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

Abstract

One of the major eye diseases called Diabetic retinopathy (DR), which causes loss of sight if it is not noticed in the early hours. In order to keep the patient’s vision, the early detection and periodic screening of DR plays an important role in eye diagnosis by examining the deformity in retinal fundus images. During the early detection of DR, ophthalmologists identify the lesions called microaneurysms that emerge as the first symptom of the disease. The various test methods availability and the handlings of all these test methods for detection of DR are not possible in rural areas. The automatic DR detection system offers the potential to be used in large-scale screening programs. This paper presents a hybrid classifier and region-dependent integrated features for detection of DR automatically. In the proposed hybrid classifier, holoentropy enabled decision tree is combined with a feed forward neural network using the proposed score level fusion method. The performance is evaluated and compared with existing classification algorithms using sensitivity, specificity, and accuracy. Two different databases such as DIARETDB0 and DIARETDB1 are utilized for the experimentation. From the experimental results, proposed technique obtained the accuracy of 98.70%, which is better as compared with existing algorithms.