Texture analysis on MR images helps predicting non-response to NAC in breast cancer

BMC Cancer

Table 3 List of parameters used for breast lesion characterization

Parameter type		Parameter description
Kinetic
1	Wash-in rate	Rate of contrast material uptake
2	Maximal amplitude	Maximal contrast enhancement
3	Wash-out rate	Rate of contrast enhancement washout
Geometric (according to BI-RADS lexicon)
4	Mass	3D space-occupying lesion that comprises one process,
		usually round, oval, lobular or irregular in shape
5	non Mass	Enhancement of an area that is not a mass
Texture
6^a	Energy	Measure of local uniformity of grey levels
7^a	Entropy	Measure of randomness of grey levels
8^a	Contrast	Measure of the amount of grey levels variations
9^a	Homogeneity	Measure of local homogeneity. It increases with less contrast
10^a	Correlation	Measure of linear dependency of grey levels of neighbouring pixels
11^a	Inverse difference moment	Measure of local homogeneity of the grey levels
12^a	Sum average	Measure of overall image brightness
13^a	Sum variance	Measure of how spread out the sum of the grey levels of voxel pair is
14^a	Difference in variance	Measure of variation in the difference in gray levels between voxel pairs
15^b	SRE	Short Run Emphasis (first property of run-length distribution)
16^b	LRE	Long Run Emphasis
17^b	GLN	Gray-Level Nonuniformity
18^b	RLN	Run-Length Nonuniformity
19^b	RP	Run percentage
20^b	LGRE	Low Gray-Level Run Emphasis
21^b	HGRE	High Gray-Level Run Emphasis
22^b	SRLGE	Short Run Low Gray-Level Emphasis
23^b	SRHGE	Short Run High Gray-Level Emphasis
24^b	LRLGE	Long Run Low Gray-Level Emphasis
25^b	LRHGE	Long Run High Gray-Level Emphasis

ISSN: 1471-2407