Retinal Width Estimation of High-Resolution Fundus Images For Diabetic Retinopathy Detection

摘要

Studies have shown some correlations between retinal vessel morphologies and multiple systemic diseases. While this could pave the way to timely diagnosis of such diseases by examining vessels from fundus images, practical application of measuring and quantifying changes in vessel width over time remains a challenge. In this study, we propose a semi-automated estimation method to efficiently summarize vessel width characteristics from fundus images. The method consists of retinal vessel segmentation, optic disc (OD) localization and vessel width parameters estimation. The proposed method is validated using a public database of high-resolution fundus images called HRF, where the significance of obtained vessel width parameters in differentiating the three image groups in the database are analysed. Results indicate that the obtained parameter using the method that summarises the ratio between width of veins to arteries, AVR (Artery-Vein Ratio) can be used to differentiate images from patients with Diabetic Retinopathy against healthy and glaucomatous patients.