Skip to main content
. Author manuscript; available in PMC: 2023 Jun 3.
Published in final edited form as: IEEE/ACM Trans Comput Biol Bioinform. 2022 Jun 3;19(3):1387–1392. doi: 10.1109/TCBB.2021.3085608

Fig. 1.

Fig. 1.

U-Net architecture. The U-Net operates by compressing the input image into a low-level feature representation at the apex of the U. Following this, the model expands this low-level representation into the predicted segmentations for the image.