A method is proposed for three-dimensional (3-D) texture analysis of magnet
ic resonance imaging brain datasets, It is based on extended, multisort co-
occurrence matrices that employ intensity, gradient and anisotropy image fe
atures in a uniform way. Basic properties of matrices as well as their sens
itivity and dependence on spatial image scaling are evaluated. The ability
of the suggested 3-D texture descriptors is demonstrated on nontrivial clas
sification tasks for pathologic findings in brain datasets.