Table 3.

Comparison of our method with other state-of-the-art segmentation methods published previously in terms of sensitivity and specificity (—— means the author did not segment the corresponding plaques).

Methods		Fibrous	Calcified	Lipid
Our method	Sensitivity	0.95 ± 0.03	0.87 ± 0.06	0.81 ± 0.11
	Specificity	0.97 ± 0.02	0.92 ± 0.06	0.96 ± 0.03
Deep learning method	Sensitivity	——	0.85 ± 0.07	0.87 ± 0.07
	Specificity	——	0.94 ± 0.02	0.90 ± 0.05
Machine learning method	Sensitivity	0.81	0.65	0.80
	Specificity	0.91	0.91	0.88
Other patch-based method	Sensitivity	0.89	0.34	0.88
	Specificity	0.98	0.97	0.98