Literature DB >> 33317408

A Classification-Based Approach to Estimate the Number of Resting Functional Magnetic Resonance Imaging Dynamic Functional Connectivity States.

Debbrata K Saha1, Eswar Damaraju1, Barnaly Rashid2, Anees Abrol1, Sergey M Plis1, Vince D Calhoun1.   

Abstract

Aim: To determine the optimal number of connectivity states in dynamic functional connectivity analysis. Introduction: Recent work has focused on the study of dynamic (vs. static) brain connectivity in resting functional magnetic resonance imaging data. In this work, we focus on temporal correlation between time courses extracted from coherent networks called functional network connectivity (FNC). Dynamic FNC is most commonly estimated using a sliding window-based approach to capture short periods of FNC change. These data are then clustered to estimate transient connectivity patterns or states. Determining the number of states is a challenging problem. The elbow criterion is one of the widely used approaches to determine the connectivity states. Materials and
Methods: In our work, we present an alternative approach that evaluates classification (e.g., healthy controls [HCs] vs. patients) as a measure to select the optimal number of states (clusters). We apply different classification strategies to perform classification between HCs and patients with schizophrenia for different numbers of states (i.e., varying the model order in the clustering algorithm). We compute cross-validated accuracy for different model orders to evaluate the classification performance.
Results: Our results are consistent with our earlier work which shows that overall accuracy improves when dynamic connectivity measures are used separately or in combination with static connectivity measures. Results also show that the optimal model order for classification is different from that using the standard k-means model selection method, and that such optimization improves cross-validated accuracy. The optimal model order obtained from the proposed approach also gives significantly improved classification performance over the traditional model selection method.
Conclusion: The observed results suggest that if one's goal is to perform classification, using the proposed approach as a criterion for selecting the optimal number of states in dynamic connectivity analysis leads to improved accuracy in hold-out data.

Entities:  

Keywords:  ICA; classification; fMRI; functional connectivity; model order; schizophrenia

Mesh:

Year:  2021        PMID: 33317408      PMCID: PMC7993535          DOI: 10.1089/brain.2020.0794

Source DB:  PubMed          Journal:  Brain Connect        ISSN: 2158-0014


  36 in total

1.  Functional connectivity in the resting brain: a network analysis of the default mode hypothesis.

Authors:  Michael D Greicius; Ben Krasnow; Allan L Reiss; Vinod Menon
Journal:  Proc Natl Acad Sci U S A       Date:  2002-12-27       Impact factor: 11.205

2.  Network modelling methods for FMRI.

Authors:  Stephen M Smith; Karla L Miller; Gholamreza Salimi-Khorshidi; Matthew Webster; Christian F Beckmann; Thomas E Nichols; Joseph D Ramsey; Mark W Woolrich
Journal:  Neuroimage       Date:  2010-09-15       Impact factor: 6.556

3.  The graphical lasso: New insights and alternatives.

Authors:  Rahul Mazumder; Trevor Hastie
Journal:  Electron J Stat       Date:  2012-11-09       Impact factor: 1.125

4.  Time-frequency dynamics of resting-state brain connectivity measured with fMRI.

Authors:  Catie Chang; Gary H Glover
Journal:  Neuroimage       Date:  2009-12-16       Impact factor: 6.556

Review 5.  Dynamic functional connectivity: promise, issues, and interpretations.

Authors:  R Matthew Hutchison; Thilo Womelsdorf; Elena A Allen; Peter A Bandettini; Vince D Calhoun; Maurizio Corbetta; Stefania Della Penna; Jeff H Duyn; Gary H Glover; Javier Gonzalez-Castillo; Daniel A Handwerker; Shella Keilholz; Vesa Kiviniemi; David A Leopold; Francesco de Pasquale; Olaf Sporns; Martin Walter; Catie Chang
Journal:  Neuroimage       Date:  2013-05-24       Impact factor: 6.556

6.  Mapping Thalamocortical Functional Connectivity in Chronic and Early Stages of Psychotic Disorders.

Authors:  Neil D Woodward; Stephan Heckers
Journal:  Biol Psychiatry       Date:  2015-07-02       Impact factor: 13.382

7.  Discriminative analysis of non-linear brain connectivity in schizophrenia: an fMRI Study.

Authors:  Longfei Su; Lubin Wang; Hui Shen; Guiyu Feng; Dewen Hu
Journal:  Front Hum Neurosci       Date:  2013-10-22       Impact factor: 3.169

8.  Functional connectivity classification of autism identifies highly predictive brain features but falls short of biomarker standards.

Authors:  Mark Plitt; Kelly Anne Barnes; Alex Martin
Journal:  Neuroimage Clin       Date:  2014-12-24       Impact factor: 4.881

9.  Classification of schizophrenia and bipolar patients using static and dynamic resting-state fMRI brain connectivity.

Authors:  Barnaly Rashid; Mohammad R Arbabshirani; Eswar Damaraju; Mustafa S Cetin; Robyn Miller; Godfrey D Pearlson; Vince D Calhoun
Journal:  Neuroimage       Date:  2016-04-23       Impact factor: 6.556

10.  A method for functional network connectivity among spatially independent resting-state components in schizophrenia.

Authors:  Madiha J Jafri; Godfrey D Pearlson; Michael Stevens; Vince D Calhoun
Journal:  Neuroimage       Date:  2007-11-13       Impact factor: 6.556

View more
  3 in total

1.  Multimodel Order Independent Component Analysis: A Data-Driven Method for Evaluating Brain Functional Network Connectivity Within and Between Multiple Spatial Scales.

Authors:  Xing Meng; Armin Iraji; Zening Fu; Peter Kochunov; Aysenil Belger; Judith Ford; Sara McEwen; Daniel H Mathalon; Bryon A Mueller; Godfrey Pearlson; Steven G Potkin; Adrian Preda; Jessica Turner; Theo van Erp; Jing Sui; Vince D Calhoun
Journal:  Brain Connect       Date:  2021-11-22

2.  Widespread cortical functional disconnection in gliomas: an individual network mapping approach.

Authors:  Erica Silvestri; Manuela Moretto; Silvia Facchini; Marco Castellaro; Mariagiulia Anglani; Elena Monai; Domenico D'Avella; Alessandro Della Puppa; Diego Cecchin; Alessandra Bertoldo; Maurizio Corbetta
Journal:  Brain Commun       Date:  2022-04-08

3.  Two-step clustering-based pipeline for big dynamic functional network connectivity data.

Authors:  Mohammad S E Sendi; David H Salat; Robyn L Miller; Vince D Calhoun
Journal:  Front Neurosci       Date:  2022-07-25       Impact factor: 5.152

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.