Skip to main content
. 2023 Oct 25;13:18304. doi: 10.1038/s41598-023-43104-y

Figure 1.

Figure 1

(A) Workflow of this study. Input data extracted from OCT images are used to predict VF indexes (MD, PSD, VFI) through a DNN model. Detailed structure of dashed line box with a red star is described in (B). (B) Detailed structure of the DNN model. Each number above each box represents the number of nodes in the prior layer. The number below each box means the number of nodes in the present layer. OCT = optical coherence tomography; MD = mean deviation; PSD = pattern standard deviation; VFI = visual field index; DNN = deep neural network.