Visualization and Detection of Changes in Brain States Using t-SNE

Harshit S. Parmar, Sunanda Mitra, Brian Nutter, Rodney Long, Sameer Antani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Dimensionality reduction techniques are used primarily for visualization purposes. With sophisticated visualization techniques like t-distributed Stochastic Neighbor Embedding (t-SNE), we can preserve the original neighborhood information even in lower dimensions. Taking advantage of this property, we present a post-processing technique for fMRI data, which can identify changes in the brain states in the tSNE space. The predicted brain state changes detected by such method show high temporal correlation to actual experimental paradigm. Such a technique can be used to extract additional information and better understand the temporal characteristics during task and resting-state fMRI experiments.

Original languageEnglish
Title of host publication2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages14-17
Number of pages4
ISBN (Electronic)9781728157450
DOIs
StatePublished - Mar 2020
Event2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Santa Fe, United States
Duration: Mar 29 2020Mar 31 2020

Publication series

NameProceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume2020-March

Conference

Conference2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020
CountryUnited States
CitySanta Fe
Period03/29/2003/31/20

Keywords

  • brain states
  • fMRI
  • t-SNE
  • visualization

Fingerprint Dive into the research topics of 'Visualization and Detection of Changes in Brain States Using t-SNE'. Together they form a unique fingerprint.

Cite this