Texture analysis of pulmonary parenchymateous changes related to pulmonary thromboembolism in dogs – a novel approach using quantitative methods

Table 1 Overview of the 22 texture features

	First and second order statistical parameters	Abbreviation
1	Autocorrelation [34]	autoc
2	Contrast [13, 34]	contr
3	Correlation (Matlab)	corrm
4	Correlation [13, 34]	corrp
5	Cluster prominence [34]	cprom
6	Dissimilarity [34]	dissi
7	Energy [13, 34]	energ
8	Entropy [34]	entro
9	Inverse difference is homogeneity [22]	homom
10	Homogeneity [34]	homop
11	Maximum probability [34]	maxpr
12	Sum of squares (variance) [13]	sosvh
13	Sum of average [34]	savgh
14	Sum of variance [34]	svarh
15	Sum of entropy [34]	senth
16	Difference variance [34]	dvarh
17	Difference entropy [34]	denth
18	Information measure of correlation 1 [34]	inf1h
19	Information measure of correlation 2 [34]	inf2h
20	Inverse difference normalized [22]	indnc
21	Inverse different moment normalized [22]	indmc
22	Cluster shade [34]	cshad

Overview of and nomenclature for the 22 texture features derived from the grey level co-occurrence matrices generated. One parameter was created in Matlab (noted in brackets)

ISSN: 1746-6148