Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Feature selection for brain tumour classification using ratios of metabolites' peak areas from MRSI data

A. Heerschap, Zervakis Michalis, G.J. Postma, L.M.C. Buydens, M.E. Blazadonakis

Full record


URI: http://purl.tuc.gr/dl/dias/91F093D4-8436-49F7-B84F-2D059E032A59
Year 2008
Type of Item Conference Full Paper
License
Details
Bibliographic Citation M.G. Kounelakis, M.E.Zervakis, M.E. Blazadonakis, G.J. Postma, L.M.C. Buydens, A. Heerschap, X. Kotsiakis ,"Feature selection for brain tumour classification using ratios of metabolites' peak areas from MRSI data,"in 6th European Symposium on Biomedical Engineering ESBME,2008, pp.1-6.
Appears in Collections

Summary

The main goal of this study was threefold. Firstly, to investigate the significance of the brain metabolites' peak area Ratios derived from the MRSI spectra provided, by performing brain tumor binary classification and comparing the result with those obtained by using only the metabolites' Peak Amplitudes. Secondly to measure the influence of the four magnetic resonance image intensities (MRI) on the classification process and thirdly to estimate the minimum but also biologically significant set of features

Services

Statistics