Research Article
Pixel-Boundary-Dependent Segmentation Method for Early Detection of Diabetic Retinopathy
Table 1
Analysis summary of features.
| | Metrics | AD-FF | PSO-GIT2FMFs | DS-KL | Proposed improvements |
| | Accuracy | 0.872 | 0.923 | 0.9623 | 6.48% high | | Precision | 0.905 | 0.936 | 0.982 | 6.15% high | | Error | 0.071 | 0.052 | 0.0357 | 7.74% less | | Sensitivity | 0.915 | 0.954 | 0.989 | 7.4% high | | Specificity | 0.902 | 0.941 | 0.974 | 7.2% high | | MCC | 0.786 | 0.813 | 0.877 | 9.1% high |
|
|