Application of Machine Learning to Classify Diabetic Retinopathy

Pilar Pérez Conde, Jorge de la Calleja, Ma. Auxilio Medina, and Antonio Benitez


Medical Image Analysis, Machine Learning, Principal Component Analysis, Diabetic Retinopathy


This paper presents experimental results of a method for image-based classification of diabetic retinopathy. In our study we categorize the disease into two classes: diabetic retinopathy non-proliferative and diabetic retinopathy proliferative. The method reduces the dimensionality of the images and finds features using the statistical method of principal component analysis (PCA). Then, it classifies the images using decision trees, the naive Bayes classifier, neural networks, k-nearest neighbors and support vector machines. Preliminary results show that the naive Bayes classifier obtains the best results with 73.4% of accuracy, and 68.4% for F-measure, using a data set of 151 images and testing with different resolutions.

Important Links:

Go Back