Skip to main content
. Author manuscript; available in PMC: 2022 Jul 3.
Published in final edited form as: IEEE J Biomed Health Inform. 2022 Jul 1;26(7):3185–3196. doi: 10.1109/JBHI.2022.3149754

Fig. 1.

Fig. 1.

The proposed deep network. Context-aware patch swap propagates boundary high frequencies to fill the hole. The symmetry loss is used to constrain the complete F2I translated image. Of note, the training images include both normal and pathological images with irregular holes.