A method to compare the discriminatory power of data-driven methods: Application to ICA and IVA

Yuri Levin-Schwartz, Vince Daniel Calhoun, Tülay Adalı

Research output: Contribution to journalArticle

Abstract

Background: The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. New method: We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. Comparison with existing methods: We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. Results: Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. Conclusions: These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses.

LanguageEnglish (US)
Pages267-276
Number of pages10
JournalJournal of Neuroscience Methods
Volume311
DOIs
StatePublished - Jan 1 2019

Fingerprint

Schizophrenia
Magnetic Resonance Imaging
Power (Psychology)
Task Performance and Analysis
Psychiatry
Regression Analysis

Keywords

  • fMRI
  • ICA
  • Schizophrenia

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

A method to compare the discriminatory power of data-driven methods : Application to ICA and IVA. / Levin-Schwartz, Yuri; Calhoun, Vince Daniel; Adalı, Tülay.

In: Journal of Neuroscience Methods, Vol. 311, 01.01.2019, p. 267-276.

Research output: Contribution to journalArticle

@article{ecbd2b95605c439b971770367c64a1ba,
title = "A method to compare the discriminatory power of data-driven methods: Application to ICA and IVA",
abstract = "Background: The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. New method: We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. Comparison with existing methods: We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. Results: Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. Conclusions: These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses.",
keywords = "fMRI, ICA, Schizophrenia",
author = "Yuri Levin-Schwartz and Calhoun, {Vince Daniel} and T{\"u}lay Adalı",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.jneumeth.2018.10.008",
language = "English (US)",
volume = "311",
pages = "267--276",
journal = "Journal of Neuroscience Methods",
issn = "0165-0270",
publisher = "Elsevier",

}

TY - JOUR

T1 - A method to compare the discriminatory power of data-driven methods

T2 - Journal of Neuroscience Methods

AU - Levin-Schwartz, Yuri

AU - Calhoun, Vince Daniel

AU - Adalı, Tülay

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. New method: We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. Comparison with existing methods: We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. Results: Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. Conclusions: These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses.

AB - Background: The widespread application of data-driven factorization-based methods, such as independent component analysis (ICA), to functional magnetic resonance imaging data facilitates the study of neural function and how it is disrupted by psychiatric disorders such as schizophrenia. While the increasing number of these methods motivates a comparison of their relative performance, such a comparison is difficult to perform on real fMRI data, since the ground truth is, relatively, unknown and the alignment of factors across different methods is impractical and imprecise. New method: We present a novel method, global difference maps (GDMs), to compare the results of different fMRI analysis techniques on real fMRI data, quantify their relative performances, and highlight the differences between the decompositions visually. Comparison with existing methods: We apply this method to compare the performances of two different factorization-based methods, ICA and its multiset extension independent vector analysis (IVA), for the analysis of fMRI data from 109 patients with schizophrenia and 138 healthy controls during the performance of three tasks. Results: Through this application of GDMs, we find that IVA can determine regions that are more discriminatory between patients and controls than ICA, though IVA is less effective at emphasizing regions found in only a subset of the tasks. Conclusions: These results demonstrate that GDMs are an effective way to compare the performances of different factorization-based methods as well as regression-based analyses.

KW - fMRI

KW - ICA

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85056190569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056190569&partnerID=8YFLogxK

U2 - 10.1016/j.jneumeth.2018.10.008

DO - 10.1016/j.jneumeth.2018.10.008

M3 - Article

VL - 311

SP - 267

EP - 276

JO - Journal of Neuroscience Methods

JF - Journal of Neuroscience Methods

SN - 0165-0270

ER -