Skip to main content
. Author manuscript; available in PMC: 2024 Sep 16.
Published in final edited form as: Nat Med. 2024 Mar 19;30(3):850–862. doi: 10.1038/s41591-024-02857-3

Extended Data Fig. 7: Visualizing segmentation results in SegPath.

Extended Data Fig. 7:

Using the Mask2Former head, we visualize the tissue segmentation of each class in SegPath created by all pretrained encoders. Overall, we find that UNI is competitive with convolutional and hierarchical models like CTransPath and REMEDIS in matching the segmentation masks obtained via immunofluorescence and DAPI nuclear staining.