Abstract

Diabetic Retinopathy (DR) is a general difficulty of diabetes mellitus, resulting in retina damage that affects vision. If left undetected, it has the potential to cause blindness. Regrettably, DR is irreversible, and only treatment can maintain vision. The early analysis and treatment of DR can considerably decrease the potential for visual impairment. Unlike computer-aided diagnosis (CAD) systems, the manual diagnostics method of DR retinal images by ophthalmologists is effort-, cost-, and time-consuming and liable to misdiagnoses. In present scenario, deep learning (DL) has become the classical approach that has remarkable performance in different fields, mainly in medical image classification and analysis. Convolutional neural networks (CNN) are more commonly deployed as a DL system in medical image analysis and they are very efficient. In this manuscript, we offer the design of Tent Chaotic Dung Beetle Optimization with Deep Ensemble Learning for Diabetic Retinopathy (TCDBO-DELDR) Recognition approach on Fundus Imaging. The foremost intention of the TCDBO-DELDR technique is to automate the DR detection process on fundus images via the ensemble DL model. To eradicate the noise, the TCDBO-DELDR technique initially exploits the median filtering (MF) methodology. In the TCDBO-DELDR model, the Inception v3 (IV3) model is employed for the purposes of feature extractor. For the hyperparameter tuning procedure, the TCDBO technique is used for IV3 model. Finally, the detection of DR is carried out utilizing an ensemble of three classifiers namely Deep Feedforward Neural Network (DeepFFNN), Convolutional FFNN (ConvFFNN), and Convolutional bi-directional long short-term memory (ConvBLSTM). For ensuring the enhanced efficiency of the TCDBO-DELDR system in the DR detection procedure, a widespread experimental study is prepared on the benchmark DR database. The results illustrate the superior efficiency of the TCDBO-DELDR technique with other recent DL approaches.