Evaluation of Liver Fibrosis Using Texture Analysis on Combined-Contrast-Enhanced Magnetic Resonance Images at 3.0T

Table 4

Fibrosis prediction model parameters (texture versus %-collagen).

	Source image	Texture class	Texture feature
1	Original	Gaussian mixture model	STD of the lower intensity pixels
2	Original	Voronoi polygons	Mean of the 2nd order inertial moment
3	Original	Voronoi polygons	STD of the 1st order inertial moment
4	Gradient	Voronoi polygons	Mean of the 2nd order inertial moment
5	Gradient	Gaussian mixture model	STD of the lower intensity pixels
6	Laplacian	Voronoi polygons	Mean of the 3rd order inertial moment

Six most predictive texture features, from strongest to weakest. Keys: STD: standard deviation, AIC: Akaike Information Criterion, inertial moments: mathematical description the shape/area of the Voronoi polygons (see supplementary materials).