Fig. 2From: Deep learning-based amyloid PET positivity classification model in the Alzheimer’s disease continuum by using 2-[18F]FDG PETConvolutional neural network architecture in 2.5 dimensions (2.5-D). A total of 291 2-D images were used as inputs for the model. 291 number of prediction values obtained from 291 submodules pass through the fully connected layer for the final prediction. Abbreviation: Conv = convolution layer; MaxPool = Max pooling layer; FC = fully connected layerBack to article page