DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwang, Hye Jeon | ko |
dc.contributor.author | Kim, Hyunjong | ko |
dc.contributor.author | Seo, Joon Beom | ko |
dc.contributor.author | Ye, Jong Chul | ko |
dc.contributor.author | Oh, Gyutaek | ko |
dc.contributor.author | Lee, Sang Min | ko |
dc.contributor.author | Jang, Ryoungwoo | ko |
dc.contributor.author | Yun, Jihye | ko |
dc.contributor.author | Kim, Namkug | ko |
dc.contributor.author | Park, Hee Jun | ko |
dc.contributor.author | Lee, Ho Yun | ko |
dc.contributor.author | Yoon, Soon Ho | ko |
dc.contributor.author | Shin, Kyung Eun | ko |
dc.contributor.author | Lee, Jae Wook | ko |
dc.contributor.author | Kwon, Woocheol | ko |
dc.contributor.author | Sun, Joo Sung | ko |
dc.contributor.author | You, Seulgi | ko |
dc.contributor.author | Chung, Myung Hee | ko |
dc.contributor.author | Gil, Bo Mi | ko |
dc.contributor.author | Lim, Jae-Kwang | ko |
dc.contributor.author | Lee, Youkyung | ko |
dc.contributor.author | Hong, Su Jin | ko |
dc.contributor.author | Choi, Yo Won | ko |
dc.date.accessioned | 2023-11-25T08:00:55Z | - |
dc.date.available | 2023-11-25T08:00:55Z | - |
dc.date.created | 2023-11-25 | - |
dc.date.created | 2023-11-25 | - |
dc.date.issued | 2023-08 | - |
dc.identifier.citation | KOREAN JOURNAL OF RADIOLOGY, v.24, no.8, pp.807 - 820 | - |
dc.identifier.issn | 1229-6929 | - |
dc.identifier.uri | http://hdl.handle.net/10203/315161 | - |
dc.description.abstract | Objective: To assess whether computed tomography (CT) conversion across different scan parameters and manufacturers using a routable generative adversarial network (RouteGAN) can improve the accuracy and variability in quantifying interstitial lung disease (ILD) using a deep learning-based automated software. Materials and Methods: This study included patients with ILD who underwent thin-section CT. Unmatched CT images obtained using scanners from four manufacturers (vendors A-D), standard- or low-radiation doses, and sharp or medium kernels were classified into groups 1–7 according to acquisition conditions. CT images in groups 2–7 were converted into the target CT style (Group 1: vendor A, standard dose, and sharp kernel) using a RouteGAN. ILD was quantified on original and converted CT images using a deep learning-based software (Aview, Coreline Soft). The accuracy of quantification was analyzed using the dice similarity coefficient (DSC) and pixel-wise overlap accuracy metrics against manual quantification by a radiologist. Five radiologists evaluated quantification accuracy using a 10-point visual scoring system. Results: Three hundred and fifty CT slices from 150 patients (mean age: 67.6 ± 10.7 years; 56 females) were included. The overlap accuracies for quantifying total abnormalities in groups 2–7 improved after CT conversion (original vs. converted: 0.63 vs. 0.68 for DSC, 0.66 vs. 0.70 for pixel-wise recall, and 0.68 vs. 0.73 for pixel-wise precision; P < 0.002 for all). The DSCs of fibrosis score, honeycombing, and reticulation significantly increased after CT conversion (0.32 vs. 0.64, 0.19 vs. 0.47, and 0.23 vs. 0.54, P < 0.002 for all), whereas those of ground-glass opacity, consolidation, and emphysema did not change significantly or decreased slightly. The radiologists’ scores were significantly higher (P < 0.001) and less variable on converted CT. Conclusion: CT conversion using a RouteGAN can improve the accuracy and variability of CT images obtained using different scan parameters and manufacturers in deep learning-based quantification of ILD. | - |
dc.language | English | - |
dc.publisher | KOREAN SOCIETY OF RADIOLOGY | - |
dc.title | Generative Adversarial Network-Based Image Conversion Among Different Computed Tomography Protocols and Vendors: Effects on Accuracy and Variability in Quantifying Regional Disease Patterns of Interstitial Lung Disease | - |
dc.type | Article | - |
dc.identifier.wosid | 001124224700007 | - |
dc.identifier.scopusid | 2-s2.0-85165872004 | - |
dc.type.rims | ART | - |
dc.citation.volume | 24 | - |
dc.citation.issue | 8 | - |
dc.citation.beginningpage | 807 | - |
dc.citation.endingpage | 820 | - |
dc.citation.publicationname | KOREAN JOURNAL OF RADIOLOGY | - |
dc.identifier.doi | 10.3348/kjr.2023.0088 | - |
dc.identifier.kciid | ART002981998 | - |
dc.contributor.localauthor | Ye, Jong Chul | - |
dc.contributor.nonIdAuthor | Hwang, Hye Jeon | - |
dc.contributor.nonIdAuthor | Kim, Hyunjong | - |
dc.contributor.nonIdAuthor | Seo, Joon Beom | - |
dc.contributor.nonIdAuthor | Lee, Sang Min | - |
dc.contributor.nonIdAuthor | Jang, Ryoungwoo | - |
dc.contributor.nonIdAuthor | Yun, Jihye | - |
dc.contributor.nonIdAuthor | Kim, Namkug | - |
dc.contributor.nonIdAuthor | Park, Hee Jun | - |
dc.contributor.nonIdAuthor | Lee, Ho Yun | - |
dc.contributor.nonIdAuthor | Yoon, Soon Ho | - |
dc.contributor.nonIdAuthor | Shin, Kyung Eun | - |
dc.contributor.nonIdAuthor | Lee, Jae Wook | - |
dc.contributor.nonIdAuthor | Kwon, Woocheol | - |
dc.contributor.nonIdAuthor | Sun, Joo Sung | - |
dc.contributor.nonIdAuthor | You, Seulgi | - |
dc.contributor.nonIdAuthor | Chung, Myung Hee | - |
dc.contributor.nonIdAuthor | Gil, Bo Mi | - |
dc.contributor.nonIdAuthor | Lim, Jae-Kwang | - |
dc.contributor.nonIdAuthor | Lee, Youkyung | - |
dc.contributor.nonIdAuthor | Hong, Su Jin | - |
dc.contributor.nonIdAuthor | Choi, Yo Won | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Interstitial lung disease | - |
dc.subject.keywordAuthor | Computed tomography | - |
dc.subject.keywordAuthor | Quantification | - |
dc.subject.keywordAuthor | Artificial intelligence | - |
dc.subject.keywordPlus | IDIOPATHIC PULMONARY-FIBROSIS | - |
dc.subject.keywordPlus | QUANTITATIVE CT INDEXES | - |
dc.subject.keywordPlus | HIGH-RESOLUTION CT | - |
dc.subject.keywordPlus | AUTOMATED QUANTIFICATION | - |
dc.subject.keywordPlus | PNEUMONIA | - |
dc.subject.keywordPlus | DIAGNOSIS | - |
dc.subject.keywordPlus | SURVIVAL | - |
dc.subject.keywordPlus | HRCT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.