Skip to main content
. Author manuscript; available in PMC: 2022 Jan 1.
Published in final edited form as: Med Image Anal. 2020 Oct 17;67:101880. doi: 10.1016/j.media.2020.101880

Fig. 5.

Fig. 5.

Top: Box plots with the DICE measure between the true mask and the masks aligned using the registration transforms. Bottom: Box plots of the average consistency of the registered masks. Both LiMo-MoCo and REFVOl attained the highest DICE coefficient (0.953 and 0.958), however, the masks registered with LiMo-MoCo were more self-consistent than the rest of the algorithms.