An Edge-Assisted Computing and Mask Attention Based Network for Lung Region Segmentation

Table 4

Results of EAM-Net and the state-of-the-art lung region segmentation methods on the JSRT dataset.

Methods	PA (%)	Dice (%)	JA (%)
Bayesian feature pyramid network [21]	96.24	93.13	87.14
Kim and Lee [32]	98.17	96.68	93.57
Kholiavchenko et al. [22]	98.38	97.06	94.29
Yahyatabar et al. [17]	98.58	97.42	94.97
Novikov et al. [15]	98.55	97.36	94.86
SED [9]	98.62	97.51	95.14
EAM-Net	98.96	98.11	96.15

Bold values represent the the highest performance for each performance metric.