Volumetric Texture Description and Discriminant Feature Selection for MRI
This paper considers the problem of classification of Magnetic Resonance Images using 2D and 3D texture measures. Joint statistics such as co-occurrence matrices are common for analysing texture in 2D since they are simple and effective to implement. However, the computational complexity can be prohibitive especially in 3D. In this work, we develop a texture classification strategy by a sub-band filtering technique that can be extended to 3D. We further propose a feature selection technique based on the Bhattacharyya distance measure that reduces the number of features required for the classification by selecting a set of discriminant features conditioned on a set training texture samples. We describe and illustrate the methodology by quantitatively analysing a series of images: 2D synthetic phantom, 2D natural textures, and MRI of human knees.
KeywordsImage Segmentation Texture classification Sub-band filtering Feature selection Co-occurrence
Unable to display preview. Download preview PDF.
- 1.Bhalerao, A., Rajpoot, N.: Selecting Discriminant Subbands for Texture Classification. Submitted to BMVC’U3 (2003)Google Scholar
- 2.COST European Cooperation in the field of Scientific and Technical Research. COST B11 Quantitation of MRI Texture (2002), http://www.uib.no/costb11/
- 3.Cross, G.R., Jain, A.K.: Markov Random Field Texture Models. IEEE Trans. on PAMI PAMI-5(1), 25–39 (1983)Google Scholar
- 6.Fukanaga, K.: Introd. to Statistical Pattern Recognition. Academic Press, London (1972)Google Scholar
- 8.Kapur, T.: Model based three dimensional Medical Image Segmentation. PhD thesis, AI Lab, Massachusetts Institute of Technology (May 1999)Google Scholar
- 10.Eden, M., Unser, M.: Multiresolution Feature Extraction and Selection for Texture Segmentation. IEEE Trans. on PAMI 11(7), 717–728 (1989)Google Scholar
- 13.Randen, T., Håkon Husøy, J.: Filtering for Texture Classification: A Comparative Study. IEEE Trans. on PAMI 21(4), 291–310 (1999)Google Scholar
- 14.Reyes-Aldasoro, C.C., Bhalerao, A.: Sub-band filtering for mr texture segmentation. In: Proceedings of Medical Image Understanding und Analysis, Portsmouth, UK, July 2002, pp. 185–188 (2002)Google Scholar
- 18.Wilson, R., Spann, M.: Finite Prolate Spheroidal Sequences and Their Applications. IEEE Trans. on PAMI 10(2), 193–203 (1988)Google Scholar