KMID : 0880420230240080807
|
|
Korean Journal of Radiology 2023 Volume.24 No. 8 p.807 ~ p.820
|
|
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 Hyun-Jong Seo Joon-Beom Ye Jong-Chul Oh Gyu-Taek Lee Sang-Min Jang Ryoung-Woo Yun Ji-Hye Kim Nam-Kug Park Hee-Jun Jinping Zhang Yoon Soon-Ho Shin Kyung-Eun Lee Jae-Wook Kwon Woo-Cheol Sun Joo-Sung You Seul-Gi Chung Myung-Hee Gil Bo-Mi Lim Jae-Kwang Lee You-Kyung Hong Su-Jin Choi Yo-Won
|
|
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 ¡¾ 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.
|
|
KEYWORD
|
|
Interstitial lung disease, Computed tomography, Quantification, Artificial intelligence
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|
|