Deep Angiogram: Trivializing Retinal Vessel Segmentation

TL;DR

This paper introduces a contrastive variational auto-encoder that synthesizes a vessel-only representation of retinal images, enabling robust, threshold-based segmentation across diverse domains and conditions.

Contribution

The novel deep angiogram approach filters irrelevant features and enhances cross-domain vessel segmentation robustness compared to existing deep learning models.

Findings

Achieves higher segmentation accuracy than baseline networks.

Generates stable, vessel-only images across different domains.

Provides a non-invasive alternative to fluorescein angiography.

Abstract

Among the research efforts to segment the retinal vasculature from fundus images, deep learning models consistently achieve superior performance. However, this data-driven approach is very sensitive to domain shifts. For fundus images, such data distribution changes can easily be caused by variations in illumination conditions as well as the presence of disease-related features such as hemorrhages and drusen. Since the source domain may not include all possible types of pathological cases, a model that can robustly recognize vessels on unseen domains is desirable but remains elusive, despite many proposed segmentation networks of ever-increasing complexity. In this work, we propose a contrastive variational auto-encoder that can filter out irrelevant features and synthesize a latent image, named deep angiogram, representing only the retinal vessels. Then segmentation can be readily accomplished by thresholding the deep angiogram. The generalizability of the synthetic network is improved by the contrastive loss that makes the model less sensitive to variations of image contrast and noisy features. Compared to baseline deep segmentation networks, our model achieves higher segmentation performance via simple thresholding. Our experiments show that the model can generate stable angiograms on different target domains, providing excellent visualization of vessels and a non-invasive, safe alternative to fluorescein angiography.