Fully automated assessment of Macular Edema using Optical Coherence Tomography (OCT) images

Abstract

Macular Edema (ME) is the retinal disorder which is caused because of fluid deposition in the sub-retinal layers. It causes loss of central vision if left untreated. The symptoms of this disease are not apparent in early stage and as the disease progresses; it becomes very difficult to diagnose. Optical Coherence Tomography (OCT) imaging is one of the latest and efficient techniques for the detection of macular edema at early stage. This paper proposes a fully automated method for the identification of ME from OCT images using Discriminant Analysis (DA) classifier. We trained the classifier by extracting 3 different features (max and min thickness between Inner Limiting Membrane (ILM) layer and choroid layer and the difference of max and min thickness) from 16 labeled OCT image. 30 OCT images (15 Healthy, 15 ME) are studied in proposed research. Our algorithm correctly classified 100% of ME patients and 93.33% of healthy patients.