Table 3.

The result of different nucleus segmentation algorithms evaluated on 250 test images; DSC (dice similarity coefficient), Std (standard deviation), ms (millisecond), M (million).

Methods	Precision		Sensitivity		DSC		Time (ms)	Trainable Parameters (M)
	Mean	Std	Mean	Std	Mean	Std
U-Net ++ 33	0.9598	0.0632	0.9873	0.0225	0.9719	0.0397	1612	0.89
Attention U-Net36	0.9478	0.0903	0.9850	0.0213	0.9633	0.0584	628	0.85
Mask R-CNN37	0.8859	0.1142	0.9680	0.0936	0.9198	0.0923	1740	44.6
Mousavi et al.35	0.9362	0.1158	0.9827	0.0310	0.9542	0.0750	47	0
Proposed method	0.9972	0.0090	0.9526	0.0300	0.9675	0.0180	45	0

Bold values Illustrate the best-obtained value.