Prediction of FDG uptake in Lung Tumors from CT Images Using Generative Adversarial Networks
Annika Liebgott, Darius Hindere, Karim Armanious, Alexander Bartler, Konstantin Nikolaou, Sergios Gatidis, Bin Yangl · 2019
In modern medicine, combined PET-CT is a commonly-used tool in clinical diagnostics, which is especially important in oncology for staging or treatment planning. Variations in FDG uptake visible in a PET image, which indicate variances in metabolic activity, are not visually recognizable within a CT scan from the same region, making both imaging modalities necessary for diagnosis and exposing the patient to a high amount of radiation. In this study, we investigate the possibility of using generative adversarial networks (GANs) to synthesize a PET image from a CT scan to predict metabolic activity.