Literature DB >> 32726664

Temporal embedding and spatiotemporal feature selection boost multi-voxel pattern analysis decoding accuracy.

Jeiran Choupan1, Pamela K Douglas2, Yaniv Gal3, Mark S Cohen4, David C Reutens5, Zhengyi Yang6.   

Abstract

BACKGROUND: In fMRI decoding, temporal embedding of spatial features of the brain allows the incorporation of brain activity dynamics into the multivariate pattern classification process, and provides enriched information about stimulus-specific response patterns and potentially improved prediction accuracy. NEW
METHOD: This study investigates the possibility of enhancing the classification performance by exploring temporal embedding, to identify the optimum combination of spatiotemporal features based on their classification performance. We investigated the importance of spatiotemporal feature selection using a slow event-related design adapted from the classic Haxby study (Haxby et al., 2001). Data were collected using a multiband fMRI sequence with temporal resolution of 0.568 s. COMPARISON WITH EXISTING
METHODS: A wide range of spatiotemporal observations were created as various combinations of spatiotemporal features. Using both random forest, and support vector machine, classifiers prediction accuracies for these combinations were then compared with the single spatial multivariate pattern approach that uses only a single temporal observation.
RESULTS: Our findings showed that, on average, spatiotemporal feature selection improved prediction accuracy. Moreover, the random forest algorithm outperformed the support vector machine and benefitted from temporal information to a greater extent.
CONCLUSIONS: As expected, the most influential temporal durations were found to be around the peak of the hemodynamic response function, a few seconds after the stimuli onset until -4 s after the peak of the hemodynamic response function. The superiority of spatiotemporal feature selection over single time-point spatial approaches invites future work to design optimal approaches that incorporate spatiotemporal dependencies into feature selection for decoding.
Copyright © 2020 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Multi-variate pattern analysis; Multiband EPI; Random forest; Spatiotemporal feature selection; Support vector machine; fMRI

Mesh:

Year:  2020        PMID: 32726664      PMCID: PMC9419668          DOI: 10.1016/j.jneumeth.2020.108836

Source DB:  PubMed          Journal:  J Neurosci Methods        ISSN: 0165-0270            Impact factor:   2.987


  50 in total

1.  Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses.

Authors:  Daniel A Handwerker; John M Ollinger; Mark D'Esposito
Journal:  Neuroimage       Date:  2004-04       Impact factor: 6.556

2.  Expecting unpleasant stimuli--an fMRI study.

Authors:  Uwe Herwig; Birgit Abler; Henrik Walter; Susanne Erk
Journal:  Psychiatry Res       Date:  2006-12-19       Impact factor: 3.222

3.  Multivariate analysis of fMRI time series: classification and regression of brain responses using machine learning.

Authors:  Elia Formisano; Federico De Martino; Giancarlo Valente
Journal:  Magn Reson Imaging       Date:  2008-05-27       Impact factor: 2.546

4.  Parametric analysis of fMRI data using linear systems methods.

Authors:  M S Cohen
Journal:  Neuroimage       Date:  1997-08       Impact factor: 6.556

Review 5.  A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives.

Authors:  John-Dylan Haynes
Journal:  Neuron       Date:  2015-07-15       Impact factor: 17.173

Review 6.  Decoding neural representational spaces using multivariate pattern analysis.

Authors:  James V Haxby; Andrew C Connolly; J Swaroop Guntupalli
Journal:  Annu Rev Neurosci       Date:  2014-06-25       Impact factor: 12.449

Review 7.  Survey of encoding and decoding of visual stimulus via FMRI: an image analysis perspective.

Authors:  Mo Chen; Junwei Han; Xintao Hu; Xi Jiang; Lei Guo; Tianming Liu
Journal:  Brain Imaging Behav       Date:  2014-03       Impact factor: 3.978

8.  Effects of image reconstruction on fiber orientation mapping from multichannel diffusion MRI: reducing the noise floor using SENSE.

Authors:  S N Sotiropoulos; S Moeller; S Jbabdi; J Xu; J L Andersson; E J Auerbach; E Yacoub; D Feinberg; K Setsompop; L L Wald; T E J Behrens; K Ugurbil; C Lenglet
Journal:  Magn Reson Med       Date:  2013-02-07       Impact factor: 4.668

9.  The utility of data-driven feature selection: re: Chu et al. 2012.

Authors:  Wesley T Kerr; Pamela K Douglas; Ariana Anderson; Mark S Cohen
Journal:  Neuroimage       Date:  2013-07-25       Impact factor: 6.556

10.  Insights into multimodal imaging classification of ADHD.

Authors:  John B Colby; Jeffrey D Rudie; Jesse A Brown; Pamela K Douglas; Mark S Cohen; Zarrar Shehzad
Journal:  Front Syst Neurosci       Date:  2012-08-16
View more
  1 in total

1.  Age Effects on Neural Discriminability and Monitoring Process During Memory Retrieval for Auditory Words.

Authors:  Xuhao Shao; Wenzhi Liu; Ying Guo; Bi Zhu
Journal:  Front Aging Neurosci       Date:  2022-07-19       Impact factor: 5.702

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.