Fig. 3: Cellular-level indocyanine green (ICG) retinal pigment epithelial (RPE) cell images from healthy eyes can be generated using stratified cycleGAN. | Communications Medicine

Fig. 3: Cellular-level indocyanine green (ICG) retinal pigment epithelial (RPE) cell images from healthy eyes can be generated using stratified cycleGAN.

From: Artificial intelligence assisted clinical fluorescence imaging achieves in vivo cellular resolution comparable to adaptive optics ophthalmoscopy

Fig. 3

Representative foveal RPE images from four separate eyes are shown. Conventional ICG and adaptive optics enhanced ICG (AO-ICG) images from the same ___location are acquired from each eye, and stratified cycleGAN image enhancement was applied to the conventional ICG image to generate the artificial intelligence assisted ICG (AI-ICG) image. Individual RPE cells can be identified (yellow arrows) in all three ICG image modalities though at different quality. Results show that AI-ICG RPE images demonstrate visibly improved quality compared to their corresponding conventional ICG images, and closely resemble the ground truth AO-ICG images. Scale bar: 100 µm.

Back to article page