Unsupervised learning toward brain imaging data analysis: Cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis

Dong Youl Kim, Jong-Hwan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A data-driven unsupervised learning such as an independent component analysis was gainfully applied to bloodoxygenation- level-dependent (BOLD) functional magnetic resonance imaging (fMRI) data compared to a model-based general linear model (GLM). This is due to an ability of this unsupervised learning method to extract a meaningful neuronal activity from BOLD signal that is a mixture of confounding non-neuronal artifacts such as head motions and physiological artifacts as well as neuronal signals. In this study, we support this claim by identifying neuronal underpinnings of cigarette craving and cigarette resistance. The fMRI data were acquired from heavy cigarette smokers (n = 14) while they alternatively watched images with and without cigarette smoking. During acquisition of two fMRI runs, they were asked to crave when they watched cigarette smoking images or to resist the urge to smoke. Data driven approaches of group independent component analysis (GICA) method based on temporal concatenation (TC) and TCGICA with an extension of iterative dual-regression (TC-GICA-iDR) were applied to the data. From the results, cigarette craving and cigarette resistance related neuronal activations were identified in the visual area and superior frontal areas, respectively with a greater statistical significance from the TC-GICA-iDR method than the TC-GICA method. On the other hand, the neuronal activity levels in many of these regions were not statistically different from the GLM method between the cigarette craving and cigarette resistance due to potentially aberrant BOLD signals.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
PublisherSPIE
Volume9118
ISBN (Print)9781628410556
DOIs
Publication statusPublished - 2014 Jan 1
EventIndependent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII - Baltimore, MD, United States
Duration: 2014 May 72014 May 9

Other

OtherIndependent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII
CountryUnited States
CityBaltimore, MD
Period14/5/714/5/9

Fingerprint

Unsupervised learning
Functional Magnetic Resonance Imaging
Unsupervised Learning
Independent component analysis
Tobacco Products
learning
brain
magnetic resonance
Independent Component Analysis
Activation
Brain
Data analysis
Chemical activation
Imaging
activation
Concatenation
Imaging techniques
Smoking
artifacts
Data-driven

ASJC Scopus subject areas

  • Applied Mathematics
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics

Cite this

Unsupervised learning toward brain imaging data analysis : Cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis. / Kim, Dong Youl; Lee, Jong-Hwan.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 9118 SPIE, 2014. 91180L.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, DY & Lee, J-H 2014, Unsupervised learning toward brain imaging data analysis: Cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 9118, 91180L, SPIE, Independent Component Analyses, Compressive Sampling, Wavelets, Neural Net, Biosystems, and Nanoengineering XII, Baltimore, MD, United States, 14/5/7. https://doi.org/10.1117/12.2053765
@inproceedings{52a8296865d14de2af9dd9559f1dc6ad,
title = "Unsupervised learning toward brain imaging data analysis: Cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis",
abstract = "A data-driven unsupervised learning such as an independent component analysis was gainfully applied to bloodoxygenation- level-dependent (BOLD) functional magnetic resonance imaging (fMRI) data compared to a model-based general linear model (GLM). This is due to an ability of this unsupervised learning method to extract a meaningful neuronal activity from BOLD signal that is a mixture of confounding non-neuronal artifacts such as head motions and physiological artifacts as well as neuronal signals. In this study, we support this claim by identifying neuronal underpinnings of cigarette craving and cigarette resistance. The fMRI data were acquired from heavy cigarette smokers (n = 14) while they alternatively watched images with and without cigarette smoking. During acquisition of two fMRI runs, they were asked to crave when they watched cigarette smoking images or to resist the urge to smoke. Data driven approaches of group independent component analysis (GICA) method based on temporal concatenation (TC) and TCGICA with an extension of iterative dual-regression (TC-GICA-iDR) were applied to the data. From the results, cigarette craving and cigarette resistance related neuronal activations were identified in the visual area and superior frontal areas, respectively with a greater statistical significance from the TC-GICA-iDR method than the TC-GICA method. On the other hand, the neuronal activity levels in many of these regions were not statistically different from the GLM method between the cigarette craving and cigarette resistance due to potentially aberrant BOLD signals.",
keywords = "Blood oxygenation level dependent, cigarette craving, cigarette resistance, dual regression, functional magnetic resonance imaging, general linear model, independent component analysis, unsupervised learning",
author = "Kim, {Dong Youl} and Jong-Hwan Lee",
year = "2014",
month = "1",
day = "1",
doi = "10.1117/12.2053765",
language = "English",
isbn = "9781628410556",
volume = "9118",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",

