Hybrid classifier and region-dependent integrated features for detection of diabetic retinopathy

Classification and grading of diabetic retinopathy images using mixture of ensemble classifiers

Diabetic Retinopathy (DR) is one of the most common diabetic diseases that affect the retina’s blood vessels. Too much of the glucose level in blood leads to blockage of blood vessels in the retina, weakening and damaging the retina. Automatic classification of diabetic retinopathy is a challenging task in medical research. This work proposes a Mixture of Ensemble Classifiers (MEC) to classify and grade diabetic retinopathy images using hierarchical features. We use an ensemble of classifiers such as support vector machine, random forest, and Adaboost classifiers that use the hierarchical feature maps obtained at every pooling layer of a convolutional neural network (CNN) for training. The feature maps are generated by applying the filters to the output of the previous layer. Lastly, we predict the class label or the grade for the given test diabetic retinopathy image by considering the class labels of all the ensembled classifiers. We have tested our approaches on the E-ophtha dataset for the classification task and the Messidor dataset for the grading task. We achieved an accuracy of 95.8% and 96.2% for the E-ophtha and Messidor datasets, respectively. A comparison among prominent convolutional neural network architectures and the proposed approach is provided.

Intelligent-assistant system for scleral spur location

A system based on the use of two artificial neural networks (ANNs) to determine the location of the scleral spur of the human eye in ocular images generated by an ultrasound biomicroscopy is presented in this paper. The two ANNs establish a relationship between the distance of four manually placed landmarks in an ocular image with the coordinates of the scleral spur. The latter coordinates are generated by the expert knowledge of a subject matter specialist. Trained ANNs that generate good results for scleral spur location are incorporated into a software system. Statistical indicators and results yield an efficiency performance above 95%.