Skip to main content
. Author manuscript; available in PMC: 2021 Mar 1.
Published in final edited form as: IEEE Trans Med Imaging. 2020 Mar 5;39(9):2881–2892. doi: 10.1109/TMI.2020.2972547

Fig. 10.

Fig. 10

Per-voxel mean and uncertainty estimations on the CGM segmentation task for classically augmented and motion augmented models. Results are shown for a test-retest pair for which one scan is heavily artefacted and for the corresponding motion-corrected image, as output by the artefact removal CNN. Bottom row: KL-divergence (KLD) between the probability distributions produced by each model.