lazyslide.tl.spatial_domain

spatial_domain(wsi, feature_key, tile_key='tiles', layer=None, resolution=0.1, key_added='domain')

Perform unsupervised spatial domain segmentation on a WSI using feature embeddings.

This function applies scaling, PCA, neighborhood graph construction, and Leiden clustering to identify spatial domains within the WSI based on the provided features.

Parameters:

wsiWSIData

The whole-slide image object.

feature_keystr

The key for the feature table to use.

tile_keystr, default: “tiles”

The key for the tile table.

layerstr, optional

The layer in the feature table to use for clustering.

resolutionfloat, optional

The resolution parameter for Leiden clustering. Defaults to 0.1.

key_addedstr, optional

The key under which to store the domain labels. Defaults to “domain”.

Returns:

None

The domain labels are added to the tile table in the WSIData object.

Examples

>>> import lazyslide as zs
>>> wsi = zs.datasets.sample()
>>> zs.pp.find_tissues(wsi)
>>> zs.pp.tile_tissues(wsi, 256, mpp=0.5)
>>> zs.tl.feature_extraction(wsi, "resnet50")
>>> zs.pp.tile_graph(wsi)
>>> zs.tl.spatial_features(wsi, "resnet50")
>>> zs.tl.spatial_domain(wsi, layer="spatial_features", feature_key="resnet50", resolution=0.3)