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

Abstract

We present a novel and fully automated fundus image processing technique for glaucoma prescreening based on the rim-to-disc ratio (RDR). The technique accurately segments the optic disc and optic cup and then computes the RDR based on which it is possible to differentiate a normal fundus from a glaucomatous one. The technique performs a further categorization into normal, moderate, or severely glaucomatous classes following the disc-damage-likelihood scale (DDLS). To the best of our knowledge, this is the first engineering attempt at using RDR and DDLS to perform glaucoma severity assessment. The segmentation of the optic disc and cup is based on the active disc, whose parameters are optimized to maximize the local contrast. The optimization is performed efficiently by means of a multiscale representation, accelerated gradient-descent, and Green's theorem. Validations are performed on several publicly available databases as well as data provided by manufacturers of some commercially available fundus imaging devices. The segmentation and classification performance is assessed against expert clinician annotations in terms of sensitivity, specificity, accuracy, Jaccard, and Dice similarity indices. The results show that RDR based automated glaucoma assessment is about 8% to 10% more accurate than a cup-to-disc ratio (CDR) based system. An ablation study carried out considering the ground-truth expert outlines alone for classification showed that RDR is superior to CDR by 5.28% in a two-stage classification and about 3.21% in a three-stage severity grading.

Figure 1

(a) Neuroretinal rim (the region between the optic disc and cup); Clinically relevant parameters for glaucoma assessment: (b) Cup-to-disc ratio, (c) Rim-to-disc ratio, and (d) ISNT.

Figure 2

(a) Nearly concentric optic disc and cup but non-glaucomatous. (b) Eccentric disc and cup but glaucomatous. (c,d) Two optic disc and cup drawings with identical CDR but with unequal rim-width and with (c) being non-glaucomatous, and (d) being glaucomatous.

Figure 3

(a) Disc template. (b) Optimal active-disc fit on the optic disc.

Figure 4

Determination of the narrowest rim-width. O₁ and O₂ denote the centers of the optic cup and disc, respectively. The narrowest rim-width is l.

Figure 5

An illustration of the segmentation performance of the proposed method. (a1–a3) Input fundus images. (b1–b3) Optic disc outlines (green). (c1–c3) Optic cup outlines (blue). (d1–d3) Narrowest rim-width in black color. (e1–e3) Inferior, superior, nasal, and temporal rim widths in white, red, yellow, and black colors, respectively.

Figure 6

A comparison of the algorithm outlines (thick contours) with the expert outlines (thin contours).