Dense Convolution Neural Network for Automated Diabetic Retinopathy Detection

Abstract

Diabetic Retinopathy is a diabetes complication due to uncontrolled levels of glucose in the body which leads to abnormality in the eyes which owing to distortion in the retina and leading to permanent damage of the eye or vision losses. Hence identification and classification of diabetic retinopathy through manual observation is a challenging process due to composite boundaries and features with a high degree of intraclass variation and a low degree of interclass variation.
 Unsupervised machine learning algorithms have been used to classify diseases automatically based on the appearance of lesions and their characteristics. These models require more processing time and less reliability. It has been proposed that deep learning architecture can overcome these limitations as it is more efficient and accurate at detecting the lesion’s features.
 The novel dense convolution neural network has been proposed with preprocessing, segmentation, feature extraction and classification steps. Laplacian filter and CLAHE techniques have been used in a preprocessing step. The region growing algorithm, Principal Component Analysis and Dense CNN have been used for segmentation, Feature extraction and classification of DR lesions. Furthermore, the proposed model was compared with conventional classifiers in terms of Accuracy parameters. The proposed model achieves 97.88 % of Accuracy. It improves computing efficiency and minimizes network complexity. Hence the proposed model can accurately detect the lesions in the retinal fundus images.