Research Communication | Open Access
Volume 2021 | Communication ID 257
Volume 2021 | Communication ID 257
| Automated detection of retinal blood vessels for the diagnosis of diabetic retinopathy by convolutional neural networks |
Ayoub Skouta, Abdelali Elmoufidi
Received |
Accepted |
Published |
January 31, 2021 |
February 15, 2021 |
March 15, 2021 |
Abstract: Early diagnosis of diabetic retinopathy is extremely important because it can prevent diabetic patients from losing their sight. Automatic detection of retinal blood vessels makes it easier to analyze and diagnose diabetic retinopathy diseases such as microaneurysms, hemorrhages, hard exudates and soft exudates (Cotton spots), which is very useful for the treatment of early diseases of the fundus. In this work, we propose a semantic segmentation method based on the U-NET architecture to detect fundus blood vessels. Since the contrast between the retinal blood vessels and the background of ...