Figure 5 | Scientific Reports

Figure 5

From: Classifying central serous chorioretinopathy subtypes with a deep neural network using optical coherence tomography images: a cross-sectional study

Figure 5

An illustration of the proposed model based on VGG-16 architecture. Our proposed model consists of an input layer, 16 convolutional neural network layers with ReLU activation functions, five max-pooling layers, four FC layers with dropouts, and soft-max. The final FC layer with a soft-max activation function has been used to predict one of the four subtypes, i.e., acute, chronic, in-active, and non-resolving central serous chorioretinopathy.

Back to article page