Pseudo-contrast cardiac CT angiography derived from non-contrast CT using conditional generative adversarial networks

Contrast computed tomography angiography (CTA) is utilized in wide variety of applications ranging from clinical practices to emerging technologies. However, radiation exposure, the necessity of contrast administration, as well as the overall complexity of the acquisition are major limitations. We aimed to generate pseudo-contrast CTA, utilizing a conditional generative adversarial network (cGAN). We synthesize realistic contrast CTA from a perfectly registered non-contrast thin slice computed tomography (NCCT). Our method may substitute contrast CTA with a pseudo-contrast CTA for certain clinical applications such as the assessments of cardiac anatomy.