. Author manuscript; available in PMC: 2021 Aug 1.

Published in final edited form as: IEEE Trans Med Imaging. 2021 Feb 2;40(2):699–711. doi: 10.1109/TMI.2020.3035253

Table VIII.

Comparison Between Different Variants of Scale Attention-Based Networks. L-A (1-K) Represents the Features From Scale 1 To K Were Concatenated For Scale Attention

Network	Placenta		Fetal Brain
Network	Dice(%)	ASSD(pix)	Dice(%)	ASSD(pix)
Baseline	84.79±8.45	0.77±0.95	93.20±5.96	0.38±0.92
L-A(l-2)	86.17±6.02	0.59±0.41	94.19±3.29	0.27±0.36
L-A(1-3)	86.17±6.53	0.50±0.37	94.61±3.13	0.54±0.63
L-A(1-4)	86.21+5.96	0.52±0.58	95.18±3.22	0.27±0.59
L-A(1-5)	86.09±6.10	0.61±0.47	95.05±2.51	0.24±0.47