Generative adversarial networks (GAN) in medicine are valuable techniques for augmenting unbalanced rare data, anomaly detection, and avoiding patient privacy issues. However, there were limits to generating high-quality endoscopic images with various characteristics, such as peristalsis, viewpoints, light sources, and mucous patterns. This study used the progressive growing of GAN (PGGAN) within the normal distribution dataset to confirm the ability to generate high-quality gastrointestinal images and investigated what barriers PGGAN has to generate endoscopic images. We trained the PGGAN with 107,060 gastroscopy images from 4165 normal patients to generate highly realistic 5122 pixel-sized images. For the evaluation, visual Turing tests were conducted on 100 real and 100 synthetic images to distinguish the authenticity of images by 19 endoscopists. The endoscopists were divided into three groups based on their years of clinical experience for subgroup analysis. The overall accuracy, sensitivity, and specificity of the 19 endoscopist groups were 61.3%, 70.3%, and 52.4%, respectively. The mean accuracy of the three endoscopist groups was 62.4 [Group I], 59.8 [Group II], and 59.1% [Group III], which was not considered a significant difference. There were no statistically significant differences in the location of the stomach. However, the real images with the anatomical landmark pylorus had higher detection sensitivity. The images generated by PGGAN showed highly realistic depictions that were difficult to distinguish, regardless of their expertise as endoscopists. However, it was necessary to establish GANs that could better represent the rugal folds and mucous membrane texture.
BACKGROUND An Image Turing Test on Realistic Gastroscopy Images Generated by using the Progressive Growing of Generative Adversarial Networks(PGGAN) OBJECTIVE This study aims to present a method for generating gastroscopy images using a deep learning-based progressive growing of generative adversarial networks (PGGAN) as the first step for anomaly detection. METHODS We trained the PGGAN with a total 107,060 normal gastroscopy images to generate highly realistic images 512 x 512 pixels in size. For the evaluation, image Turing tests were conducted on 200 images, including 100 real and 100 synthesized images, by 19 endoscopists. The endoscopists were divided into three groups based on their years of clinical experience (0 to 5, 5 to 10, and 10 or more). RESULTS For the image Turing test, the mean accuracy, sensitivity, and specificity of the 19 endoscopists were 61.3%, 70.3%, and 52.4%, respectively. The mean accuracy of the three endoscopist groups was 62.4 (0 to 5 yrs.), 59.8 (5 to 10 yrs.), and 59.1 % (10 or more yrs.), which was not considered a significant difference. There were no statistically significant differences in the location of the stomach. However, in sensitivity to anatomical landmarks, the sensitivity to the pylorus was higher (P = 0.002). CONCLUSIONS Images generated by PGGAN showed highly realistic depictions that were difficult to distinguish, regardless of expertise, and could be used for anomaly detection in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.