An Efficient Retinal Segmentation-Based Deep Learning Framework for Disease Prediction

Table 2

STARE dataset performance with various architecture.

Network	U-Net [28]	RU-Net [4]	Dense U-net [18]	Proposed EDLFDPRS
Accuracy	96.33	97.6	97.21	97.33
score	81.22	82.63	81.47	82.3
Recall	84.27	82.61	83.17	82.12
Precision	80.07	82.16	81.92	82.52
Sensitivity	82.12	82.69	79.37	84.27
Specificity	97.97	97.28	97.47	98.57
AUC	97.82	97.15	97.45	98.84