Overlapping and cross nuclei segmentation

[chenyhvvvv]

Hi! Thank you for your excellent tools.

/home/yhchenmath/.cargo/bin/proseg --output-spatialdata /import/home2/yhchenmath/Code/Triplet/Data/XeniumHumanLungPreview/output.zarr --xenium /import/home2/yhchenmath/Dataset/DeconvSeg/xenium_human_lung_preview/transcripts.csv

And I get a bad and cross nuclei segmentation with spatialdata visualization. Is there something wrong with my trial?

[dcjones]

Hi, thanks for using proseg. Version 3 was was inadvertently outputing a different polygon estimation (unioned polygons) than version 2 (consensus 2d polygons), which made the the overlap seem worse than it is in visualizations. I've just release 3.0.3 which should fix that.

I should also note that your visualization here isn't quite right. Proseg segments using voxels so its boundaries are always made up of horizontal and vertical line segments.