Fig. 6From: ParaPET: non-invasive deep learning method for direct parametric brain PET reconstruction using histoimagesVoxel-wise comparison between the kinetic parameters calculated using the ML method, Ki-NLS and Ki-Patlak in Subject 3. Linear regression indicates a linear relationship. Ki values calculated from ML, NLS and Patlak values are shown for an example subject for qualitative comparisonBack to article page