Brighteye: Glaucoma Screening with Color Fundus Photographs based on Vision Transformer
This work addresses challenges in glaucoma screening for medical applications, but it is incremental as it builds on existing Vision Transformer and object detection methods.
The paper tackled automated glaucoma detection from color fundus photographs by proposing Brighteye, a Vision Transformer-based method that localizes the optic disc and crops a region of interest, improving sensitivity at 95% specificity from 79.20% to 85.70% for detection and reducing Hamming distance from 0.2470 to 0.1250 for feature classification.
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.