Automated Glaucoma Diagnosis System Based on Fundus Images Features

Glaucoma is a disease that can damage the eye’s optic nerve and cause permanent vision loss or even total blindness if not detected in early stage and thus, it is important diagnose early to prevent blindness. Image processing techniques has been used to detect early glaucoma using the fundus images. In this paper, a computer aided glaucoma diagnosis system is proposed based on fundus image features. The optic disc and optic cup features are extracted from funds images and two parameters are calculated, namely: Cup to Disc Ratio (CDR) which indicates the enlargement of cup and the Inferior Superior to Nasal Temporal (ISNT) which determine the ratio of the thickness of the rim. Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) classifiers are used to classify images into "Normal" or "Abnormal". The quality of both classifiers is evaluated and compared in terms of three performance metrics, namely: sensitivity, specificity and accuracy and satisfactory results have been achieved where the system accuracy is 95%. Moreover; Patient data such as age, family history of the disease, eye pressure and the last eye examination record were taken in account. The proposed system can categorize images into five categories: "no risk", "low risk", "moderate risk", "high risk" and "very high risk".