Partial Clustering for Tissue Segmentation in MRI

Reference:

Nicolau Gonçalves, Janne Nikkilä, and Ricardo Vigário. Partial clustering for tissue segmentation in MRI. In M. Köppen et al., editor, Proceedings of ICONIP 2008, volume LNCS 5507, pages 559–566, 2009.

Abstract:

Magnetic resonance imaging (MRI) is a imaging and diagnostic tool widely used, with excellent spatial resolution, and efficient in distinguishing between soft tissues. Here, we present a method for semiautomatic identification of brain tissues in MRI, based on a combination of machine learning approaches. Our approach uses self-organising maps (SOMs) for voxel labelling, which are used to seed the discriminative clustering (DC) classification algorithm. This method reduces the intensive need for a specialist, and allows for a rather systematic follow-up of the evolution of brain lesions, or their treatment.

Keywords:

brain MRI, discriminative clustering, tissue segmentation, unsupervised classification, MS lesion

Suggested BibTeX entry:

@inproceedings{Goncalves2009,
    author = {Gonçalves, Nicolau and Nikkilä, Janne and Vigário, Ricardo},
    booktitle = {Proceedings of ICONIP 2008},
    editor = {M. Köppen et al.},
    language = {eng},
    pages = {559-566},
    title = {Partial Clustering for Tissue Segmentation in {MRI}},
    volume = {LNCS 5507},
    year = {2009},
}