An ensemble-based system for automatic screening of diabetic retinopathy

Abstract

In this paper, an ensemble-based method for the screening of diabetic retinopathy (DR) is proposed. This approach is based on features extracted from the output of several retinal image processing algorithms, such as image-level (quality assessment, pre-screening, AM/FM), lesion-specific (microaneurysms, exudates) and anatomical (macula, optic disc) components. The actual decision about the presence of the disease is then made by an ensemble of machine learning classifiers. We have tested our approach on the publicly available Messidor database, where 90% sensitivity, 91% specificity and 90% accuracy and 0.989 AUC are achieved in a disease/no-disease setting. These results are highly competitive in this field and suggest that retinal image processing is a valid approach for automatic DR screening.

References in corpus (2)

• An Ensemble-based System for Microaneurysm Detection and Diabetic Retinopathy Grading
• A Two-phase Decision Support Framework for the Automatic Screening of Digital Fundus Images

Cited by in corpus (18)

• Application of Deep Learning in Fundus Image Processing for Ophthalmic Diagnosis -- A Review
• Improved Microaneurysm Detection using Deep Neural Networks
• VIBNN: Hardware Acceleration of Bayesian Neural Networks
• Fractional norms and quasinorms do not help to overcome the curse of dimensionality
• A simple and efficient architecture for trainable activation functions
• A Modified Bayesian Optimization based Hyper-Parameter Tuning Approach for Extreme Gradient Boosting
• Curvature-based Feature Selection with Application in Classifying Electronic Health Records
• On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach
• Early Blindness Detection Based on Retinal Images Using Ensemble Learning
• ${\text{O}}^2$PF: Oversampling via Optimum-Path Forest for Breast Cancer Detection
• Maximally Correlated Principal Component Analysis
• Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
• Decision trees as partitioning machines to characterize their generalization properties
• IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks
• Classifier ensemble creation via false labelling
• CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
• A stochastic approach to handle knapsack problems in the creation of ensembles
• Targeted Deep Learning: Framework, Methods, and Applications