Retinal Microvasculature as Biomarker for Diabetes and Cardiovascular Diseases

TL;DR

This study demonstrates that retinal microvasculature features, analyzed through deep learning and vessel reconstruction, serve as reliable biomarkers for diabetic retinopathy and cardiovascular diseases, with high classification accuracy.

Contribution

The paper introduces a novel approach combining CNN-based segmentation and harmonic descriptors for vascular analysis as biomarkers for DR and cardiovascular risk.

Findings

Over 93.8% accuracy in classifying DR severity based on vasculature defects

96.7% accuracy in distinguishing non-sight threatening from sight-threatening DR

Strong correlation between vasculature shape and disease progression

Abstract

Purpose: To demonstrate that retinal microvasculature per se is a reliable biomarker for Diabetic Retinopathy (DR) and, by extension, cardiovascular diseases. Methods: Deep Learning Convolutional Neural Networks (CNN) applied to color fundus images for semantic segmentation of the blood vessels and severity classification on both vascular and full images. Vessel reconstruction through harmonic descriptors is also used as a smoothing and de-noising tool. The mathematical background of the theory is also outlined. Results: For diabetic patients, at least 93.8% of DR No-Refer vs. Refer classification can be related to vasculature defects. As for the Non-Sight Threatening vs. Sight Threatening case, the ratio is as high as 96.7%. Conclusion: In the case of DR, most of the disease biomarkers are related topologically to the vasculature. Translational Relevance: Experiments conducted on eye blood vasculature reconstruction as a biomarker shows a strong correlation between vasculature shape and later stages of DR.