Brighteye: Glaucoma Screening with Color Fundus Photographs based on Vision Transformer

TL;DR

Brighteye employs a Vision Transformer-based approach with optic disc localization to improve automated glaucoma detection from fundus images, demonstrating enhanced sensitivity and feature classification accuracy.

Contribution

This paper introduces Brighteye, a novel Vision Transformer-based method incorporating optic disc localization for improved glaucoma detection and classification from fundus photographs.

Findings

Increased sensitivity from 79.20% to 85.70% at 95% specificity.

Reduced Hamming distance from 0.2470 to 0.1250 for feature classification.

Secured fifth place in the JustRAIGS challenge out of 226 entries.

Abstract

Differences in image quality, lighting conditions, and patient demographics pose challenges to automated glaucoma detection from color fundus photography. Brighteye, a method based on Vision Transformer, is proposed for glaucoma detection and glaucomatous feature classification. Brighteye learns long-range relationships among pixels within large fundus images using a self-attention mechanism. Prior to being input into Brighteye, the optic disc is localized using YOLOv8, and the region of interest (ROI) around the disc center is cropped to ensure alignment with clinical practice. Optic disc detection improves the sensitivity at 95% specificity from 79.20% to 85.70% for glaucoma detection and the Hamming distance from 0.2470 to 0.1250 for glaucomatous feature classification. In the developmental stage of the Justified Referral in AI Glaucoma Screening (JustRAIGS) challenge, the overall outcome secured the fifth position out of 226 entries.