Rim-to-Disc Ratio Outperforms Cup-to-Disc Ratio for Glaucoma Prescreening

Area of Science:

• Ophthalmology
• Medical Imaging
• Computer Vision

Background:

• Glaucoma is a leading cause of irreversible blindness worldwide.
• Accurate and early detection of glaucoma is crucial for preventing vision loss.
• Current diagnostic methods often rely on manual interpretation of fundus images, which can be subjective and time-consuming.

Purpose of the Study:

• To develop and validate a novel, fully automated fundus image processing technique for glaucoma prescreening.
• To assess glaucoma severity using the rim-to-disc ratio (RDR) and the disc-damage-likelihood scale (DDLS).
• To compare the performance of the RDR-based method against the traditional cup-to-disc ratio (CDR) system.

Main Methods:

• Automated segmentation of the optic disc and optic cup in fundus images.
• Calculation of the rim-to-disc ratio (RDR) using an active disc model optimized for local contrast.
• Classification of images into normal, moderate, or severe glaucoma categories based on RDR and DDLS.
• Validation using public databases and manufacturer data, with performance assessed against expert annotations.

Main Results:

• The automated RDR-based technique achieved high accuracy in segmenting optic discs and cups.
• The RDR-based glaucoma assessment demonstrated 8% to 10% greater accuracy than CDR-based systems.
• Ablation studies confirmed RDR's superiority over CDR in both two-stage and three-stage glaucoma classification.

Conclusions:

• The developed automated RDR and DDLS technique offers a reliable and efficient approach for glaucoma prescreening and severity assessment.
• This novel engineering approach provides a significant improvement over existing CDR-based methods.
• The findings suggest potential for widespread clinical adoption to enhance early glaucoma detection and management.