Fig. 8From: Adopting transfer learning for neuroimaging: a comparative analysis with a custom 3D convolution neural network modelProcessing 18F-FDG-PET raw scans for generating 3D as well as 2D inputs for custom 3D model and TL models. For 3D input we build 3D matrix having 60 slices along the axial plane. To transform input for 2D-TL models, we arrange these 60 slices into a 2D gridBack to article page