CMMCSegNet: Cross-Modality Multicascade Indirect LGE Segmentation on Multimodal Cardiac MR

Table 3

Performance comparisons for the number of cascade generators on the multicascade pix2pix segmentation network, where “P-” means to use perceptual loss and “simple” means to use cascade generator with the simplified U-net version (where the number of upsampling/downsampling layers in the middle part of the U-net generators is reduced from (, , ) to (, , ) for generators (, ), respectively).

Number of cascades	LV	MYO	RV
1
+P-
2
+P-
+P-+simple
3
+P-
+P-+simple
4
+P-
+P-+simple