Search

Diabetic retinopathy (DR) and age related macular degeneration (AMD) becomes widespread microvascular illness among diabetic patients. Traditional retinal fundus image classification requires visual inspection by the professionals, which is time consuming and requires expert's knowledge. Earlier identification of retinal diseases is essential to delay or avoid vision deterioration and vision loss. The recently developed artificial intelligence (AI) and deep learning (DL) models can be employed for accurate retinal image classification. With this motivation, this study designs a new artificial intelligence with optimal deep convolutional neural network (AI‐ODCNN) technique for retinal fundus image classification. Primarily, the proposed model uses the Gaussian Blur based noise removal and contrast enhancement technique (CLAHE) based contrast enhancement technique to pre‐process the retinal fundus image. In addition, morphology and contour based image segmentation is performed. Moreover, the deep CNN with RMSProp Optimizer is employed for retinal fundus image classification. A wide range of simulations was performed on the automated retinal image analysis and structured analysis of the retina and the outcomes are examined with respect to various measures. The simulation outcomes ensured the better performance of the proposed approach related to other recent algorithms with maximum accuracy of 96.47%. [ABSTRACT FROM AUTHOR]

Retinal fundus images are widely employed to screen for various eye diseases, giving them significant clinical importance. Investigation of medical images has been considerably enhanced by using deep learning (DL) approaches which enables automated learning of the related features for particular tasks rather than handcrafted techniques. In this view, this study develops an Optimal Deep Convolutional Neural Network for Retinal Fundus Image Classification (ODCNN-RFIC) model. The presented technique involves pre-processing in two stages: Guided Filter (GF) and Adaptive Median Filter (AMF). The U-Net technique is employed for image segmentation, allowing the infected regions to be detected appropriately. Additionally, the EfficientNet feature extractor is utilized for generating feature vectors. Finally, the mayfly optimization with kernel extreme learning machine (MFO-KELM) model is applied as a classification model. The experimental values highlighted the superior performance of the proposed method on existing algorithms. [ABSTRACT FROM AUTHOR]