESH | Tomography, X-Ray Computed* / methods | - |
dc.subject.MESH | Wavelet Analysis | - |
dc.title | Wavelet subband-specific learning for low-dose computed tomography denoising | - |
dc.type | Article | - |
dc.contributor.college | College of Medicine (의과대학) | - |
dc.contributor.department | Dept. of Radiation Oncology (방사선종양학교실) | - |
dc.contributor.googleauthor | Wonjin Kim | - |
dc.contributor.googleauthor | Jaayeon Lee | - |
dc.contributor.googleauthor | Mihyun Kang | - |
dc.contributor.googleauthor | Jin Sung Kim | - |
dc.contributor.googleauthor | Jang-Hwan Choi | - |
dc.identifier.doi | 10.1371/journal.pone.0274308 | - |
dc.contributor.localId | A04548 | - |
dc.relation.journalcode | J02540 | - |
dc.identifier.eissn | 1932-6203 | - |
dc.identifier.pmid | 36084002 | - |
dc.contributor.alternativeName | Kim, Jinsung | - |
dc.contributor.affiliatedAuthor | 김진성 | - |
dc.citation.volume | 17 | - |
dc.citation.number | 9 | - |
dc.citation.startPage | e0274308 | - |
dc.identifier.bibliographicCitation | PLOS ONE, Vol.17(9) : e0274308, 2022-09 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.