Table 4.

Performance evaluation metrics used in the research of the above literature for deep learning in DFUs.

Evaluation metrics	Formula and the source literature	Source references
Accuracy	$\text{Accuracy}=\frac{TN+TP}{TN+TP+FN+FP}$ (35)	(3, 28–30, 43, 50)
Sensitivity	Sensitivity=TP/(TP+FN) (35)	(29, 30)
Specificity	Sensitivity=TN/(TN+FP) (35)	(29, 30)
Precision	Precision=TP/(FP+TP) (35)	(8, 27, 29, 39, 51)
Recall	Recall=TP/(TP+FN) (35)	(27)
AUC	$\text{AUC}=\frac{{\displaystyle {\sum }_{in{s}_i\in postiveclass}ran{k}_{in{s}_i}-\frac{M\times \left(M+1\right)}{2}}}{M\times N}$ (35)	(10, 29, 30)
F1-Score	$\text{F Score}=\text{F Score}=\frac{2\times Recall\times Precision}{Recall+Precision}$ (35)	(27, 28, 39, 45)
Average precision (AP)	$\text{AP}=\frac{{\displaystyle {\sum }_{q=1}^Q\frac{T{P}_i}{T{P}_i+F{P}_i}}}{Q}$ (35)
Mean average precision (mAP)	$\text{mAP}=\frac{{\displaystyle {\sum }_{q=1}^{Q}AveP\left(q\right)}}{Q}$ (35)	(43, 45, 51, 53)
Dice similarity coefficient (DSC)	$\text{DSC}=\frac{2\times TP}{2\times TP+FP+FN}$ (50)	(50)
Union index (IoU)	$\text{IoU}=\frac{TP}{TP+FP+FN}$ (50)	(50)