ARGALI: An Automatic Cup-to-Disc Ratio Measurement System for Glaucoma Analysis Using Level-set Image Processing

Abstract

Glaucoma is a leading cause of blindness worldwide, accounting for 12.3% of the permanently blind according to the World Heath Organization. The disease is particularly prevalent in Asia, with up to 50% of total glaucoma cases found in the region. Although glaucomatous damage is irreversible, studies have shown that early detection can be effective in slowing or halting glaucomatous atrophy. The ratio of the size of the optic cup to the optic disc, also known as the cup-to-disc ratio (CDR), is an important indicator for glaucoma assessment, since glaucomatous progression corresponds to increased excavation of the optic cup. In current clinical practice, the CDR is measured manually and can be subjective, limiting its use in screening for early detection. We describe the ARGALI system which automatically calculates the CDR from non-stereographic retinal fundus photographs, providing a fast, objective and consistent measurement. The ARGALI system consists of a series of steps. As the optic disc occupies only a small region of the entire retinal image, a region of interest is first extracted via pixel intensity analysis. Variational level-set algorithm is next used to segment the optic disc. Optic cup segmentation is more challenging due to the cup’s interweavement with blood vessels and surrounding tissues. A multi-modal approach consisting of different methods is used extract the cup. To obtain a smoother contour, ellipse fitting is applied to the extracted cup and disc. A neural network has also been proposed to fuse the results obtained via the various modes. The ARGALI system was tested using images collected from patients at the Singapore Eye Research Institute and achieves an RMS error of 0.05 with a risk assessment accuracy of 95%. The results are promising for ARGALI to be developed into a low cost, objective and efficient screening system for automatic assessment glaucoma risk assessment.