Microaneurysm detection in retinal images using an ensemble classifier

Diabetic Retinopathy (DR) is one of the leading causes of blindness amongst the working age population. The presence of microaneurysms (MA) in retinal images is a pathognomonic sign of DR. In this work we have presented a novel combination of algorithms applied to a public dataset for automated detection of MA in colour fundus images of the retina. The proposed technique first detects an initial set of candidates using a Gaussian Matched filter and then classifies the initial set of candidates in order to reduce the number of false positives. A Random Forest ensemble classifier using a set of 79 features (the most common features used within literature) was used for classification. Our proposed algorithm was evaluated on a subset of 20 images from the MESSIDOR dataset. We show that the use of the Random Forest classifier with the 79 features improves the sensitivity of the detection, compared to using a K-Nearest Neighbours classifier that has been proposed in other techniques. In addition, the Random Forest is capable of ranking features according to their importance. We have ranked the 79 features according to their importance. This ranking provides an insight into the most important features that are necessary for discriminating true MA candidates from spurious objects. Eccentricity, aspect ratio and moments are found to be among the important features.