A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear: Application to schizophrenia, bipolar, and schizoaffective disorders

Yuhui Du, Godfrey D. Pearlson, Jingyu Liu, Jing Sui, Qingbao Yu, Hao He, Eduardo Castro, Vince Daniel Calhoun

Research output: Contribution to journalArticle

Abstract

Schizophrenia (SZ), bipolar disorder (BP) and schizoaffective disorder (SAD) share some common symptoms, and there is still a debate about whether SAD is an independent category. To the best of our knowledge, no study has been done to differentiate these three disorders or to investigate the distinction of SAD as an independent category using fMRI data. This study is aimed to explore biomarkers from resting-state fMRI networks for differentiating these disorders and investigate the relationship among these disorders based on fMRI networks with an emphasis on SAD. Firstly, a novel group ICA method, group information guided independent component analysis (GIG-ICA), was applied to extract subject-specific brain networks from fMRI data of 20 healthy controls (HC), 20 SZ patients, 20 BP patients, 20 patients suffering from SAD with manic episodes (SADM), and 13 patients suffering from SAD with depressive episodes exclusively (SADD). Then, five-level one-way analysis of covariance and multiclass support vector machine recursive feature elimination were employed to identify discriminative regions from the networks. Subsequently, the t-distributed stochastic neighbor embedding (t-SNE) projection and the hierarchical clustering were implemented to investigate the relationship among those groups. Finally, to evaluate the generalization ability, 16 new subjects were classified based on the found regions and the trained model using original 93 subjects. Results show that the discriminative regions mainly included frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insula and supramarginal cortices, which performed well in distinguishing different groups. SADM and SADD were the most similar to each other, although SADD had greater similarity to SZ compared to other groups, which indicates that SAD may be an independent category. BP was closer to HC compared with other psychotic disorders. In summary, resting-state fMRI brain networks extracted via GIG-ICA provide a promising potential to differentiate SZ, BP, and SAD.

Original languageEnglish (US)
Pages (from-to)272-280
Number of pages9
JournalNeuroImage
Volume122
DOIs
StatePublished - Nov 5 2015
Externally publishedYes

Fingerprint

Bipolar Disorder
Psychotic Disorders
Schizophrenia
Magnetic Resonance Imaging
Parietal Lobe
Aptitude
Brain
Cluster Analysis
Biomarkers

Keywords

  • Bipolar disorder
  • Functional magnetic resonance imaging
  • Independent component analysis
  • Resting-state brain intrinsic networks
  • Schizoaffective disorder
  • Schizophrenia

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear : Application to schizophrenia, bipolar, and schizoaffective disorders. / Du, Yuhui; Pearlson, Godfrey D.; Liu, Jingyu; Sui, Jing; Yu, Qingbao; He, Hao; Castro, Eduardo; Calhoun, Vince Daniel.

In: NeuroImage, Vol. 122, 05.11.2015, p. 272-280.

Research output: Contribution to journalArticle

Du, Yuhui ; Pearlson, Godfrey D. ; Liu, Jingyu ; Sui, Jing ; Yu, Qingbao ; He, Hao ; Castro, Eduardo ; Calhoun, Vince Daniel. / A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear : Application to schizophrenia, bipolar, and schizoaffective disorders. In: NeuroImage. 2015 ; Vol. 122. pp. 272-280.
@article{80645d56c2a7415190e94a2048adcb54,
title = "A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear: Application to schizophrenia, bipolar, and schizoaffective disorders",
abstract = "Schizophrenia (SZ), bipolar disorder (BP) and schizoaffective disorder (SAD) share some common symptoms, and there is still a debate about whether SAD is an independent category. To the best of our knowledge, no study has been done to differentiate these three disorders or to investigate the distinction of SAD as an independent category using fMRI data. This study is aimed to explore biomarkers from resting-state fMRI networks for differentiating these disorders and investigate the relationship among these disorders based on fMRI networks with an emphasis on SAD. Firstly, a novel group ICA method, group information guided independent component analysis (GIG-ICA), was applied to extract subject-specific brain networks from fMRI data of 20 healthy controls (HC), 20 SZ patients, 20 BP patients, 20 patients suffering from SAD with manic episodes (SADM), and 13 patients suffering from SAD with depressive episodes exclusively (SADD). Then, five-level one-way analysis of covariance and multiclass support vector machine recursive feature elimination were employed to identify discriminative regions from the networks. Subsequently, the t-distributed stochastic neighbor embedding (t-SNE) projection and the hierarchical clustering were implemented to investigate the relationship among those groups. Finally, to evaluate the generalization ability, 16 new subjects were classified based on the found regions and the trained model using original 93 subjects. Results show that the discriminative regions mainly included frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insula and supramarginal cortices, which performed well in distinguishing different groups. SADM and SADD were the most similar to each other, although SADD had greater similarity to SZ compared to other groups, which indicates that SAD may be an independent category. BP was closer to HC compared with other psychotic disorders. In summary, resting-state fMRI brain networks extracted via GIG-ICA provide a promising potential to differentiate SZ, BP, and SAD.",
keywords = "Bipolar disorder, Functional magnetic resonance imaging, Independent component analysis, Resting-state brain intrinsic networks, Schizoaffective disorder, Schizophrenia",
author = "Yuhui Du and Pearlson, {Godfrey D.} and Jingyu Liu and Jing Sui and Qingbao Yu and Hao He and Eduardo Castro and Calhoun, {Vince Daniel}",
year = "2015",
month = "11",
day = "5",
doi = "10.1016/j.neuroimage.2015.07.054",
language = "English (US)",
volume = "122",
pages = "272--280",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear

