Table 6. Conventional and proposed Seg-Net best performing training and validation results with various evaluation metrics.

Model	Loss	Dice	IoU	Recall	Precision	Accuracy
Proposed Seg-Net training	−0.9612	0.9612	0.9529	0.9701	0.9776	0.9868
Proposed Seg-Net validation	−0.9494	0.9494	0.9293	0.9550	0.9662	0.9803