Improving microaneurysm detection using an optimally selected subset of candidate extractors and preprocessing methods

In this paper, we present an approach to improve microaneurysm detection in digital color fundus images. Instead of following the standard process which considers preprocessing, candidate extraction and classification, we propose a novel approach that combines several preprocessing methods and candidate extractors before the classification step. We ensure high flexibility by using a modular model and a simulated annealing-based search algorithm to find the optimal combination. Our experimental results show that the proposed method outperforms the current state-of-the-art individual microaneurysm candidate extractors.

► State-of-the-art microaneurysm detectors do not find all the microaneurysms even at candidate extraction level. ► Applying different preprocessing methods on the images leads to different results. ► 〈〈 Preprocessing method, candidate extractor 〉〉 pairs are formed to serve as a pool for combination. ► An optimal ensemble of such pairs is found algorithmically that increases the number of true microaneurysm detections.