Model Architecture

In our study, EfficientNetB4 was used as the convolutional neural network (CNN) for the classification model (Figure 2). Because our goal was to aid disease diagnosis and the detection of disease severity, the models had 2 outputs: (1) disease classification and (2) treatment requirement determination. However, features indicating severity may differ based on the disease. Our model first delivered disease prediction for differentiating different retinal vascular diseases. We then designed a layer consisting of a fully connected, reshaped, and weighted sum to facilitate the model classification of treatment requirement partially according to the results from the disease prediction part. In addition, to visualize the features for model prediction, heat maps were generated using gradient-weighted class activation mapping [17], which used the gradient based on the output scores to show the activation map for the specific image. The features of the heat maps were highlighted in a lighter color.

Architecture of the deep learning prediction model. CNN: convolutional neural network; FCL: fully connected layer; GAP: global average pooling.