| Autor: |
W. R. Sam Emmanuel, A. Mary Dayana |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Proceeding of the International Conference on Computer Networks, Big Data and IoT (ICCBI-2019) ISBN: 9783030431914 |
| DOI: |
10.1007/978-3-030-43192-1_75 |
| Popis: |
Diabetic Retinopathy (DR) is one of the key symptoms of Diabetes Mellitus that is caused by the deterioration of blood capillaries which nourish the retina of the eye. The spread of the pathological lesions in the retina determine the severity of diabetic retinopathy. Therefore, it is obligatory to analyze the symptoms of DR at an early clinical stage as it prevents the progression of the disease and protects the vision. Deep learning algorithms play an important role in detecting multiple abnormalities from retinal fundus images and also highlights the areas of corresponding lesions with considerable accuracy. In the proposed method a deep convolutional neural network is designed for the segmentation of small lesions with patch-based analysis in retinal fundus images. A sliding window method was used to create image patches. The trained network analyzes the image patches and generates the probability map which in turn predicts the different types of lesions. The results obtained by the proposed work shows significantly better performance in accuracy and sensitivity when compared with other works on related tasks. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
