Name
Abstract | ||
|---|---|---|
Presence of exudates on a retina is an early sign of diabetic retinopathy, and automatic detection of these can improve the diagnosis of the disease. Convolutional Neural Networks (CNNs) have been used for automatic exudate detection, but with poor performance. This study has investigated different deep learning techniques to maximize the sensitivity and specificity. We have compared multiple deep learning methods, and both supervised and unsupervised classifiers for improving the performance of automatic exudate detection, i.e., CNNs, pre-trained Residual Networks (ResNet-50) and Discriminative Restricted Boltzmann Machines. The experiments were conducted on two publicly available databases: (i) DIARETDB1 and (ii) e-Ophtha. The results show that ResNet-50 with Support Vector Machines outperformed other networks with an accuracy and sensitivity of 98% and 0.99, respectively. This shows that ResNet-50 can be used for the analysis of the fundus images to detect exudates. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.compbiomed.2018.10.031 | Computers in Biology and Medicine |
Keywords | Field | DocType |
Exudate detection,Deep learning,Convolutional neural networks,Deep residual networks,Discriminative restricted Boltzmann machines,Diabetic retinopathy | Computer vision,Boltzmann machine,Pattern recognition,Convolutional neural network,Computer science,Support vector machine,Fundus (eye),Exudate,Artificial intelligence,Deep learning,Discriminative model | Journal |
Volume | ISSN | Citations |
104 | 0010-4825 | 4 |
PageRank | References | Authors |
0.42 | 30 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Parham Khojasteh | 1 | 4 | 0.42 |
| Leandro Aparecido Passos Júnior | 2 | 4 | 0.42 |
| Tiago de Carvalho | 3 | 37 | 10.29 |
| Edmar Rezende | 4 | 4 | 0.42 |
| Behzad Aliahmad | 5 | 8 | 3.51 |
| João P. Papa | 6 | 689 | 46.87 |
| Dinesh Kant Kumar | 7 | 168 | 28.34 |