}

TY - GEN

T1 - Unsupervised learning toward brain imaging data analysis

T2 - Cigarette craving and resistance related neuronal activations from functional magnetic resonance imaging data analysis

AU - Kim, Dong Youl

AU - Lee, Jong-Hwan

PY - 2014/1/1

Y1 - 2014/1/1

N2 - A data-driven unsupervised learning such as an independent component analysis was gainfully applied to bloodoxygenation- level-dependent (BOLD) functional magnetic resonance imaging (fMRI) data compared to a model-based general linear model (GLM). This is due to an ability of this unsupervised learning method to extract a meaningful neuronal activity from BOLD signal that is a mixture of confounding non-neuronal artifacts such as head motions and physiological artifacts as well as neuronal signals. In this study, we support this claim by identifying neuronal underpinnings of cigarette craving and cigarette resistance. The fMRI data were acquired from heavy cigarette smokers (n = 14) while they alternatively watched images with and without cigarette smoking. During acquisition of two fMRI runs, they were asked to crave when they watched cigarette smoking images or to resist the urge to smoke. Data driven approaches of group independent component analysis (GICA) method based on temporal concatenation (TC) and TCGICA with an extension of iterative dual-regression (TC-GICA-iDR) were applied to the data. From the results, cigarette craving and cigarette resistance related neuronal activations were identified in the visual area and superior frontal areas, respectively with a greater statistical significance from the TC-GICA-iDR method than the TC-GICA method. On the other hand, the neuronal activity levels in many of these regions were not statistically different from the GLM method between the cigarette craving and cigarette resistance due to potentially aberrant BOLD signals.

AB - A data-driven unsupervised learning such as an independent component analysis was gainfully applied to bloodoxygenation- level-dependent (BOLD) functional magnetic resonance imaging (fMRI) data compared to a model-based general linear model (GLM). This is due to an ability of this unsupervised learning method to extract a meaningful neuronal activity from BOLD signal that is a mixture of confounding non-neuronal artifacts such as head motions and physiological artifacts as well as neuronal signals. In this study, we support this claim by identifying neuronal underpinnings of cigarette craving and cigarette resistance. The fMRI data were acquired from heavy cigarette smokers (n = 14) while they alternatively watched images with and without cigarette smoking. During acquisition of two fMRI runs, they were asked to crave when they watched cigarette smoking images or to resist the urge to smoke. Data driven approaches of group independent component analysis (GICA) method based on temporal concatenation (TC) and TCGICA with an extension of iterative dual-regression (TC-GICA-iDR) were applied to the data. From the results, cigarette craving and cigarette resistance related neuronal activations were identified in the visual area and superior frontal areas, respectively with a greater statistical significance from the TC-GICA-iDR method than the TC-GICA method. On the other hand, the neuronal activity levels in many of these regions were not statistically different from the GLM method between the cigarette craving and cigarette resistance due to potentially aberrant BOLD signals.

KW - Blood oxygenation level dependent

KW - cigarette craving

KW - cigarette resistance

KW - dual regression

KW - functional magnetic resonance imaging

KW - general linear model

KW - independent component analysis

KW - unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=84906347238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906347238&partnerID=8YFLogxK

U2 - 10.1117/12.2053765

DO - 10.1117/12.2053765

M3 - Conference contribution

AN - SCOPUS:84906347238

SN - 9781628410556

VL - 9118

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - SPIE

ER -