Dice Coefficient Calculator
Calculate the Dice coefficient to evaluate overlap in image segmentation tasks.
About Dice Coefficient Calculator
The Dice coefficient (F1 for sets) measures overlap between predicted and ground truth segmentation masks: Dice = 2×|Intersection| / (|Prediction| + |Ground Truth|). It ranges from 0 (no overlap) to 1 (perfect overlap) and is the standard metric for medical image segmentation tasks.
Formula
Dice Coefficient
Dice = 2 * |X ∩ Y| / (|X| + |Y|)
- |X ∩ Y|
- Number of pixels in both prediction and ground truth
Worked example
With the default values below, Dice Coefficient Calculator returns Dice Coefficient of 0.7619. Change any input above and every figure here is recalculated in your browser.
Inputs used
- Intersection (pixels)minimum 0
- 800
- Prediction Size (pixels)minimum 1
- 1,000
- Ground Truth Size (pixels)minimum 1
- 1,100
Results
- Dice Coefficient
- 0.7619
Step by step
- 1Dice = 2×Intersection / (|Pred| + |GT|)= 0.761905
Assumptions and limits
- The result is derived only from the 3 inputs listed above. Anything not among them is not part of the calculation.
- In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
- Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.
How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.
Frequently Asked Questions
How does Dice relate to IoU?
Dice = 2*IoU / (1 + IoU). Dice is always ≥ IoU for the same prediction. Both measure overlap, but Dice gives more credit for partial overlap and is preferred in medical imaging where class imbalance is severe.
Why is Dice preferred over accuracy for segmentation?
In segmentation, the background class often dominates (>95% of pixels), making pixel accuracy misleading. Dice focuses exclusively on the overlap of the foreground class of interest.