Analyzing retina structure in high-resolution images, such as those obtained in optical coherence tomography, is one of the most widespread ways of identifying structural changes that may indicate the onset or progression of visual impairment. During the diagnosis process, the specialist performs several manual analyses of the data generated by imaging equipment. There is a consensus regarding the benefits of having support from automated approaches to help in this diagnosis process. Nevertheless, automated glaucoma detection using optical coherence tomography is still considered an area needing further research. This work presents an approach to foster automatic glaucoma evaluation considering convolutional neural networks for semantic segmentation of retinal layers through optical coherence tomography images and image processing for measuring the cup region in the optic nerve head portion. We provide a quantitative evaluation comparing the results obtained by a specialist physician. The work’s main contribution is presenting the first approach supporting the automation of a new biomarker for diagnosing glaucoma.