Fig. 4From: A deep learning pipeline to simulate fluorodeoxyglucose (FDG) uptake in head and neck cancers using non-contrast CT images without the administration of radioactive tracerTechnical Assessment of Simulated SUV Map Accuracy. Bland–Altman plots for the SUV0 (a), SUV50 (b), SUVMax (c) and tumour volume (d) were constructed to assess the percentage difference between the gold standard and generated SUV maps. The bias along with the 95% confidence intervals is indicated in each plot. These assessment criteria were adapted from the PERCIST v.1 criteria to characterise and monitor tumour progression using PET/SUV images.Back to article page