The psc-CVM assessment system: A three-stage type system for CVM assessment based on deep learning

BMC Oral Health

Table 2 Precision, recall rates and F1 score of the psc-CVM assessment system on test set for each CVM subgroup

	Precision	Recall	F1 score	Sample size of each subgroup
CVS 1	0.8559	0.7509	0.8000	261
CVS 2	0.5704	0.6335	0.6003	262
CVS 3	0.6067	0.6639	0.6340	244
CVS 4	0.7510	0.6592	0.7021	270
CVS 5	0.6760	0.7137	0.6943	269
CVS 6	0.8185	0.8117	0.8151	239

Precision = TP/TP + FP; Recall = TP/TP + FN; F1 score = 2*Precision*Recall/Precision + Recall. TP is true CVS, cervical vertebral maturation stage; FP is false positive, FN is false negative, and TN is true negative. Precision, Recall and F1 score are calculated with confusion matrix in Fig. 4

ISSN: 1472-6831