Table 3.

Evaluation metrics

Metrics	Formula
Accuracy	$\frac{TP+TN}{TP+TN+FP+FN}$
Sensitivity (or recall)	$\frac{\mathit{TP}}{TP+FN}$
Specificity	$\frac{\mathit{TN}}{FP+TN}$
Precision	$\frac{\mathit{TP}}{TP+TN}$
F1 score	$2\times \frac{\text{Precision}\times \text{Recall}}{\text{Precision}+\text{Recall}}$
Area under the receiving operator	$\frac{S_p-\frac{n_p\left(n_n+1\right)}{2}}{n_p{n}_n}$
Jaccard index	$\frac{\left|X\cap Y\right|}{\left|X\right|+\left|Y\right|+\left|X\cap Y\right|}$
DICE score	$2\frac{\left|X\cap Y\right|}{\left|X\right|+\left|Y\right|}$

FN false negative, FP false positive, TN true negative, TP true positive, S_p sum of all positive ranked samples, n_p number of negative samples, n_p number of positive samples, |X| and |Y|: representing the X and Y segmentations, respectively; |X∩Y|: representing the intersection between X and Y