Abstract
BackgroundGenerative adversarial network (GAN)–based synthetic images can be viable solutions to current supervised deep learning challenges. However, generating highly realistic images is a prerequisite for these approaches.ObjectiveThe aim of this study was to investigate and validate the unsupervised synthesis of highly realistic body computed tomography (CT) images by using a progressive growing GAN (PGGAN) trained to learn the probability distribution of normal data.MethodsWe trained the PGGAN by using 11,755 body CT scans. Ten radiologists (4 radiologists with <5 years of experience [Group I], 4 radiologists with 5-10 years of experience [Group II], and 2 radiologists with >10 years of experience [Group III]) evaluated the results in a binary approach by using an independent validation set of 300 images (150 real and 150 synthetic) to judge the authenticity of each image.ResultsThe mean accuracy of the 10 readers in the entire image set was higher than random guessing (1781/3000, 59.4% vs 1500/3000, 50.0%, respectively; P<.001). However, in terms of identifying synthetic images as fake, there was no significant difference in the specificity between the visual Turing test and random guessing (779/1500, 51.9% vs 750/1500, 50.0%, respectively; P=.29). The accuracy between the 3 reader groups with different experience levels was not significantly different (Group I, 696/1200, 58.0%; Group II, 726/1200, 60.5%; and Group III, 359/600, 59.8%; P=.36). Interreader agreements were poor (κ=0.11) for the entire image set. In subgroup analysis, the discrepancies between real and synthetic CT images occurred mainly in the thoracoabdominal junction and in the anatomical details.ConclusionsThe GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; however, it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details.
Highlights
Generative adversarial networks (GANs) is a recent innovative technology that generates artificial but realistic-looking images
The mean accuracy of the 10 readers in the entire image set was higher than the random guessing (1781/3000, 59.4% vs 1500/3000, 50.0%, respectively; P
In terms of identifying synthetic images as fake, there was no significant difference in the specificity between the visual Turing test and random guessing (779/1500, 51.9% vs 750/1500, 50.0%, respectively; P=.29)
Summary
Generative adversarial networks (GANs) is a recent innovative technology that generates artificial but realistic-looking images. The use of diagnostic radiological images in the public domain always raises the problem of protecting patients’ privacy [2,3,4,5] This has been a great challenge to researchers in the field of deep learning. The traditional supervised learning methods have been challenged by a lack of high-quality training data labelled by experts. Building these data requires considerable time input from experts and leads to correspondingly high costs [6]. Conclusions: The GAN can synthesize highly realistic high-resolution body CT images that are indistinguishable from real images; it has limitations in generating body images of the thoracoabdominal junction and lacks accuracy in the anatomical details
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
