# Diabetic Retinopathy Grading

Retinal disease grading has mostly relied on raw color fundus photographs, where low-contrast lesions and thin vessels are easily lost to illumination and noise. F2D-RetinaNet sends an enhanced green channel and a vessel map through two separate branches and fuses them into one grading decision. On APTOS 2019 five-grade diabetic retinopathy staging it reaches 93.32% accuracy, 3.25 points above the RGB-only baseline, and 87.14% on the external DREAM-RFI set after overlapping images were excluded.

Retinal disease grading has mostly relied on raw color fundus photographs, where low-contrast lesions and thin vessels are easily lost to illumination and noise. F2D-RetinaNet sends an enhanced green channel and a vessel map through two separate branches and fuses them into one grading decision. On APTOS 2019 five-grade diabetic retinopathy staging it reaches 93.32% accuracy, 3.25 points above the RGB-only baseline, and 87.14% on the external DREAM-RFI set after overlapping images were excluded.

The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.

The study pretrained StyleGAN3 and Medfusion on an auxiliary dataset, curated synthetic images through a domain-matched Oracle network using Latent Space Rejection Sampling and Class-Conditioned SDEdit Escalation, and evaluated downstream grading on the Indian DR Image Dataset across ConvNeXt, ResNet50, and VGG16 with five random seeds, finding that a real-data-only ConvNeXt baseline reached a quadratic weighted kappa of 0.6350 ± 0.0135, curated StyleGAN3 augmentation raised it to 0.7185 ± 0.0309, Medfusion augmentation reached 0.7695 ± 0.0254 (an absolute improvement of 0.1345), and Medfusion doubled proliferative DR recall from 0.2615 ± 0.1595 to 0.5385 ± 0.0942.