Fig. 7

VAE-based method results on Dataset 1 (MMWHS). The first column shows the original input images, the following columns show outputs of the network for progressively higher level of supervision. Rows 1–2 show reconstructed images, while row 3 shows segmentation output. The VAE-based method tries to reconstruct a source (CT) and a target (MR) image which are modality-invariant. Legend for segmentation labels as follows: LV = turquoise, LVM = orange, RV = blue, LA = green, RA = yellow, AO = grey