Is the slide resolution taken into account when extracting tiles ?

[CharlieCheckpt]

Hello,
Thank you for this nice package !

I used histoprep on two slides with different resolutions.
One was scanned at a mpp of 0.25, the other one with a mpp of 0.5. It seems that when extracting the tiles with the following code, it reads images of size 512x512 at the lowest openslide level, without taking in account the resolution. This implies that the cell scale etc.. differs between the images extracted on the two different slides (see images below, first is mpp 0.25, second is mpp 0.5).

from histoprep import SlideReader

# Read slide image.
reader = SlideReader("./slides/slide_with_ink.jpeg")
# Detect tissue.
threshold, tissue_mask = reader.get_tissue_mask(level=-1)
# Extract overlapping tile coordinates with less than 50% background.
tile_coordinates = reader.get_tile_coordinates(
    tissue_mask, width=512, overlap=0.5, max_background=0.5
)
# Save tile images with image metrics for preprocessing.
tile_metadata = reader.save_regions(
    "./train_tiles/", tile_coordinates, threshold=threshold, save_metrics=True
)

Is this an intended behaviour or am I missing something?
Best

[jopo666]

This is intended behaviour. If this feature is something that you need feel free to add a pull request! This could be implemented for example as a helper method get_width_from_mmp, which could then be passed into get tile coordinates.