lazyslide.metrics.segmentation.dice

dice(stats)

Compute Dice coefficient from segmentation statistics.

The Dice coefficient (also known as Sørensen-Dice coefficient or F1 score) measures the similarity between two sets by computing twice the size of their intersection divided by the total size of both sets.

Parameters:

statsSegmentationStats

Segmentation statistics containing true positives (tp), false positives (fp), and false negatives (fn).

Returns:

float

Dice coefficient in the range [0, 1], where 1 indicates perfect overlap. A small epsilon (1e-8) is added to the denominator to avoid division by zero.

Notes

Dice = 2 * TP / (2 * TP + FP + FN) This is mathematically equivalent to the F1 score.