Skip to main content
. Author manuscript; available in PMC: 2023 Mar 27.
Published in final edited form as: Med Image Anal. 2022 Dec 14;84:102726. doi: 10.1016/j.media.2022.102726

Fig. 1.

Fig. 1.

Visualization of the input images with object masks (a) and three corresponding deep features (b)–(d) extracted from three convolutional units. (b) shows that the activated values are on the background pixels/voxels, (c) shows the activated values are on the object pixels/voxels and (d) shows the activated values are on both object and background pixels/voxels.