Figure 4 | Scientific Reports

Figure 4

From: Deep learning approaches to predict 10-2 visual field from wide-field swept-source optical coherence tomography en face images in glaucoma

Figure 4

Representative cases of 10-2 visual field (VF) prediction. The actual threshold values (THVs) of 10-2 VF tests are represented in the left column (a, b, c). The combined OCT images are represented in the middle column. The THVs predicted by the en face model (upper) and RNFLT model (lower) are represented in the right column. Darker color represents lower THV (left and right columns). mGC/IPLT  macular ganglion cell/inner plexiform layer thickness; RNLFT  retinal nerve fiber layer thickness; MAE  mean absolute error.

Back to article page