Automated system for detection and classification of cystoid macular oedema using OCT images

Optical Coherence Tomography (OCT) is a non-invasive tool for imaging the cross-sectional view of the retina. Cystoid macular oedema (CME) is a pathological condition of the retina that can lead to significant visual impairment. In this paper, we propose an automated system for the detection and classification of CME. The first step includes pre-processing for the removal of speckle noise using edge preserving bilateral image filtering. Thereafter, four retinal layers (ILM, ELM, IS/OS and RPE) are segmented using graph cut theory. Macular thickness is measured for the detection of CME. The third step detects the presence of cystoid fluid inside the layers as positive CME cases followed by classification of CME. The algorithm is tested on 115 healthy and 115 CME-affected OCT images collected from publicly available and clinical databases. The proposed methodology shows promising results with sensitivity, specificity and accuracy of 95.81%, 98.73% and 98.12%, respectively.