Artifact Reduction in Fundus Imaging using Cycle Consistent Adversarial Neural Networks

TL;DR

This paper presents a CycleGAN-based neural network approach with residual blocks to automatically reduce artifacts in fundus images, improving image quality for better diagnosis of ophthalmic disorders.

Contribution

The paper introduces a novel application of CycleGAN with residual blocks specifically for artifact removal in fundus imaging, demonstrating significant improvements over existing methods.

Findings

Notable artifact reduction in fundus images.

Enhanced image clarity compared to prior techniques.

Potential for improved diagnostic accuracy.

Abstract

Fundus images are very useful in identifying various ophthalmic disorders. However, due to the presence of artifacts, the visibility of the retina is severely affected. This may result in misdiagnosis of the disorder which may lead to more complicated problems. Since deep learning is a powerful tool to extract patterns from data without much human intervention, they can be applied to image-to-image translation problems. An attempt has been made in this paper to automatically rectify such artifacts present in the images of the fundus. We use a CycleGAN based model which consists of residual blocks to reduce the artifacts in the images. Significant improvements are seen when compared to the existing techniques.