Improved automated detection of glaucoma by correlating fundus and SD-OCT image analysis

Glaucoma is a multifactorial ocular disease. Ophthalmologists mostly use fundus or optical coherence tomography (OCT) for diagnosis of glaucoma. In this study, a hybrid computer-aided-diagnosis (H-CAD) system has been proposed that integrates both fundus and OCT imaging technologies for reliable diagnosis of glaucoma. Fundus module inspects the outer layer of eye's posterior part. It considers a variety of structural and textural features and makes a decision using support vector machine (SVM). In OCT module, the cup to disc ratio (CDR) has been computed by examining the internal layers of the retina. The cup contour has been extracted from inner-limiting-membrane (ILM) layer using a set of novel techniques for the calculation of cup diameter. Similarly, in the disc diameter calculation the retinal-pigment-epithelium (RPE) layer termination points have been identified by a number of innovative strategies to locate disc margin. Furthermore, a new criterion based on the mean value of RPE-layer end points has been proposed for the determination of cup edges. A local-dataset annotated by four ophthalmologists has been used for evaluation of proposed H-CAD system. The evaluations and results have shown that the final result of H_CAD system is more trustable than its contemporary automated models.