Skip to main content
. Author manuscript; available in PMC: 2020 Jan 9.
Published in final edited form as: IEEE Access. 2019 Jan 9;7:11093–11104. doi: 10.1109/ACCESS.2019.2891970

Fig. 11.

Fig. 11.

Dice scores for the cerebrospinal fluid (CSF) segmentation, compared with the lower and higher bound trained models and the pseudo-labelling semi-supervised method for experiments with 1, 2, and 5 labeled training images. For CSF segmentation our method outperformed all other models including the higher bound model which used full labeled images instead of only using one-fifth of the labels of each training image.