Glaucoma disease is the second leading cause of blindness in the world. This progressive ocular neuropathy is mainly caused by uncontrolled high intraocular pressure. Although there is still no cure, early detection and appropriate treatment can stop the disease progression to low vision and blindness. In the clinical practice, the gold standard used by ophthalmologists for glaucoma diagnosis is fundus retinal imaging, in particular optic nerve head (ONH) subjective/manual examination. In this work, we propose an unsupervised superpixel-based method for the optic nerve head (ONH) segmentation. An automatic algorithm based on linear iterative clustering is used to compute an ellipse fitting for the automatic detection of the ONH contour. The tool has been tested using a public retinal fundus images dataset with medical expert ground truths of the ONH contour and validated with a classified (control vs. glaucoma eyes) database. Results showed that the automatic segmentation method provides similar results in ellipse fitting of the ONH that those obtained from the ground truth experts within the statistical range of inter-observation variability. Our method is a user-friendly available program that provides fast and reliable results for clinicians working on glaucoma screening using retinal fundus images.
Keywords: artificial intelligence; glaucoma; retinal imaging; superpixel segmentation.