T2 - Application to schizophrenia, bipolar, and schizoaffective disorders

AU - Du, Yuhui

AU - Pearlson, Godfrey D.

AU - Liu, Jingyu

AU - Sui, Jing

AU - Yu, Qingbao

AU - He, Hao

AU - Castro, Eduardo

AU - Calhoun, Vince Daniel

PY - 2015/11/5

Y1 - 2015/11/5

N2 - Schizophrenia (SZ), bipolar disorder (BP) and schizoaffective disorder (SAD) share some common symptoms, and there is still a debate about whether SAD is an independent category. To the best of our knowledge, no study has been done to differentiate these three disorders or to investigate the distinction of SAD as an independent category using fMRI data. This study is aimed to explore biomarkers from resting-state fMRI networks for differentiating these disorders and investigate the relationship among these disorders based on fMRI networks with an emphasis on SAD. Firstly, a novel group ICA method, group information guided independent component analysis (GIG-ICA), was applied to extract subject-specific brain networks from fMRI data of 20 healthy controls (HC), 20 SZ patients, 20 BP patients, 20 patients suffering from SAD with manic episodes (SADM), and 13 patients suffering from SAD with depressive episodes exclusively (SADD). Then, five-level one-way analysis of covariance and multiclass support vector machine recursive feature elimination were employed to identify discriminative regions from the networks. Subsequently, the t-distributed stochastic neighbor embedding (t-SNE) projection and the hierarchical clustering were implemented to investigate the relationship among those groups. Finally, to evaluate the generalization ability, 16 new subjects were classified based on the found regions and the trained model using original 93 subjects. Results show that the discriminative regions mainly included frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insula and supramarginal cortices, which performed well in distinguishing different groups. SADM and SADD were the most similar to each other, although SADD had greater similarity to SZ compared to other groups, which indicates that SAD may be an independent category. BP was closer to HC compared with other psychotic disorders. In summary, resting-state fMRI brain networks extracted via GIG-ICA provide a promising potential to differentiate SZ, BP, and SAD.

AB - Schizophrenia (SZ), bipolar disorder (BP) and schizoaffective disorder (SAD) share some common symptoms, and there is still a debate about whether SAD is an independent category. To the best of our knowledge, no study has been done to differentiate these three disorders or to investigate the distinction of SAD as an independent category using fMRI data. This study is aimed to explore biomarkers from resting-state fMRI networks for differentiating these disorders and investigate the relationship among these disorders based on fMRI networks with an emphasis on SAD. Firstly, a novel group ICA method, group information guided independent component analysis (GIG-ICA), was applied to extract subject-specific brain networks from fMRI data of 20 healthy controls (HC), 20 SZ patients, 20 BP patients, 20 patients suffering from SAD with manic episodes (SADM), and 13 patients suffering from SAD with depressive episodes exclusively (SADD). Then, five-level one-way analysis of covariance and multiclass support vector machine recursive feature elimination were employed to identify discriminative regions from the networks. Subsequently, the t-distributed stochastic neighbor embedding (t-SNE) projection and the hierarchical clustering were implemented to investigate the relationship among those groups. Finally, to evaluate the generalization ability, 16 new subjects were classified based on the found regions and the trained model using original 93 subjects. Results show that the discriminative regions mainly included frontal, parietal, precuneus, cingulate, supplementary motor, cerebellar, insula and supramarginal cortices, which performed well in distinguishing different groups. SADM and SADD were the most similar to each other, although SADD had greater similarity to SZ compared to other groups, which indicates that SAD may be an independent category. BP was closer to HC compared with other psychotic disorders. In summary, resting-state fMRI brain networks extracted via GIG-ICA provide a promising potential to differentiate SZ, BP, and SAD.

KW - Bipolar disorder

KW - Functional magnetic resonance imaging

KW - Independent component analysis

KW - Resting-state brain intrinsic networks

KW - Schizoaffective disorder

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=84939635527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939635527&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2015.07.054

DO - 10.1016/j.neuroimage.2015.07.054

M3 - Article

C2 - 26216278

AN - SCOPUS:84939635527

VL - 122

SP - 272

EP - 280

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -