The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity
The brain at wakefulness is active even in the absence of goal-directed behavior or salient stimuli. However, patterns of this resting-state (RS) activity can undergo long-term alterations following exposure to preceding meaningful stimuli. This study was aimed to develop an unbiased method to detec...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | NeuroImage: Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666956021000337 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849700443413807104 |
|---|---|
| author | Nikita Pospelov Alina Tetereva Olga Martynova Konstantin Anokhin |
| author_facet | Nikita Pospelov Alina Tetereva Olga Martynova Konstantin Anokhin |
| author_sort | Nikita Pospelov |
| collection | DOAJ |
| description | The brain at wakefulness is active even in the absence of goal-directed behavior or salient stimuli. However, patterns of this resting-state (RS) activity can undergo long-term alterations following exposure to preceding meaningful stimuli. This study was aimed to develop an unbiased method to detect such changes in the RS activity after exposure to emotionally meaningful stimuli. For this purpose, we used functional magnetic resonance imaging (fMRI) of RS brain activity before and after acquisition and extinction of experimental conditioned fear. A group of healthy volunteers participated in three fMRI sessions: a RS before fear conditioning, a fear extinction session, and a RS immediately after fear extinction. The fear-conditioning paradigm consisted of three neutral visual stimuli paired with a partial reinforcement by a mild electric current. We used both linear and non-linear dimensionality reduction approaches to distinguish between the initial RS and the RS after stimuli exposure. The principal component analysis (PCA) as a linear dimensionality reduction method showed significantly worse results than non-linear methods (Isomap, LLE, Laplacian eigenmaps). Using the Laplacian eigenmaps manifold learning method, we were able to show significant differences between the two RSs at the level of individual participants. This detection was further improved by smoothing the BOLD signal with the wavelet multiresolution analysis. The developed method can improve the discrimination of functional states collected in longitudinal fMRI studies. |
| format | Article |
| id | doaj-art-686759c0dc384caf94ce936c8a39480b |
| institution | DOAJ |
| issn | 2666-9560 |
| language | English |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Reports |
| spelling | doaj-art-686759c0dc384caf94ce936c8a39480b2025-08-20T03:18:16ZengElsevierNeuroImage: Reports2666-95602021-09-011310003510.1016/j.ynirp.2021.100035The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activityNikita Pospelov0Alina Tetereva1Olga Martynova2Konstantin Anokhin3Institute for Advanced Brain Studies, Lomonosov Moscow State University, Moscow, Russia; Corresponding author. Institute for Advanced Brain Studies, Lomonosov Moscow State University, Lomonosovsky av. 27, 119192, Moscow, Russia.Institute of Higher Nervous Activity and Neurophysiology of the Russian Academy of Science, Russia; Department of Psychology, University of Otago, Dunedin, New ZealandInstitute of Higher Nervous Activity and Neurophysiology of the Russian Academy of Science, RussiaInstitute for Advanced Brain Studies, Lomonosov Moscow State University, Moscow, RussiaThe brain at wakefulness is active even in the absence of goal-directed behavior or salient stimuli. However, patterns of this resting-state (RS) activity can undergo long-term alterations following exposure to preceding meaningful stimuli. This study was aimed to develop an unbiased method to detect such changes in the RS activity after exposure to emotionally meaningful stimuli. For this purpose, we used functional magnetic resonance imaging (fMRI) of RS brain activity before and after acquisition and extinction of experimental conditioned fear. A group of healthy volunteers participated in three fMRI sessions: a RS before fear conditioning, a fear extinction session, and a RS immediately after fear extinction. The fear-conditioning paradigm consisted of three neutral visual stimuli paired with a partial reinforcement by a mild electric current. We used both linear and non-linear dimensionality reduction approaches to distinguish between the initial RS and the RS after stimuli exposure. The principal component analysis (PCA) as a linear dimensionality reduction method showed significantly worse results than non-linear methods (Isomap, LLE, Laplacian eigenmaps). Using the Laplacian eigenmaps manifold learning method, we were able to show significant differences between the two RSs at the level of individual participants. This detection was further improved by smoothing the BOLD signal with the wavelet multiresolution analysis. The developed method can improve the discrimination of functional states collected in longitudinal fMRI studies.http://www.sciencedirect.com/science/article/pii/S2666956021000337Resting-state fMRIBOLD signalConditioned fearDimensionality reductionLaplacian eigenmapsMultiresolution analysis |
| spellingShingle | Nikita Pospelov Alina Tetereva Olga Martynova Konstantin Anokhin The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity NeuroImage: Reports Resting-state fMRI BOLD signal Conditioned fear Dimensionality reduction Laplacian eigenmaps Multiresolution analysis |
| title | The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity |
| title_full | The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity |
| title_fullStr | The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity |
| title_full_unstemmed | The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity |
| title_short | The Laplacian eigenmaps dimensionality reduction of fMRI data for discovering stimulus-induced changes in the resting-state brain activity |
| title_sort | laplacian eigenmaps dimensionality reduction of fmri data for discovering stimulus induced changes in the resting state brain activity |
| topic | Resting-state fMRI BOLD signal Conditioned fear Dimensionality reduction Laplacian eigenmaps Multiresolution analysis |
| url | http://www.sciencedirect.com/science/article/pii/S2666956021000337 |
| work_keys_str_mv | AT nikitapospelov thelaplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT alinatetereva thelaplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT olgamartynova thelaplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT konstantinanokhin thelaplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT nikitapospelov laplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT alinatetereva laplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT olgamartynova laplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity AT konstantinanokhin laplacianeigenmapsdimensionalityreductionoffmridatafordiscoveringstimulusinducedchangesintherestingstatebrainactivity |