A new unified framework for the early detection of the progression to diabetic retinopathy from fundus images. (1st November 2017)

• Record Type: Journal Article
• Authors: Leontidis, Georgios; Al-Diri, Bashir; Hunter, Andrew
• Is Part Of: Computers in biology and medicine. Volume 90(2017)
• Page Start: 98
• Page End: 115
• Publication Date: 2017-11-01
• Subjects: Framework -- Diabetic retinopathy -- Statistical analysis -- Detection -- Classification; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.09.008
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Human retina is a diverse and important tissue, vastly studied for various retinal and other diseases. Diabetic retinopathy (DR), a leading cause of blindness, is one of them. This work proposes a novel and complete framework for the accurate and robust extraction and analysis of a series of retinal vascular geometric features. It focuses on studying the registered bifurcations in successive years of progression from diabetes (no DR) to DR, in order to identify the vascular alterations. Retinal fundus images are utilised, and multiple experimental designs are employed. The framework includes various steps, such as image registration and segmentation, extraction of features, statistical analysis and classification models. Linear mixed models are utilised for making the statistical inferences, alongside the elastic-net logistic regression, boruta algorithm, and regularised random forests for the feature selection and classification phases, in order to evaluate the discriminative potential of the investigated features and also build classification models. A number of geometric features, such as the central retinal artery and vein equivalents, are found to differ significantly across the experiments and also have good discriminative potential. The classification systems yield promising results with the area under the curve values ranging from 0.821 to 0.968, across the four different investigated combinations. Graphical abstract: Highlights: A novel machine-learning based framework (FRiAReD) for studying retinal diseases is presented, utilising handcrafted features. Retinal vascular alterations are associated with the progression from early and late stages of diabetes-NoDR to DR. Several geometric features of the retinal vasculature exhibit good discriminative potential. Classification results in terms of the AUC ranged from 0.821 to 0.968