Development of computer aided diagnosis system for glaucoma in retinal images

Abstract

Glaucoma, also known as silent theft of sight is a disease of an eye, in which damage to the optic nerve of an eye leads to progressive and irreversible loss of vision. It is the second most common cause of blindness as per the World health organization (WHO). The earlier prediction of this disease is of utmost significance for precise diagnosis and treatment planning. The retinal imaging modality is commonly employed till date for diagnosis purpose at initial stage. Traditional approaches used by the ophthalmologists for same are time-consuming, require human interaction and are prone to subjective errors. Thus, to overcome these challenges, researchers are working in the field of medical imaging by analysis of the retinal images for glaucoma diagnosis. The study analysed various pre-processing, segmentation and classification approaches used by different researchers in the concerned field. Further, the objective of this study i.e. the development of a Computer aided diagnosis (CAD) system to differentiate amongst glaucomatous and non-glaucomatous retinal images is presented. The system comprises of pre-processing, segmentation, feature extraction, feature selection and classification stages. Thus, the investigational outcomes recommend that the developed CAD system has a potential for performing classification of retinal images as normal or glaucomatous which could be used by ophthalmologists for initial screening. Finally, some suggestions based on the observations and experiments are also stated to carry out further research in this area. newline