overlay_prediction_mask¶

overlay_prediction_mask(img, prediction, alpha=0.35, label_info=None, min_val=0.0, ax=None, *, return_ax)[source]¶

Generate an overlay, given a 2D prediction map.

Parameters:

  • img (ndarray) – Input image to overlay the results on top of.

  • prediction (ndarray) – 2D prediction map. Multi-class prediction should have values ranging from 0 to N-1, where N is the number of classes.

  • label_info (dict) – A dictionary containing the mapping for each integer value within prediction to its string and color. [int] : (str, (int, int, int)). By default, integer will be taken as label and color will be random.

  • min_val (float) – Only consider predictions greater than or equal to min_val. Otherwise, the original WSI in those regions will be displayed.

  • alpha (float) – Opacity value used for the overlay.

  • ax (ax) – Matplotlib ax object.

  • return_ax (bool) – Whether to return the matplotlib ax object. If not, then the overlay array will be returned.

Returns:

If return_ax is True, return the matplotlib ax object. Else, return the overlay array.

Return type:

np.ndarray | Axes

Examples

>>> from tiatoolbox.utils.visualization import overlay_prediction_mask
>>> import numpy as np
>>> from matplotlib import pyplot as plt
>>> # Generate a random example; replace with your own data
>>> img = np.random.randint(0, 256, size=(256, 256, 3), dtype=np.uint8)
>>> prediction = np.random.randint(0, 3, size=(256, 256), dtype=np.uint8)
>>> label_info = {
...     0: ("Background", (0, 0, 0)),
...     1: ("Tumor", (255, 0, 0)),
...     2: ("Stroma", (0, 255, 0))
... }
>>> # Example usage of overlay_prediction_mask
>>> ax = overlay_prediction_mask(
...     img=img,
...     prediction=prediction,
...     alpha=0.5,
...     label_info=label_info,
...     min_val=0.0,
...     ax=None,
...     return_ax=True
... )
>>> plt.show()