Early detection of retinal nerve fiber layer defects using fundus image processing

Glaucoma, the second leading cause of blindness is a disease characterized by loss of neural tissue over time. The key issue in dealing with this disease is early detection of its presence or progression, with the rapid initiation or advancement of appropriate treatment. Quantitative analysis of Retinal Nerve Fiber Layer (RNFL) via image processing of fundus images plays a major role in its early detection. The disease is characterized by the progressive degeneration of optic nerve fibers showing a distinct image of the optic nerve head. Glaucoma leads to (i) structural changes of the optic nerve head (ONH) and the nerve fiber layer and (ii) a simultaneous functional failure of the visual field. This work aims to develop a system which will recognize the presence of glaucoma by the changes in the fundus image of an eye of a person and automatically quantify the RNFL defect using image processing techniques which aids in the diagnosis of glaucoma disease. Input image of the system will be the fundus image of an eye saved in bitmap or JPEG format or a real time one. Results show that the performance of our system is appreciable with the clinical diagnosis. In the future, the system can provide a first low-priced glaucoma indication in order to possibly reduce the amount of false positives misrouted to the cost-intensive elaborate clinical investigations.