Mutual Information Based Metric for Evaluation of fMRI Data Processing Approaches

Afshin-Pour, Babak; Soltanian‐Zadeh, Hamid; Hossein-Zadeh, Gholam-Ali; Strother, Stephen C.

doi:10.1016/s1053-8119(09)70578-6

Cited by 3 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, for spike trains, various metrics can be defined that emphasize different properties of the spike trains [Victor, 2005]. MI conveyed by high-dimensional time courses can be estimated based on a hyperbolic distance measure formed from the correlation coefficient between pairs of time series [Afshin-Pour et al, 2011]. While these methods are relatively unbiased, they often have a high variance and are computationally intensive.…”

Section: Continuous Methodsmentioning

confidence: 99%

“…Other approaches to estimating MI in higher dimensional response spaces include extensions to the nearest-neighbor method with specifically chosen distance measures that preserve the appropriate structure of the high-dimensional space. For example, in fMRI a distance based on correlation between voxel time courses can be used to estimate MI between a statistical parameter map and a high-dimensional whole brain validation dataset [Afshin-Pour et al, 2011].…”

Section: Application To Multidimensional Spacesmentioning

confidence: 99%

“…MI has been used to compare different neural response codes [Ince et al, 2013;Kayser et al, 2009;Reich et al, 2001], characterize different neurons [Sharpee, 2014] as well as quantify the effect of correlations between neurons [Ince et al, 2009[Ince et al, , 2010Moreno-Bote et al, 2014] and the importance of spike timing Nemenman et al, 2008;Panzeri et al, 2001]. Recent studies have begun to explore its application to neuroimaging [Afshin-Pour et al, 2011;Caballero-Gaudes et al, 2013;Gross et al, 2013;Guggenmos et al, 2015;Ostwald and Bagshaw, 2011;Panzeri et al, 2008;Salvador et al, 2007;Saproo and Serences, 2010;Schyns et al, 2011;Serences et al, 2009].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula

Ince

Giordano

Kayser

et al. 2016

Human Brain Mapping

243

261

View full text Add to dashboard Cite

We begin by reviewing the statistical framework of information theory as applicable to neuroimaging data analysis. A major factor hindering wider adoption of this framework in neuroimaging is the difficulty of estimating information theoretic quantities in practice. We present a novel estimation technique that combines the statistical theory of copulas with the closed form solution for the entropy of Gaussian variables. This results in a general, computationally efficient, flexible, and robust multivariate statistical framework that provides effect sizes on a common meaningful scale, allows for unified treatment of discrete, continuous, unidimensional and multidimensional variables, and enables direct comparisons of representations from behavioral and brain responses across any recording modality. We validate the use of this estimate as a statistical test within a neuroimaging context, considering both discrete stimulus classes and continuous stimulus features. We also present examples of analyses facilitated by these developments, including application of multivariate analyses to MEG planar magnetic field gradients, and pairwise temporal interactions in evoked EEG responses. We show the benefit of considering the instantaneous temporal derivative together with the raw values of M/EEG signals as a multivariate response, how we can separately quantify modulations of amplitude and direction for vector quantities, and how we can measure the emergence of novel information over time in evoked responses. Open‐source Matlab and Python code implementing the new methods accompanies this article. Hum Brain Mapp 38:1541–1573, 2017. © 2016 Wiley Periodicals, Inc.

show abstract

Section: Continuous Methodsmentioning

confidence: 99%

Section: Application To Multidimensional Spacesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula

Ince

Giordano

Kayser

et al. 2016

Human Brain Mapping

243

261

View full text Add to dashboard Cite

show abstract

“…However, because of the lack of a formal definition for interpretability, different characteristics of brain decoding models are considered as the main objective in improving their interpretability. Reproducibility [53, 54], stability selection [7, 47, 69], sparsity [96], and neurophysiological plausibility [97] are examples of related criteria.…”

Section: Discussionmentioning

confidence: 99%

Interpretability of Multivariate Brain Maps in Brain Decoding: Definition and Quantification

Kia

2016

Preprint

View full text Add to dashboard Cite

Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. Linear classifiers are widely employed in the brain decoding paradigm to discriminate among experimental conditions. Then, the derived linear weights are visualized in the form of multivariate brain maps to further study the spatio-temporal patterns of underlying neural activities. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. Therefore, improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of multivariate brain maps. As a consequence, there is no quantitative measure for evaluating the interpretability of different brain decoding methods. In this paper, first, we present a theoretical definition of interpretability in brain decoding; we show that the interpretability of multivariate brain maps can be decomposed into their reproducibility and representativeness. Second, as an application of the proposed definition, we formalize a heuristic method for approximating the interpretability of multivariate brain maps in a binary magnetoencephalography (MEG) decoding scenario. Third, we pro- * Corresponding author:Email address: seyedmostafa.kia@unitn.it (Seyed Mostafa Kia ) . CC-BY-NC 4.0 International license It is made available under a was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity.The copyright holder for this preprint (which . http://dx.doi.org/10.1101/047522 doi: bioRxiv preprint first posted online Apr. 6, 2016; pose to combine the approximated interpretability and the performance of the brain decoding into a new multi-objective criterion for model selection. Our results for the MEG data show that optimizing the hyper-parameters of the regularized linear classifier based on the proposed criterion results in more informative multivariate brain maps. More importantly, the presented definition provides the theoretical background for quantitative evaluation of interpretability, and hence, facilitates the development of more effective brain decoding algorithms in the future.

show abstract

“…The Intraclass Correlation Coefficient(ICC) [23] is a widely used non-threshold metric [24]. A new approach based on measuring the approximate Mutual Information between the fMRI time-series of a validation dataset and a calculated activation map is proposed in [25]. This method can be applied on thresholded label maps or continuous maps.…”

Section: Introductionmentioning

confidence: 99%

Functional magnetic resonance imaging: Comparison between activation maps and computation pipelines in a clinical context

Pedoia

Strocchi

Colli

et al. 2013

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Mutual Information Based Metric for Evaluation of fMRI Data Processing Approaches

Cited by 3 publications

References 0 publications

A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula

A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula

Interpretability of Multivariate Brain Maps in Brain Decoding: Definition and Quantification

Functional magnetic resonance imaging: Comparison between activation maps and computation pipelines in a clinical context

Contact Info

Product

Resources

About