Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Visualizing temporal brain-state changes for fMRI using t-distributed stochastic neighbor embedding

Visualizing temporal brain-state changes for fMRI using t-distributed stochastic neighbor embedding Abstract.Purpose: Currently, functional magnetic resonance imaging (fMRI) is the most commonly used technique for obtaining dynamic information about the brain. However, because of the complexity of the data, it is often difficult to directly visualize the temporal aspect of the fMRI data.Approach: We outline a t-distributed stochastic neighbor embedding (t-SNE)-based postprocessing technique that can be used for visualization of temporal information from a 4D fMRI data. Apart from visualization, we also show its utility in detection of major changes in the brain meta-states during the scan duration.Results: The t-SNE approach is able to detect brain-state changes from task to rest and vice versa for single- and multitask fMRI data. A temporal visualization can also be obtained for task and resting state fMRI data for assessing the temporal dynamics during the scan duration. Additionally, hemodynamic delay can be quantified by comparison of the detected brain-state changes with the experiment paradigm for task fMRI data.Conclusion: The t-SNE visualization can visualize help identify major brain-state changes from fMRI data. Such visualization can provide information about the degree of involvement and attentiveness of the subject during the scan and can be potentially utilized as a quality control for subject’s performance during the scan. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Visualizing temporal brain-state changes for fMRI using t-distributed stochastic neighbor embedding

Download PDF
21 pages

Loading next page...
 
/lp/spie/visualizing-temporal-brain-state-changes-for-fmri-using-t-distributed-NLrNJllre7
Publisher
SPIE
Copyright
© 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.8.4.046001
Publisher site
See Article on Publisher Site

Abstract

Abstract.Purpose: Currently, functional magnetic resonance imaging (fMRI) is the most commonly used technique for obtaining dynamic information about the brain. However, because of the complexity of the data, it is often difficult to directly visualize the temporal aspect of the fMRI data.Approach: We outline a t-distributed stochastic neighbor embedding (t-SNE)-based postprocessing technique that can be used for visualization of temporal information from a 4D fMRI data. Apart from visualization, we also show its utility in detection of major changes in the brain meta-states during the scan duration.Results: The t-SNE approach is able to detect brain-state changes from task to rest and vice versa for single- and multitask fMRI data. A temporal visualization can also be obtained for task and resting state fMRI data for assessing the temporal dynamics during the scan duration. Additionally, hemodynamic delay can be quantified by comparison of the detected brain-state changes with the experiment paradigm for task fMRI data.Conclusion: The t-SNE visualization can visualize help identify major brain-state changes from fMRI data. Such visualization can provide information about the degree of involvement and attentiveness of the subject during the scan and can be potentially utilized as a quality control for subject’s performance during the scan.

Journal

Journal of Medical Imaging – SPIE

Published: Jul 1, 2021

Keywords: brain-state changes; dimensionality reduction; functional MRI visualization; t -distributed stochastic neighbor embedding

References

  • Resting-state fMRI: a review of methods and clinical applications
    Lee, M. H.; Smyser, C. D.; Shimony, J. S.
  • Independent component analysis: algorithms and applications
    Hyvärinen, A.; Oja, E.
  • Deep belief networks
    Hinton, G. E.
  • Autoencoders, unsupervised learning, and deep architectures
    Baldi, P.
  • Generative adversarial nets
    Goodfellow, I.
  • Visualizing data using t-SNE
    van der Maaten, L.; Hinton, G.
  • A tool for interactive data visualization: application to over 10,000 brain imaging and phantom MRI data sets
    Panta, S. R.
  • Exploring the brain network: a review on resting-state fMRI functional connectivity
    Van Den Heuvel, M. P.; Pol, H. E. H.
  • Tracking ongoing cognition in individuals using brief, whole-brain functional connectivity patterns
    Gonzalez-Castillo, J.
  • Whole-brain connectivity dynamics reflect both task-specific and individual-specific modulation: a multitask study
    Xie, H.
  • Efficacy of different dynamic functional connectivity methods to capture cognitively relevant information
    Xie, H.
  • Brain meta-state transitions demarcate spontaneous thoughts in movie-viewing and resting cognition
    Tseng, J.; Poppenk, J.
  • Stochastic neighbor embedding
    Hinton, G. E.; Roweis, S. T.
  • f-Sim: a quasi-realistic fMRI simulation toolbox using digital brain phantom and modeled noise
    Parmar, H. S.
  • Whole-brain, time-locked activation with simple tasks revealed using massive averaging and model-free analysis
    Gonzalez-Castillo, J.
  • Automated signal drift and global fluctuation removal from 4D fMRI data based on principal component analysis as a major preprocessing step for fMRI data analysis
    Parmar, H. S.
  • SPM12 manual
    Ashburner, J.
  • The variability of human, BOLD hemodynamic responses
    Aguirre, G. K.; Zarahn, E.; D’Esposito, M.
  • Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses
    Handwerker, D. A.; Ollinger, J. M.; D’Esposito, M.
  • Linking inter-individual differences in neural activation and behavior to intrinsic brain dynamics
    Mennes, M.
  • Inter-individual differences in resting-state functional connectivity predict task-induced BOLD activity
    Mennes, M.
  • Competition between functional brain networks mediates behavioral variability
    Kelly, A. M. C.
  • Which fMRI clustering gives good brain parcellations?
    Thirion, B.
  • A whole brain fMRI atlas generated via spatially constrained spectral clustering
    Craddock, R. C.
  • Inhibit, switch, and update: a within-subject fMRI investigation of executive control
    Lemire-Rodger, S.
  • Saliency, switching, attention and control: a network model of insula function
    Menon, V.; Uddin, L. Q.
  • Spontaneous neuronal activity distinguishes human dorsal and ventral attention systems
    Fox, M. D.