Table 3 The performance of the one-stage method for no-DR and DR categories
From: General deep learning model for detecting diabetic retinopathy
DataBase | Accuracy (%) | Sensitivity (%) | Specificity (%) | Precision (%) |
|---|---|---|---|---|
Train & validation set | ||||
EyePACs | 89.79 | 91.20 | 85.87 | 94.75 |
Test set | ||||
DIARETDB0 | 61.54 | 100 | 54.55 | 28.57 |
DIARETDB1 | 47.19 | 75.00 | 45.88 | 06.12 |
e-ophtha | 67.82 | 54.10 | 86.67 | 84.80 |
MESSIDOR | 59.39 | 99.81 | 28.09 | 51.81 |
DRIVER | 87.50 | 100 | 28.57 | 86.84 |