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

Table 3

CHASE_DB1 dataset performance with various architecture.

Network	U-Net [28]	RU-Net [4]	Dense U-net [18]	Proposed EDLFDPRS
Accuracy	96.12	96.12	96.43	97.44
score	78.23	79.81	79.98	81.94
Recall	82.45	82.74	82.58	83.92
Precision	82.21	83.23	83.05	80.07
Sensitivity	82.45	85.55	78.86	83.92
Specificity	97.98	97.17	97.55	98.45
AUC	98.05	98.11	98.17	98.79