Clustering Algorithms for MRI
Magnetic Resonance Imaging (MRI) plays a relevant role in the design of systems for computer assisted diagnosis. MR-images are multi-dimensional in nature; physicians have to combine several perceptual information images to perform the tissue classification needed for diagnosis. Automatic clustering methods help to discriminate relevant features and to perform a preliminary segmentation of the image; it can guide the final manual classification of body-tissues. Three clustering techniques and their integration in a MRI-system are described. Their performance and accuracy was evaluated on synthetic and real image-data. A comparison of our approach with the tissue-classification done by a radiologist was performed.
Key-wordsMRI clustering classification data-analysis
Unable to display preview. Download preview PDF.
- E. Herskovits, M. Walker, “Computer-Aided Classification of Magnetic-Resonance Images”, Tech.Rep. N.KSL-89-47, Medical Computer Science, Stanford University, 1989.Google Scholar
- R. Dann, J. Hoford, et al., “Preliminary Clinical Evaluation of Multi-Resolution Elastic Matching Software”, Tech.Report, MS-CIS-85-35, Department of Computer Science and Information Science, University of Pennsylvania, 1988.Google Scholar
- W.A. Hanson, E. Herskovits, R. De La Paz and R. Bernstein, “A Maximum-Likelihood Classifier for Automated Radiologic Diagnosis”, 1988.Google Scholar
- V. Di Gesu’, R.L. De La Paz, W.A. Hanson, R. Bernstein, “A comparison of Clustering Algorithms for MRI”, PASC-Tech.Rep., N., 1989.Google Scholar
- V. Di Gesu’, et all., “Hierarchical Clustering Algorithms: a comparative analysis”, in preparation.Google Scholar
- J.C.Bezdek, “Pattern Recognition with Fuzzy Objective Function Algorithms”, Plenum Press, NY, 1987.Google Scholar
- V. Di Gesù, “A Clustering Approach to Texture Classification”, in Real Time Object and Environment Measurement and Classification, A.K.Anil Jain ed., NATO ASI Series F, Vol.42, Springer Verlag, 1988.Google Scholar