Taylor series‐based deep belief network for automatic classification of diabetic retinopathy using retinal fundus images

Abstract

AbstractThe diagnosis of diabetic retinopathy (DR) disease in the early stage is very important to reduce the risk in DR treatment. Different methods are in practice for detecting the lesions automatically with the retinal image. However, detecting the occurrence of exudates in the macular region poses a challenging task in the computer‐assisted diagnosis of DR. A robust and computationally efficient model for localizing the lesions and features in the retinal fundus image is processed in this research by proposing the Taylor‐based deep belief network (T‐based DBN) classifier. Exudates and their contours are determined based on the blood vessel and optic disc segmentation model. The microaneurysms are detected based on the wavelet model, and the lesions are segmented with the thresholding and binarization approach. The proposed T‐based DBN is highly effective in classifying the DR, based on the multiple layers associated with the restricted Boltzmann machines (RBM) and multi‐layer perceptron (MLP) layer. The proposed T‐based DBN is the integration of the Taylor series with the DBN classifier. The proposed T‐based DBN produces an accurate detection rate and yields better theoretical error bounds. The performance revealed by the proposed model is evaluated using the metrics, namely specificity, sensitivity, and accuracy, with the values of 90.757%, 92.225%, and 92.122%, respectively.