Fig. 1From: Independent attenuation correction of whole body [18F]FDG-PET using a deep learning approach with Generative Adversarial NetworksProcess of independent whole body PET AC. Paired training data of non-attenuation corrected PET (PETNAC) and corresponding acquired CT are used to train a deep neural network to generate pseudo CT (CTGAN) from PETNAC. This pseudo CT can then be used for PET attenuation-correction resulting in an attenuation corrected PET data set (PETAC)Back to article page