An Ensemble-based System for Microaneurysm Detection and Diabetic Retinopathy Grading

TL;DR

This paper introduces an ensemble-based system combining preprocessing and candidate extraction techniques to enhance microaneurysm detection in fundus images, significantly improving diabetic retinopathy grading accuracy.

Contribution

The novel ensemble framework integrates internal components of microaneurysm detectors, outperforming existing methods in detection and grading tasks.

Findings

Ranked first in an online competition for microaneurysm detection

Achieved AUC 0.90 in diabetic retinopathy classification on Messidor database

Demonstrated improved detection accuracy over traditional approaches

Abstract

Reliable microaneurysm detection in digital fundus images is still an open issue in medical image processing. We propose an ensemble-based framework to improve microaneurysm detection. Unlike the well-known approach of considering the output of multiple classifiers, we propose a combination of internal components of microaneurysm detectors, namely preprocessing methods and candidate extractors. We have evaluated our approach for microaneurysm detection in an online competition, where this algorithm is currently ranked as first and also on two other databases. Since microaneurysm detection is decisive in diabetic retinopathy grading, we also tested the proposed method for this task on the publicly available Messidor database, where a promising AUC 0.90 with 0.01 uncertainty is achieved in a 'DR/non-DR'-type classification based on the presence or absence of the microaneurysms.