R2AU-Net: Attention Recurrent Residual Convolutional Neural Network for Multimodal Medical Image Segmentation

Table 3

Performance comparison of R2AU-Net and other networks on the lung dataset.

Methods	F1-score	Sensitivity	Specificity	Accuracy	AUC
SegNet [19]	0.9515	0.9240	0.9957	0.9820	0.9598
U-Net [3]	0.9714	0.9536	0.9977	0.9892	0.9756
Attention U-Net [20]	0.9780	0.9911	0.9915	0.9915	0.9914
RU-Net [21]	0.9638	0.9734	0.9866	0.9836	0.9800
R2U-Net [21]	0.9809	0.9842	0.9946	0.9926	0.9894
Attention Res U-Net	0.9811	0.9862	0.9942	0.9927	0.9902
R2AU-Net	0.9868	0.9874	0.9968	0.9950	0.9921