Cargando…

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

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Hwang, Hye Jeon, Kim, Hyunjong, Seo, Joon Beom, Ye, Jong Chul, Oh, Gyutaek, Lee, Sang Min, Jang, Ryoungwoo, Yun, Jihye, Kim, Namkug, Park, Hee Jun, Lee, Ho Yun, Yoon, Soon Ho, Shin, Kyung Eun, Lee, Jae Wook, Kwon, Woocheol, Sun, Joo Sung, You, Seulgi, Chung, Myung Hee, Gil, Bo Mi, Lim, Jae-Kwang, Lee, Youkyung, Hong, Su Jin, Choi, Yo Won
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Korean Society of Radiology 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10400368/
https://www.ncbi.nlm.nih.gov/pubmed/37500581
http://dx.doi.org/10.3348/kjr.2023.0088
_version_ 1785084429272612864
author Hwang, Hye Jeon
Kim, Hyunjong
Seo, Joon Beom
Ye, Jong Chul
Oh, Gyutaek
Lee, Sang Min
Jang, Ryoungwoo
Yun, Jihye
Kim, Namkug
Park, Hee Jun
Lee, Ho Yun
Yoon, Soon Ho
Shin, Kyung Eun
Lee, Jae Wook
Kwon, Woocheol
Sun, Joo Sung
You, Seulgi
Chung, Myung Hee
Gil, Bo Mi
Lim, Jae-Kwang
Lee, Youkyung
Hong, Su Jin
Choi, Yo Won
author_facet Hwang, Hye Jeon
Kim, Hyunjong
Seo, Joon Beom
Ye, Jong Chul
Oh, Gyutaek
Lee, Sang Min
Jang, Ryoungwoo
Yun, Jihye
Kim, Namkug
Park, Hee Jun
Lee, Ho Yun
Yoon, Soon Ho
Shin, Kyung Eun
Lee, Jae Wook
Kwon, Woocheol
Sun, Joo Sung
You, Seulgi
Chung, Myung Hee
Gil, Bo Mi
Lim, Jae-Kwang
Lee, Youkyung
Hong, Su Jin
Choi, Yo Won
author_sort Hwang, Hye Jeon
collection PubMed
description 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.
format Online
Article
Text
id pubmed-10400368
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Korean Society of Radiology
record_format MEDLINE/PubMed
spelling pubmed-104003682023-08-05 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 Hwang, Hye Jeon Kim, Hyunjong Seo, Joon Beom Ye, Jong Chul Oh, Gyutaek Lee, Sang Min Jang, Ryoungwoo Yun, Jihye Kim, Namkug Park, Hee Jun Lee, Ho Yun Yoon, Soon Ho Shin, Kyung Eun Lee, Jae Wook Kwon, Woocheol Sun, Joo Sung You, Seulgi Chung, Myung Hee Gil, Bo Mi Lim, Jae-Kwang Lee, Youkyung Hong, Su Jin Choi, Yo Won Korean J Radiol Thoracic Imaging 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. The Korean Society of Radiology 2023-08 2023-07-19 /pmc/articles/PMC10400368/ /pubmed/37500581 http://dx.doi.org/10.3348/kjr.2023.0088 Text en Copyright © 2023 The Korean Society of Radiology https://creativecommons.org/licenses/by-nc/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0 (https://creativecommons.org/licenses/by-nc/4.0/) ) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Thoracic Imaging
Hwang, Hye Jeon
Kim, Hyunjong
Seo, Joon Beom
Ye, Jong Chul
Oh, Gyutaek
Lee, Sang Min
Jang, Ryoungwoo
Yun, Jihye
Kim, Namkug
Park, Hee Jun
Lee, Ho Yun
Yoon, Soon Ho
Shin, Kyung Eun
Lee, Jae Wook
Kwon, Woocheol
Sun, Joo Sung
You, Seulgi
Chung, Myung Hee
Gil, Bo Mi
Lim, Jae-Kwang
Lee, Youkyung
Hong, Su Jin
Choi, Yo Won
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
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
title_full 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
title_fullStr 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
title_full_unstemmed 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
title_short 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
title_sort 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
topic Thoracic Imaging
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10400368/
https://www.ncbi.nlm.nih.gov/pubmed/37500581
http://dx.doi.org/10.3348/kjr.2023.0088
work_keys_str_mv AT hwanghyejeon generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT kimhyunjong generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT seojoonbeom generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT yejongchul generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT ohgyutaek generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT leesangmin generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT jangryoungwoo generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT yunjihye generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT kimnamkug generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT parkheejun generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT leehoyun generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT yoonsoonho generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT shinkyungeun generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT leejaewook generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT kwonwoocheol generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT sunjoosung generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT youseulgi generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT chungmyunghee generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT gilbomi generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT limjaekwang generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT leeyoukyung generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT hongsujin generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease
AT choiyowon generativeadversarialnetworkbasedimageconversionamongdifferentcomputedtomographyprotocolsandvendorseffectsonaccuracyandvariabilityinquantifyingregionaldiseasepatternsofinterstitiallungdisease