data from RNA2seg benchmark

# Segmentation_shape_vhfi

The  folder segmentation_shape_vhfi contains the segmentation shapes used in the RNA2seg paper with the dataset from
https://vizgen.com/data-release-program/ at MERSCOPE FFPE Human Immuno-Oncology Data Release

-- Cellbound1, Cellbound3 and DAPI are the segmentations done by cellpose of the corresponding staining

-- VHFI is the cell segmentation provided by vizgen

-- annotation is the annotation done for RNA2seg paper

--RNA2seg is the segmentation done by RNA2seg

each segmentation can be loaded with :

each segmentation can be load with :

```
    import geopandas as gpd
    gdf = gpd.read_file(path2save_shape_organ / "shape.shp")
```

Staining and transcripts are available at

https://vizgen.com/data-release-program/ at MERSCOPE FFPE Human Immuno-Oncology Data Release

# Segmentation_shape_cosmx

The  folder segmentation_shape_cosmx contains the segmentation shapes used in the RNA2seg paper
with the dataset from this study :

He, S., Bhatt, R., Brown, C. et al.
High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging.
Nat Biotechnol 40, 1794–1806 (2022). https://doi.org/10.1038/s41587-022-01483-z

-- CD3, CD45, DAPI and Membrane are the segmentations done by cellpose of the corresponding staining

-- cosmx_output is the cell segmentation provided by vizgen

--RNA2seg is the segmentation done by RNA2seg

each segmentation can be loaded with :

```
    import geopandas as gpd
    gdf = gpd.read_file(path2save_shape_organ / "shape.shp")
```

Staining and transcripts were provided by the authors of the study

# mouse_ileum

The  folder mouse_ileum contains the segmentation shapes used in the RNA2seg paper with the dataset from :
Petukhov, V., Xu, R.J., Soldatov, R.A. et al.
Cell segmentation in imaging-based spatial transcriptomics.
Nat Biotechnol 40, 345–354 (2022). https://doi.org/10.1038/s41587-021-01044-w

-- cellpose is the segmentation done with cellpose by the original authors of the study

-- annotation is the annotation done for RNA2seg paper

# benchmark_staining_method
The  folder benchmark_staining_method contains the benchmarking results for
segmentation from merscope (VHFI) and cellpose.

# benchmark_point_cloud_method

The  folder point_cloud_method contains the script and the benchmarking results
on our manual annotation for ComSeg and Baysor

# CNN_trained_model

model RNA2seg-cnn used for the benchmarck

contact : alice.blondel@minesparis.psl.eu, thomas.defard@minesparis.psl.eu