A WEKA Interface for fMRI Data
- PDF / 168,428 Bytes
- 5 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 198 Views
NEWS ITEM
A WEKA Interface for fMRI Data M. Pyka & A. Balz & A. Jansen & A. Krug & E. Hüllermeier
Published online: 18 March 2012 # Springer Science+Business Media, LLC 2012
Keywords fMRI . WEKA . Machine learning . Pattern recognition
Originated as a sub-discipline in artificial intelligence, machine learning has evolved into an independent field used by researchers from various scientific disciplines to solve classification and prediction problems in their area. In neuroimaging, machine learning approaches have become popular tools to predict cognitive states or group membership of subjects from functional and structural magnetic resonance imaging (MRI) data. As opposed to univariate analyses, pattern classifiers are considered to be more sensitive for discriminating information in neuroimage data since areas that are of particular importance for the classification process do not have to reflect necessarily a selective hemodynamic increase or decrease. Rather, they represent a multivariate pattern that leads, in conjunction with other areas, to high predictability. This multivariate nature of machine learning approaches leads in neuroimaging to increased sensitivity over univariate methods and allows single-subject classification.1 fMRI studies commonly use
1
O’Toole, A.J. et al., 2007. Theoretical, statistical, and practical perspectives on pattern-based classification approaches to the analysis of functional neuroimaging data. Journal of cognitive neuroscience, 19 (11), pp.1735–52. M. Pyka (*) : A. Jansen : A. Krug Department of Psychiatry, Philipps-Universität Marburg, Rudolf-Bultmann-Str. 8, 35039 Marburg, Germany e-mail: [email protected] A. Balz : E. Hüllermeier Department of Mathematics and Computer Science, Philipps-Universität Marburg, Marburg, Germany
a brain activation pattern to infer a subject’s cognitive state.2 Furthermore, single-subject classification has been recognized to be of particular value in biomarker research, as it has been shown in a number of clinical populations involving disorders such as Alzheimer’s disease,3 attention deficit hyperactivity disorder,4 schizophrenia,5 and major depressive disorder.6 As in all disciplines that adopt techniques from computer science, specific tools have emerged for the neuroscience 2 Carlson, T.A., Schrater, P. & He, S., 2003. Patterns of activity in the categorical representations of objects. Journal of cognitive neuroscience, 15(5), pp.704–17. Cox, D.D. & Savoy, R.L., 2003. Functional magnetic resonance imaging (fMRI) “brain reading”: detecting and classifying distributed patterns of fMRI activity in human visual cortex. NeuroImage, 19(2 Pt 1), pp.261–70. Davatzikos, C. et al., 2005. Classifying spatial patterns of brain activity with machine learning methods: application to lie detection. NeuroImage, 28(3), pp.663–8. 3 Magnin, B. et al., 2009. Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI. Neuroradiology, 51(2), pp.73–83. Tripoliti, E.E. et al., 2010. A six stage approach for th
Data Loading...
