An ensemble-based system for automatic screening of diabetic retinopathy

TL;DR

This paper presents an ensemble-based system that combines multiple retinal image processing algorithms and machine learning classifiers to automatically screen for diabetic retinopathy with high accuracy and reliability.

Contribution

It introduces a novel ensemble approach utilizing diverse image features and classifiers for improved diabetic retinopathy detection performance.

Findings

Achieved 90% sensitivity and 91% specificity on Messidor database

Attained 0.989 AUC indicating high diagnostic accuracy

Demonstrated the effectiveness of combining image features with ensemble classifiers

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.