Abstract
ObjectivesTo reduce the dose of intravenous iodine-based contrast media (ICM) in CT through virtual contrast-enhanced images using generative adversarial networks.MethodsDual-energy CTs in the arterial phase of 85 patients were randomly split into an 80/20 train/test collective. Four different generative adversarial networks (GANs) based on image pairs, which comprised one image with virtually reduced ICM and the original full ICM CT slice, were trained, testing two input formats (2D and 2.5D) and two reduced ICM dose levels (−50% and −80%). The amount of intravenous ICM was reduced by creating virtual non-contrast series using dual-energy and adding the corresponding percentage of the iodine map. The evaluation was based on different scores (L1 loss, SSIM, PSNR, FID), which evaluate the image quality and similarity. Additionally, a visual Turing test (VTT) with three radiologists was used to assess the similarity and pathological consistency.ResultsThe −80% models reach an SSIM of > 98%, PSNR of > 48, L1 of between 7.5 and 8, and an FID of between 1.6 and 1.7. In comparison, the −50% models reach a SSIM of > 99%, PSNR of > 51, L1 of between 6.0 and 6.1, and an FID between 0.8 and 0.95. For the crucial question of pathological consistency, only the 50% ICM reduction networks achieved 100% consistency, which is required for clinical use.ConclusionsThe required amount of ICM for CT can be reduced by 50% while maintaining image quality and diagnostic accuracy using GANs. Further phantom studies and animal experiments are required to confirm these initial results.Key Points• The amount of contrast media required for CT can be reduced by 50% using generative adversarial networks.• Not only the image quality but especially the pathological consistency must be evaluated to assess safety.• A too pronounced contrast media reduction could influence the pathological consistency in our collective at 80%.
Highlights
Computed tomographyThe use of iodine-based contrast media (ICM) is essential for dealing with various diagnostic tasks, such as the exclusion of pulmonary artery embolism or mesenteric ischemia
The amount of contrast media required for computed tomography (CT) can be reduced by 50% using generative adversarial networks
A too pronounced contrast media reduction could influence the pathological consistency in our collective at 80%
Summary
Computed tomographyThe use of iodine-based contrast media (ICM) is essential for dealing with various diagnostic tasks, such as the exclusion of pulmonary artery embolism or mesenteric ischemia. As the number of computed tomography (CT) scans continues to rise worldwide, the exposure of patients to ICM is increasing. As a result of the worldwide rise in life expectancy and the associated increase in overall morbidity and the rising prevalence of type II diabetes, the prevalence of chronic kidney disease (CKD) continues to grow [1]. It is known that the risk of developing acute kidney injury (CI-AKI) in patients with reduced renal function after exposure to intravenous ICM has been overrated in the past, the actual risk of developing CIAKI in patients with severe kidney disease remains unknown [2]. We still are increasingly faced with the challenge of making precise diagnostic statements for which we are frequently dependent on the intravenous administration of ICM and, on the other hand, we are confronted with a population with an increasing prevalence of CKD in whom the administration of intravenous ICM can potentially lead to a further deterioration in kidney function with all the consequences in terms of hospitalization, morbidity, and eventual mortality
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
