Published Paper Details:

Glaucoma is a visual disorder characterized by damage to the optic nerve which results in a narrowing of the field of view and can lead to blindness. The main cause of glaucoma is eyeball fluid or commonly called aquos humor which functions to provide nutrition to the inner eye organs, the cycle of producing and secreting this fluid is unbalanced, therefore resulting in increased pressure in the eyeball, which causes the eye nerves to become damaged. Glaucoma is the second leading cause of blindness in the world after cataracts. However, glaucoma is different from cataract because glaucoma causes permanent blindness. In 2020 glaucoma affected 79.6 million people. Therefore, early detection of glaucoma can reduce the severity of the patient. At this time, the main and popular way to diagnose glaucoma is by measuring cup-to-disc ratio (CDR) on digital fundus images. In the cup to disc ratio (CDR) measurements are made to see the Optical Disk (OD) and Optical Cup (OC). However, the detection of digital fundus images for the measurement method cup-to-disc ratio (CDR) until now has been done manually, it takes a lot of time and each expert has differences in the parameters to make measurement accuracy. Because of this, the need to perform automatic digital fundus image examination is urgently needed. One of the deep learning methods that has the best expertise in terms of classifying objects in images, namely methods CNN using Deep Learning. However, In this study, the various reviews of glaucoma classification was carried out using the Deep Learning model Convolutional Neural Network and reveals that CNN is a effective and appropriate model to classify glaucoma