Format

Send to

Choose Destination

See 1 citation found by title matching your search:

Neuroimage. 2013 Nov 1;81:347-357. doi: 10.1016/j.neuroimage.2013.05.036. Epub 2013 May 17.

Multivariate decoding of brain images using ordinal regression.

Author information

1
King's College London, Department of Neuroimaging, Institute of Psychiatry (PO89), De Crespigny Park, London SE5 8AF, UK. Electronic address: orla.doyle@kcl.ac.uk.
2
Wellcome Trust Centre for Neuroimaging, 12 Queen Square, London WC1N 3BG, UK. Electronic address: j.ashburner@ucl.ac.uk.
3
King's College London, Department of Neuroimaging, Institute of Psychiatry (PO89), De Crespigny Park, London SE5 8AF, UK. Electronic address: fernando.zelaya@kcl.ac.uk.
4
King's College London, Department of Neuroimaging, Institute of Psychiatry (PO89), De Crespigny Park, London SE5 8AF, UK. Electronic address: steve.williams@kcl.ac.uk.
5
King's College London, Department of Neuroimaging, Institute of Psychiatry (PO89), De Crespigny Park, London SE5 8AF, UK. Electronic address: mitul.mehta@kcl.ac.uk.
6
King's College London, Department of Neuroimaging, Institute of Psychiatry (PO89), De Crespigny Park, London SE5 8AF, UK. Electronic address: andre.marquand@kcl.ac.uk.

Abstract

Neuroimaging data are increasingly being used to predict potential outcomes or groupings, such as clinical severity, drug dose response, and transitional illness states. In these examples, the variable (target) we want to predict is ordinal in nature. Conventional classification schemes assume that the targets are nominal and hence ignore their ranked nature, whereas parametric and/or non-parametric regression models enforce a metric notion of distance between classes. Here, we propose a novel, alternative multivariate approach that overcomes these limitations - whole brain probabilistic ordinal regression using a Gaussian process framework. We applied this technique to two data sets of pharmacological neuroimaging data from healthy volunteers. The first study was designed to investigate the effect of ketamine on brain activity and its subsequent modulation with two compounds - lamotrigine and risperidone. The second study investigates the effect of scopolamine on cerebral blood flow and its modulation using donepezil. We compared ordinal regression to multi-class classification schemes and metric regression. Considering the modulation of ketamine with lamotrigine, we found that ordinal regression significantly outperformed multi-class classification and metric regression in terms of accuracy and mean absolute error. However, for risperidone ordinal regression significantly outperformed metric regression but performed similarly to multi-class classification both in terms of accuracy and mean absolute error. For the scopolamine data set, ordinal regression was found to outperform both multi-class and metric regression techniques considering the regional cerebral blood flow in the anterior cingulate cortex. Ordinal regression was thus the only method that performed well in all cases. Our results indicate the potential of an ordinal regression approach for neuroimaging data while providing a fully probabilistic framework with elegant approaches for model selection.

KEYWORDS:

Gaussian processes; Ketamine; Multivariate; Ordinal regression; Pharmacological MRI; Scopolamine

PMID:
23684876
PMCID:
PMC4068378
DOI:
10.1016/j.neuroimage.2013.05.036
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center