Multi-scale characterizations of colon polyps via computed tomographic colonography

Visual Computing for Industry, Biomedicine, and Art

Table 8 Four evaluation measurements for seven methods

Method	AUC	Accuracy	Specificity	Sensitivity
HF	0.8751	0.8151	0.8093	0.7693
eHM	0.8863	0.8363	0.8281	0.7256
eHM + KLT	0.9073	0.8873	0.8812	0.8475
CoLIAGe	0.9229	0.8835	0.8393	0.8331
VGG16	0.8234	0.8404	0.8069	0.8066
LMD + LMS	0.9449	0.8934	0.9019	0.8851
LMS + LMA	0.9447	0.8915	0.8801	0.9031

HF Haralick feature, eHM Extended Haralick measure, KLT Karhunen-Loeve transform, LMD Learning model by multiple displacements, LMS Learning model by multiple strides, LMA Learning model by multiple angles, CoLIAGe Co-occurrence of local anisotropic gradient orientations, AUC Area under the curve of receiver operating characteristic curve