Research Article
Pixel-Boundary-Dependent Segmentation Method for Early Detection of Diabetic Retinopathy
Table 2
Analysis summary for classifications.
| | Metrics | AD-FF | PSO-GIT2FMFs | DS-KL | Proposed improvements |
| | Accuracy | 0.873 | 0.911 | 0.9651 | 7.31% high | | Precision | 0.909 | 0.931 | 0.9824 | 6.24% high | | Error | 0.077 | 0.059 | 0.0389 | 8.73% less | | Sensitivity | 0.874 | 0.916 | 0.953 | 7.9% high | | Specificity | 0.891 | 0.946 | 0.976 | 8.5% high | | MCC | 0.793 | 0.816 | 0.852 | 5.9% high |
|
|