TPOT: Topology Preserving Optimal Transport in Retinal Fundus Image Enhancement

TL;DR

This paper introduces TPOT, a novel retinal image enhancement method that preserves blood vessel topology using persistence diagrams, outperforming existing techniques in image quality and segmentation accuracy.

Contribution

The paper proposes a topology-preserving training paradigm based on optimal transport and persistence diagrams to enhance retinal images while maintaining vascular structures.

Findings

TPOT outperforms state-of-the-art methods in image quality.

TPOT improves blood vessel segmentation accuracy.

The approach effectively preserves vascular topology during enhancement.

Abstract

Retinal fundus photography enhancement is important for diagnosing and monitoring retinal diseases. However, early approaches to retinal image enhancement, such as those based on Generative Adversarial Networks (GANs), often struggle to preserve the complex topological information of blood vessels, resulting in spurious or missing vessel structures. The persistence diagram, which captures topological features based on the persistence of topological structures under different filtrations, provides a promising way to represent the structure information. In this work, we propose a topology-preserving training paradigm that regularizes blood vessel structures by minimizing the differences of persistence diagrams. We call the resulting framework Topology Preserving Optimal Transport (TPOT). Experimental results on a large-scale dataset demonstrate the superiority of the proposed method compared to several state-of-the-art supervised and unsupervised techniques, both in terms of image quality and performance in the downstream blood vessel segmentation task. The code is available at https://github.com/Retinal-Research/TPOT.