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).
ā
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).