Early detection of diabetic retinopathy from digital retinal fundus images

Diabetic retinopathy is the impairment of the retinal blood vessels due to complications of diabetes, which can subsequently lead to loss of vision. The only solution for this problem is through the use of a retinal screening system that would diagnose the retinal damage at an early stage. This paper proposes the use of morphological operations and segmentation techniques for the detection of blood vessels, exudates and microaneurysms. The retinal fundus image is partitioned into four sub images. Various features are extracted from the retinal fundus image. Haar wavelet transformations are applied on the features extracted. Principal component analysis technique is then applied for better feature selection. Back propagation neural network and one rule classifier techniques are used for the classifying the images as diabetic or non-diabetic. Experiments are performed on a publically available diabetic retinopathy data set DIARETDB1. Performance is evaluated with metrics like sensitivity, specificity and accuracy, the results obtained are encouraging.