Optimizing Diabetic Retinopathy Diagnostics: A Novel Approach Using R-VCANet and Artificial Rabbit Optimization

Untreated diabetic retinopathy (DR), which damages the retina's blood vessels, is a leading cause of vision loss. Diabetic retinopathy (DR) causes most adult vision loss and blindness Worldwide. Diabetes patients, especially those with poorly controlled blood sugar, are affected. DR causes blurriness, floaters, and blindness by damaging retinal blood vessels.The eye's intricate anatomy makes manual diabetic retinopathy detection laborious and error-prone. Many automated methods can detect diabetic retinopathy in fundus images. These methods cannot depict the complexity of diabetic retinopathy, especially in its early stages. A vertex component analysis network (R-VCANet) and a rolling guidance filter are used to identify diabetic retinopathy using Artificial Rabbit Optimisation. This method uses powerful visual component analysis and a unique optimisation method to improve retinal imaging feature extraction and classification. The model accurately detects diabetic retinopathy pathological indicators using Artificial Rabbit Optimisation (ARO) to optimise network parameters. This makes it a promising early diagnosis tool that could reduce diabetes-related vision loss.