Diabetic Retinopathy (DR) is a preva‎lent complication of diabetes mellitus and is a primary cause of avoidable blindness globally. It causes lesions on the retina that affect vision. If this issue is diagnosed at an early stage, it is possible to treat or prevent its progression and can significantly reduce the risk of vision loss. Medical experts recommend at least annual DR screening for diabetic patients via retinal fundus photography or personally dilated eye examinations. Recently, Deep learning, a widely used technique in medical image analysis and classification applications, has demonstrated promising results and efficiency in various fields, including DR detection. However, the development and validation of deep learning models for DR detection require large datasets and careful eva‎luation. Despite these challenges, deep learning holds great potential as a tool for early detection of diabetic retinopathy, which could ultimately improve patient outcomes and prevent blindness. In this study, our aim is to review the use of Convolutional neural networks to identify referable diabetic retinopathy comparably or better than presented in the previous works. We discussed some of the techniques that were presented in past studies. Difference-challenging issues that require more investigation are also discussed.

5/10/2023 12:00:00 AM

79246

1402/04/19

Early detection of diabetic retinopathy using deep learning

يادگيري عميق , شبكه هاي عصبي كانولوشنال , رتينوپاتي ديابتي , تصاوير فوندوس شبكيه

Deep learning , Convolutional neural networks , Diabetic retinopathy , Retinal fundus images