Skip to main content
. Author manuscript; available in PMC: 2024 Jan 1.
Published in final edited form as: IEEE Trans Radiat Plasma Med Sci. 2022 Jun 30;7(1):33–40. doi: 10.1109/trpms.2022.3187595

Fig. 3.

Fig. 3.

Proposed SSTrans-3D. The slices/volumes in red represent the network-reconstructed results. The patches in blue represent the input to the network (images reconstructed using one-angle data). Structures of encoder and decoder are the same as the proposed in the original Transformer without normalization layers. During the repeating process, already reconstructed slices (red) are used to replace the one-angle patches in the input to the decoder part of the network.