Skip to main content
. 2024 May 17;4(6):100552. doi: 10.1016/j.xops.2024.100552

Figure 3.

Figure 3

Comparison of sensitivity levels (with specificity fixed at 80%) between ViT models and CNN models in all test sets. CNN = convolutional neural network; SEED = Singapore Epidemiology of Eye Diseases; SWIN = Hierarchical Vision transformer using Shifted Windows; VAN = Visual Attention Network; VGG = Visual Geometry Group; ViT = vision transformer.