Assorted Image Processing Techniques for Retinal OCT in Glaucoma Detection

Abstract

This research is focused on image processing techniques for automatic detection of glaucoma in Retinal Optical Image Coherence Tomography. In the recent year, the interest on the automated glaucoma diagnosis techniques using the image processing techniques are exploding at an optimal rate which may help in the early diagnosis of the patients to recover from the permanent blindness. The manual diagnosis process for glaucoma detection within the medical community is tedious and time-consuming process that is susceptible to error. On the contrary image processing-based algorithms in constituent to deep learning can give better computation possibility in a trustworthy manner. The primary objective of the proposed research is to define proper image pre-processing techniques that aid in the process of the diagnosis. The aim is to aid in glaucoma detection by proposing image processing techniques to process the Optical Coherence Tomography images of the retina. The saturation removal technique is used for the intensity correction with histogram equalization of flattening the images. Resizing, filtering, and argumentation is also proposed in this research as possible image processing techniques. To show the generalized nature of the proposed approach, pre-processing techniques are employed on the OCT images which resulted in good results.

Keywords: Optical image coherence tomography (OCT), glaucoma diagnosis, image processing, saturation removal, histogram equalization, deep learning