Johannes Haubold1, René Hosch2,3, Lale Umutlu2, Axel Wetter2, Patrizia Haubold4, Alexander Radbruch5, Michael Forsting2, Felix Nensa2,3, Sven Koitka2,3. 1. Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany. Johannes.haubold@uk-essen.de. 2. Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany. 3. Institute for Artificial Intelligence in Medicine, University Hospital Essen, Essen, Germany. 4. Department of Diagnostic and Interventional Radiology, Kliniken Essen-Mitte, Essen, Germany. 5. Department of Neuroradiology, University Hospital Bonn, Bonn, Germany.
Abstract
OBJECTIVES: To reduce the dose of intravenous iodine-based contrast media (ICM) in CT through virtual contrast-enhanced images using generative adversarial networks. METHODS: Dual-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. RESULTS: The -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. CONCLUSIONS: The 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%.
OBJECTIVES: To reduce the dose of intravenous iodine-based contrast media (ICM) in CT through virtual contrast-enhanced images using generative adversarial networks. METHODS: Dual-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. RESULTS: The -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. CONCLUSIONS: The 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%.
Authors: Thorsten R C Johnson; Bernhard Krauss; Martin Sedlmair; Michael Grasruck; Herbert Bruder; Dominik Morhard; Christian Fink; Sabine Weckbach; Miriam Lenhard; Bernhard Schmidt; Thomas Flohr; Maximilian F Reiser; Christoph R Becker Journal: Eur Radiol Date: 2006-12-07 Impact factor: 5.315
Authors: Eric A Finkelstein; Olga A Khavjou; Hope Thompson; Justin G Trogdon; Liping Pan; Bettylou Sherry; William Dietz Journal: Am J Prev Med Date: 2012-06 Impact factor: 5.043
Authors: Saravanabavaan Suntharalingam; Christian Mikat; Elena Stenzel; Youssef Erfanian; Axel Wetter; Thomas Schlosser; Michael Forsting; Kai Nassenstein Journal: PLoS One Date: 2017-10-18 Impact factor: 3.240
Authors: Melissa M Chen; Admir Terzic; Anton S Becker; Jason M Johnson; Carol C Wu; Max Wintermark; Christoph Wald; Jia Wu Journal: Eur J Radiol Open Date: 2022-09-29