TISNet-Enhanced Fully Convolutional Network with Encoder-Decoder Structure for Tongue Image Segmentation in Traditional Chinese Medicine

Table 2

Description of the evaluation metrics.

Metric name	Abbr.	Range	Interpretation	Category
Dice similarity coefficient	DSC	0–1	Similarity between masks	Overlap
Hausdorff distance	HD	>0	Longest Euclidean distance between mask contours (absolute error)	Distance
Symmetric mean absolute	MSD	>0	Mean Euclidean distance between mask contours (mean error)	Distance
Surface distance precision	PPV	0–1	Low values mean that the method tends to over segment	Statistical
Sensitivity	TPR	0–1	Low values mean that the method tends to under segment	Statistical
Specificity	TNR	0–1	Quality of segmented background	Statistical