 Home > Active Ingredient News > Study of Nervous System > NeuroImage: Dynamic modal decomposition to extract spatiotemporal features from rs-fMRI data to predict behavior

NeuroImage: Dynamic modal decomposition to extract spatiotemporal features from rs-fMRI data to predict behavior

 Last Update: 2022-02-19
 Source: Internet
 Author: User

Tags

based

petrographic analysis

Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com

The dynamic properties of resting-state functional connectivity (FC) provide rich information for studying brain-behavior relationships
.

Dynamic mode decomposition (dynamic modes, DMD) is a method used to characterize the dynamic characteristics of FC

Analysis process

This experiment investigates the contribution of DMs to predictions in 7 specific frequency bands (0 0.
1, .
.
.
, 0.
6 0.
7 Hz)
.

To validate the method, the study tested whether each of the 59 behavioral measures could be predicted by multivariate pattern analysis of the Gram matrix using subjects' resting-state fMRI (rs- fMRI) data were calculated to create a specific DM

Prediction results of Dynamic Mode Decomposition (DMD), Temporal Independent Component Analysis (ICA), and Spatial Independent Component Analysis (10 components)
.

Comparison of prediction results from Dynamic Mode Decomposition (DMD), Temporal Independent Component Analysis (ICA), and Spatial Independent Component Analysis (10 components)
.

Prediction results for different frequency bands
.

Clustering results (0-0.
1 Hz)
.

In this study, DMD successfully predicts behavior and outperforms a traditional data decomposition method for extracting spatial activity patterns, spatiotemporal independent component analysis
.

In a permutation test, most behavioral measures were related to cognition

This study successfully established a method for predicting individual differences in behavioral measures of DM inherent to rs-fMRI activity
.

show that DMD is superior to spatiotemporal ICA

This study successfully established a method for predicting individual differences in behavioral measures of DM inherent to rs-fMRI activity

The findings highlight the superiority of DMD in data decomposition methods for extracting spatiotemporal features from rs-fMRI data

DMD can efficiently extract spatiotemporal features from rs-fMRI data

original source

Predicting behavior through dynamic modes in resting-state fMRI data

Predicting behavior through dynamic modes in resting-state fMRI data Leave a comment here

This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.