Skip to main content
. 2020 Dec 31;17(9):6489–6498. doi: 10.1109/TII.2020.3048391

Fig. 5.

Fig. 5.

Schematic representation of the proposed tri-level attention-based segmentation network (TA-SegNet) integrating numerous tri-level attention unit (TAU) modules for semantic gap reduction between encoder and decoder modules as well as for efficient reconstruction of lesion mask.