SGW-GAN: Sliced Gromov-Wasserstein Guided GANs for Retinal Fundus Image Enhancement
This work solves the issue of preserving clinically relevant intra-class structure in retinal image enhancement for medical diagnosis, though it is incremental as it builds on existing GAN frameworks with a novel cost-reduction technique.
The paper tackled the problem of retinal fundus image enhancement by addressing distortions in intra-class geometry caused by existing GAN- and diffusion-based methods, and proposed SGW-GAN, which incorporates Sliced Gromov-Wasserstein to preserve relational fidelity. The result shows that SGW-GAN achieves superior diabetic retinopathy grading and reports the lowest GW discrepancy across disease labels, demonstrating efficiency and clinical fidelity.
Retinal fundus photography is indispensable for ophthalmic screening and diagnosis, yet image quality is often degraded by noise, artifacts, and uneven illumination. Recent GAN- and diffusion-based enhancement methods improve perceptual quality by aligning degraded images with high-quality distributions, but our analysis shows that this focus can distort intra-class geometry: clinically related samples become dispersed, disease-class boundaries blur, and downstream tasks such as grading or lesion detection are harmed. The Gromov Wasserstein (GW) discrepancy offers a principled solution by aligning distributions through internal pairwise distances, naturally preserving intra-class structure, but its high computational cost restricts practical use. To overcome this, we propose SGW-GAN, the first framework to incorporate Sliced GW (SGW) into retinal image enhancement. SGW approximates GW via random projections, retaining relational fidelity while greatly reducing cost. Experiments on public datasets show that SGW-GAN produces visually compelling enhancements, achieves superior diabetic retinopathy grading, and reports the lowest GW discrepancy across disease labels, demonstrating both efficiency and clinical fidelity for unpaired medical image enhancement.