Figure 4 | Scientific Reports

Figure 4

From: Association of imaging factors derived from convolutional neural network with visual outcomes in age-related macular degeneration and polypoidal choroidal vasculopathy

Figure 4The alternative text for this image may have been generated using AI.

Representative case of polypoidal choroidal vasculopathy (PCV) without pachychoroid. The patient is a 78-year-old woman with a baseline visual acuity of 20/30. For 67.9 months of follow-up, the eye was treated with 10 intravitreal aflibercept injections. (a) Baseline fundus photography shows subretinal fluid, exudation with orange colored polyp at nasal side of fovea. (b) Baseline indocyanine green angiography (ICGA) shows peripapillary polypoidal change with branced vascular network. (c) En face optical coherence tomography (En face OCT) scan of the final visit. Choroidal vessels are not dilated. (d) Enhanced depth imaging optical coherence (EDI OCT) at baseline (lower). Choroidal layer is generally thin with a subfoveal choroidal thickness (SFCT) of 186 µm. (e) EDI OCT scan after 12 months from baseline. Intraretinal fluid (IRF) resolved, but subretinal fluid (SRF) and pigment epithelial detachment (PED) are still present, and visual acuity decreased to 20/50. Visual acuity at the final visit was 20/100. (f) Upper panel shows predicted lesion corresponding baseline OCT B-scan by a convolutional neural network (CNN). IRF (red color), SRF (green color), and PED (blue color) are noted. Each component could be quantified by converting the pixel counts into mm2, and the areas of IRF, SRF, and PED are 0.114, 0.090, and 0.236 mm2, respectively. Lower panel shows predicted areas of SRF and PED as 0.169 and 0.228 mm2, respectively.

Back to article page