Application of Conditional GAN Models in Optic Disc/Optic Cup Segmentation of Retinal Fundus Images

Analysis of retinal fundus images have been proven to provide relevant information about the diagnoses of several pathologies. Among them, glaucoma stands out as an important pathology due to the need for early treatment. Moreover, the ration between optic disc and optic cup radii provided by retinal fundus image analysis can aid in diagnosis. Automatically generating such a relation is, therefore, an important feature for ensuring quicker and more precise conclusions. This paper evaluates the use of Conditional GAN (Generative Adversarial Networks) for an optic disc and optic cup segmentation task. Conditional GANs are hybrid machine learning models that are able to generate data based on conditioned training. The results demonstrate that the addressed method generates valid segmentation images for optic disc and optic cup location, with approximately 95% and 85% accuracy, respectively. © 2021 SPIE.