Optimal Transport Guided Unsupervised Learning for Enhancing low-quality Retinal Images
This work addresses the challenge of improving retinal image quality for clinical diagnosis, but it is incremental as it builds on existing GAN-based methods with theoretical and consistency enhancements.
The paper tackles the problem of enhancing low-quality retinal fundus images affected by artifacts and imperfections, which can lead to inaccurate clinical diagnoses, by proposing an unsupervised image-to-image translation framework using optimal transport theory and an information consistency mechanism, achieving superior perceptual and quantitative results on the EyeQ dataset.
Real-world non-mydriatic retinal fundus photography is prone to artifacts, imperfections and low-quality when certain ocular or systemic co-morbidities exist. Artifacts may result in inaccuracy or ambiguity in clinical diagnoses. In this paper, we proposed a simple but effective end-to-end framework for enhancing poor-quality retinal fundus images. Leveraging the optimal transport theory, we proposed an unpaired image-to-image translation scheme for transporting low-quality images to their high-quality counterparts. We theoretically proved that a Generative Adversarial Networks (GAN) model with a generator and discriminator is sufficient for this task. Furthermore, to mitigate the inconsistency of information between the low-quality images and their enhancements, an information consistency mechanism was proposed to maximally maintain structural consistency (optical discs, blood vessels, lesions) between the source and enhanced domains. Extensive experiments were conducted on the EyeQ dataset to demonstrate the superiority of our proposed method perceptually and quantitatively.