A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI

IntroductionFunctional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable...

Full description

Saved in:
Bibliographic Details
Main Authors: Yeseul Jeon, Jeong-Jae Kim, SuMin Yu, Junggu Choi, Sanghoon Han
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2024.1402657/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128014074576896
author Yeseul Jeon
Jeong-Jae Kim
SuMin Yu
Junggu Choi
Sanghoon Han
Sanghoon Han
author_facet Yeseul Jeon
Jeong-Jae Kim
SuMin Yu
Junggu Choi
Sanghoon Han
Sanghoon Han
author_sort Yeseul Jeon
collection DOAJ
description IntroductionFunctional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable without task-specific contexts. Nonetheless, interconnections among ROIs provide essential insights into brain activity and exhibit unique characteristics across groups.MethodsTo address these challenges, we propose an interpretable fusion analytic framework to identify and understand ROI connectivity differences between two groups, revealing their distinctive features. The framework involves three steps: first, constructing ROI-based Functional Connectivity Networks (FCNs) to manage resting-state fMRI data; second, employing a Self-Attention Deep Learning Model (Self-Attn) for binary classification to generate attention distributions encoding group-level differences; and third, utilizing a Latent Space Item-Response Model (LSIRM) to extract group-representative ROI features, visualized on group summary FCNs.ResultsWe applied our framework to analyze four types of cognitive impairments, demonstrating their effectiveness in identifying significant ROIs that contribute to the differences between the two disease groups. The results reveal distinct connectivity patterns and unique ROI features, which differentiate cognitive impairments. Specifically, our framework highlighted group-specific differences in functional connectivity, validating its capability to capture meaningful insights from high-dimensional fMRI data.DiscussionOur novel interpretable fusion analytic framework addresses the challenges of analyzing high-dimensional, resting-state fMRI data. By integrating FCNs, a Self-Attention Deep Learning Model, and LSIRM, the framework provides an innovative approach to discovering ROI connectivity disparities between groups. The attention distribution and group-representative ROI features offer interpretable insights into brain activity patterns and their variations among cognitive impairment groups. This methodology has significant potential to enhance our understanding of cognitive impairments, paving the way for more targeted therapeutic interventions.
format Article
id doaj-art-16efa7c0c3184ad9bd0337f82fbcaa55
institution Kabale University
issn 1662-453X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-16efa7c0c3184ad9bd0337f82fbcaa552024-12-11T06:45:00ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2024-12-011810.3389/fnins.2024.14026571402657A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRIYeseul Jeon0Jeong-Jae Kim1SuMin Yu2Junggu Choi3Sanghoon Han4Sanghoon Han5Department of Statistics, Texas A&M University, College Station, TX, United StatesGraduate Program in Cognitive Science, Yonsei University, Seoul, Republic of KoreaDepartment of Psychology and Neuroscience, Duke University, Durham, NC, United StatesCancer Biology, Cleveland Clinic, Lerner Research Institute, Cleveland, OH, United StatesGraduate Program in Cognitive Science, Yonsei University, Seoul, Republic of KoreaDepartment of Psychology, Yonsei University, Seoul, Republic of KoreaIntroductionFunctional magnetic resonance imaging (fMRI) data is highly complex and high-dimensional, capturing signals from regions of interest (ROIs) with intricate correlations. Analyzing such data is particularly challenging, especially in resting-state fMRI, where patterns are less identifiable without task-specific contexts. Nonetheless, interconnections among ROIs provide essential insights into brain activity and exhibit unique characteristics across groups.MethodsTo address these challenges, we propose an interpretable fusion analytic framework to identify and understand ROI connectivity differences between two groups, revealing their distinctive features. The framework involves three steps: first, constructing ROI-based Functional Connectivity Networks (FCNs) to manage resting-state fMRI data; second, employing a Self-Attention Deep Learning Model (Self-Attn) for binary classification to generate attention distributions encoding group-level differences; and third, utilizing a Latent Space Item-Response Model (LSIRM) to extract group-representative ROI features, visualized on group summary FCNs.ResultsWe applied our framework to analyze four types of cognitive impairments, demonstrating their effectiveness in identifying significant ROIs that contribute to the differences between the two disease groups. The results reveal distinct connectivity patterns and unique ROI features, which differentiate cognitive impairments. Specifically, our framework highlighted group-specific differences in functional connectivity, validating its capability to capture meaningful insights from high-dimensional fMRI data.DiscussionOur novel interpretable fusion analytic framework addresses the challenges of analyzing high-dimensional, resting-state fMRI data. By integrating FCNs, a Self-Attention Deep Learning Model, and LSIRM, the framework provides an innovative approach to discovering ROI connectivity disparities between groups. The attention distribution and group-representative ROI features offer interpretable insights into brain activity patterns and their variations among cognitive impairment groups. This methodology has significant potential to enhance our understanding of cognitive impairments, paving the way for more targeted therapeutic interventions.https://www.frontiersin.org/articles/10.3389/fnins.2024.1402657/fullfMRIADNIfunctional connectivity networkdeep learningLatent Space Item-Response Model
spellingShingle Yeseul Jeon
Jeong-Jae Kim
SuMin Yu
Junggu Choi
Sanghoon Han
Sanghoon Han
A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
Frontiers in Neuroscience
fMRI
ADNI
functional connectivity network
deep learning
Latent Space Item-Response Model
title A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
title_full A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
title_fullStr A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
title_full_unstemmed A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
title_short A fusion analytic framework for investigating functional brain connectivity differences using resting-state fMRI
title_sort fusion analytic framework for investigating functional brain connectivity differences using resting state fmri
topic fMRI
ADNI
functional connectivity network
deep learning
Latent Space Item-Response Model
url https://www.frontiersin.org/articles/10.3389/fnins.2024.1402657/full
work_keys_str_mv AT yeseuljeon afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT jeongjaekim afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT suminyu afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT jungguchoi afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT sanghoonhan afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT sanghoonhan afusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT yeseuljeon fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT jeongjaekim fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT suminyu fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT jungguchoi fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT sanghoonhan fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri
AT sanghoonhan fusionanalyticframeworkforinvestigatingfunctionalbrainconnectivitydifferencesusingrestingstatefmri