Unsupervised MRI Tissue Classification by Support Vector Machines

Reference:

Elina Karp and Ricardo Vigário. Unsupervised mri tissue classification by support vector machines. In B. Tilg, editor, Proceedings of the Second IASTED International Conference on Biomedical Engineering (BioMed 2004), pages 88–91, Innsbruck, Austria, 2004. ACTA Press.

Abstract:

The objective of this work was to develop better visuali- sation tools and techniques for detection and follow up of pathologies in magnetic resonance images. Support vector machines were used, in an unsupervised manner, to seg- ment tissues in MR images with different imaging param- eters. The segmentation rested on a training set of labelled feature vectors defined using independent component anal- ysis. Both simulated and real data was used. Support vector machines proved to be a suitable tool for classification of MR images. The classification error rates for the simulated data indicated that rather good segmentation precision was achieved.

Keywords:

Medical imaging, image processing and signal processing, magnetic resonance imaging, support vector machines, unsupervised classification

Suggested BibTeX entry:

@inproceedings{BioMed04-2,
    address = {Innsbruck, Austria},
    author = {Elina Karp and Ricardo Vig\'{a}rio},
    booktitle = {Proceedings of the Second IASTED International Conference on Biomedical Engineering (BioMed 2004)},
    editor = {B.~Tilg},
    pages = {88--91},
    publisher = {ACTA Press},
    title = {Unsupervised MRI Tissue Classification by Support Vector Machines},
    year = {2004},
}