Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor

BMC Medical Imaging

Table 3 Feature parameters differentiating between pulmonary inflammatory pseudotumor and peripheral lung cancer

Category	Parent Feature	Child Feature	P₁ -value	P₂ -value
GLCM	Cluster Prominence	135–1Cluster Prominence	0.0325	0.2731
	Correlation	333–1 Correlation	0.0111	0.0004
		333–4 Correlation	0.0497	0.0070
		45–1 Correlation	0.0128	0.0014
		45–4 Correlation	0.0020	0.0021
		45–7 Correlation	0.0025	0.0079
		90–4 Correlation	0.0028	0.0029
		90–7 Correlation	0.0086	0.0020
		135–7 Correlation	0.0265	0.0368
	Information Measure Corr1	333–4 Information Measure Corr1	0.0157	0.1208
		0–1 Information Measure Corr1	0.0128	0.0384
		45–1 Information Measure Corr1	2.97E-5	0.0018
		90–1 Information Measure Corr1	5.7E-5	0.0002
		90–4 Information Measure Corr1	0.0489	0.1070
		135–1 Information Measure Corr1	0.0137	0.0158
	Information Measure Corr2	333–1 Information Measure Corr2	0.0442	0.0140
		333–4 Information Measure Corr2	0.0442	0.0955
		0–1 Information Measure Corr2	0.0497	0.0978
		45–1 Information Measure Corr2	0.0020	0.0184
		90–1 Information Measure Corr2	0.0083	0.0130
		135–1 Information Measure Corr2	0.0168	0.0273
	Inverse Diff Moment Norm	135–7 Inverse Diff moment Norm	0.0391	0.2151
IH	Range	None	0.0169	0.0232
NIDM	Complexity	None	0.0268	0.0595
SHAPE	Compactness2	None	0.0017	0.0027
	Roundness	None	0.0083	0.0102
	Spherical Disproportion	None	0.0017	0.0020
	Sphericity	None	0.0017	0.0028
	Surface Area Density	None	0.0207	0.0443

Note: The significant difference index of Mann-Whitney U test, P1-value; the significant difference index of Binary logistic regression, P2-value; indicates a significant difference (p < 0.05)

ISSN: 1471-2342