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

Figure 4

Qualitative comparisons of our CMMCSegNet for different number of cascade blocks on fake bSSFP translated from LGE modality. From left to right: LGE, bSSFP translated by Cycle-GAN, ground truth with zoom-in views, and prediction results with zoom-in views using 1-4 cascade blocks.