A Mobile Health Approach for Glaucoma Detection

Glaucoma is a progressive eye disease that ranks as the second leading cause of blindness and the foremost cause of irreversible blindness globally. According to the National Institutes of Health’s National Eye Institute (NIH-NEI), glaucoma accounts for 3 million cases of irreversible blindness and low vision in the United States. Many individuals with glaucoma may exhibit no symptoms, making early detection essential to preventing blindness and preserving vision. This paper presents a novel smartphone-based method for the early detection and prediction of glaucoma. Our approach employs an innovative CIE LAB color-based enhancement technique for preprocessing, as well as a 3D stereo depth mapping method to extract the optic disc and optic cup from retinal fundus images. We calculate the areas of the optic disc and optic cup to determine the cup-to-disc ratios. For classification, we utilized a support vector machine (SVM). Our proposed method demonstrated a remarkable ability to differentiate glaucomatous eyes from healthy ones, achieving a sensitivity of 96.6%, specificity of 98.2%, and an overall accuracy of 97.1%.