Texture Analysis of Brain MRI Data

Kovalev V.A.1, Kruggel F.2

1 Max-Planck-Institute of Cognitive Neuroscience, Leipzig, 2 University of California, Irvine

It has long been recognized that textural features play an important role in a wide variety of image analysis problems. Very little work done in the area of characterization and analysis of 3D textures. Continuous increase of spatial resolution of neuroimaging techniques and strong practical needs challenge for new, natively 3D texture analysis methods. Our approach is based on extended, multi-sort co-occurrence matrices that combine intensity, gradient and anisotropy image features in a systematic and consistent way. Proposed co-occurrence descriptors are reflection and translation invariant and, to some extent, rotation-insensitive. Normalization of co-occurrence descriptors provides a basis for inter-subject analysis and comparisons of brain regions with different size. A comparative study revealed that general 6D matrices are the most sensitive texture descriptors. As an example we used the method to study cerebral asymmetry in a large population sample.

Brain Asymmetry

Gender-related differences in cerebral asymmetry (n=290, age 18-32 J.) as revealed by texture analysis are depicted. In males, asymmetries are more profound, especially at the dorsal third of the first temporal gyrus, the postcentral gyrus and the occipital white matter compartment.


Kovalev V.A., Kruggel F., von Cramon, D.Y., Gertz, H.J. (2001) 3D Texture Analysis of MR Brain Datasets. IEEE Transactions on Medical Imaging 20, 424-433.

Kovalev V.A., Kruggel F., von Cramon, D.Y. (2002) Structural Brain Asymmetry as Revealed by 3D Texture Analysis of Anatomical MR Images. In: 16th International Conference on Pattern Recognition (Quebec), pp. I-808-811. IEEE Computer Society Press, Piscataway.

Kovalev V.A., Kruggel F., von Cramon, D.Y., (2003) Gender and Age Effects in Structural Brain Asymmetry as Measured by MRI Texture Analysis. NeuroImage 19, 895-905.

Kovalev V.A., Kruggel F. (2004) A new Method for Quantification of Age-Related Brain Changes. In: 17th International Conference on Pattern Recognition, pp. I-808-811. IEEE Computer Society Press, Piscataway.

Kovalev V., Kruggel F. (2007) Texture Anisotropy of the Brain's White Matter as Revealed by Anatomical MRI. IEEE Transactions on Medical Imaging 26, 678-685.