Cell segmentation

import lazyslide as zs

wsi = zs.datasets.lung_carcinoma(with_data=False)

wsi

WSI: /Users/yzheng/Library/Caches/lazyslide/lung_carcinoma.ndpi
Reader: openslide
Dimensions: 15616×16384 (h×w), 8 Pyramids
Pixel physical size: 0.23 MPP (40X)

SpatialData object
└── Images
      └── 'wsi_thumbnail': DataArray[cyx] (3, 1817, 1906)
with coordinate systems:
    ▸ 'global', with elements:
        wsi_thumbnail (Images)

We are going to use instanseg for cell segmentation. instanseg runs better at mpp=0.5 with tile size of 512

zs.pp.find_tissues(wsi)
zs.pp.tile_tissues(wsi, 512, background_fraction=0.95, mpp=0.5)

zs.pl.tiles(wsi, linewidth=0.4)

zs.seg.cells(wsi)

v = zs.pl.WSIViewer(wsi)
v.add_image()
v.add_polygons("cells", linewidth=0.1)
v.add_zoom(6000, 7500, 8100, 8600)
v.show()

<Axes: >

zs.seg.nulite(wsi)

v = zs.pl.WSIViewer(wsi)
v.add_image()
v.add_polygons("cell_types", color_by="name")
v.add_zoom(6000, 7500, 8100, 8600)
v.show()

<Axes: >