Retinal status analysis based on feature quantification in OCT images

Many ophthalmopathies have close relationships with the morphology of fundus retina. Optical coherence tomography (OCT) is an in vivo imaging technique that could rapidly acquire retinal microstructure images. Analysis of retinal OCT images enables to acquire large amounts of information useful for medical diagnosis. Manual analysis methods are time consuming and the results are very depending on personal experience. This paper describes a retinal status automatic analysis method based on boundary extraction, morphological characterization, feature quantification and grade evaluation. The normal retinal reference model based on retinal boundaries was firstly presented. Then, two kinds of quantitative methods based on geometric features and morphological features were proposed. This paper put forward a retinal abnormal grading decision-making method which was used in actual analysis and evaluation of OCT images. The proposed method can obtain the parameters and features that associated with retinal morphology, realize the target image abnormal judgment and provide a reference for disease diagnosis.