scallops.segmentation.util.image2mask

scallops.segmentation.util.image2mask(image, threshold='Li', threshold_correction_factor=1, rolling_ball=False, sigma=None, depth=30)

Convert an image to a mask.

Parameters:

  • image (DataArray) – Image with the dimensions (t, c, y, x)

  • threshold (Literal['Li', 'Otsu', 'Local'] | float) – One of Li, Otsu, Local If Li, use Li’s iterative Minimum Cross Entropy method threshold_li(). If Otsu, use Otsu’s method threshold_otsu(). If ‘Local’, compute mask using image > smoothed * threshold_correction_factor

  • threshold_correction_factor (float) – Factor to adjust the computed threshold by.

  • threshold – Threshold to apply to mask.

  • rolling_ball (bool) – If true, apply skimage.restoration.rolling_ball subtraction to mask prior to calculating threshold

  • sigma (float | None) – sigma (optional) gaussian filter sigma to smooth the image prior to computing threshold

  • depth (int) – The number of elements that each block should share with its neighbors when using dask

Returns:

Image, mask, and threshold if threshold is Li or Otsu.

Return type:

tuple[ndarray | Array, ndarray | Array, float | None]