Fig. 3From: A deep learning pipeline to simulate fluorodeoxyglucose (FDG) uptake in head and neck cancers using non-contrast CT images without the administration of radioactive tracerSimulated SUV Map (Output of Cycle-GAN) displayed alongside its ground truth (Real SUV Map) and Non-Contrast CT axial slice for six patients. The error between the SUV maps is visualised and is represented by the RMSE. It is important to note that these SUV maps are inverted as this is the view commonly used by cliniciansBack to article page