SEGAN-BASED LESION SEGMENTATION AND OPTIMIZED RideNN FOR DIABETIC RETINOPATHY CLASSIFICATION

Abstract

The most significant issue with diabetes is diabetic retinopathy (DR), which is the primary cause of blindness. DR typically develops no symptoms at the beginning of the disease, thus numerous physical examinations, including pupil dilation and a visual activity test, are necessary for DR identification. Due to the differences and challenges of DR, it is more challenging to identify it during the manual assessment. For DR patients, visual loss is prevented thanks to early detection and accurate therapy. Therefore, it is even more necessary to classify the severity levels of DR in order to provide a successful course of treatment. This study develops a deep learning method based on chronological rider sea lion optimization (CRSLO) for the classification of DR. The segmentation process divides the image into multiple subgroups, which is necessary for the appropriate detection and classification procedure. For the efficient identification of DR and classification of DR severity, the deep learning approach is used. Additionally, the CRSLO scheme is used to train the deep learning technique to achieve higher performance. With respect to testing accuracy, sensitivity, and specificity of 0.9218, 0.9304 and 0.9154, the newly introduced CRSLO-based deep learning approach outperformed other existing DR classification techniques like convolutional neural networks (CNNs), deep convolutional neural network (DCNN), synergic deep learning (SDL), HPTI-V4 and DR[Formula: see text]GRADUATE. The Speech Enhancement Generative Adversarial Network (SEGAN) model in use also produced increased segmentation accuracy of 0.90300.