A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia

Mohammad S.E. Sendi; Elaheh Zendehrouh; Zening Fu; Babak Mahmoudi; Robyn L. Miller; Vince D. Calhoun

doi:10.1109/SSIAI49293.2020.9094620

A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia

Mohammad S.E. Sendi, Elaheh Zendehrouh, Zening Fu, Babak Mahmoudi, Robyn L. Miller, Vince D. Calhoun

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Schizophrenia (SZ) is a severe neuropsychiatric disorder with a hallmark of functional dysconnectivity between numerous brain regions. With an implicit assumption of stationary brain interactions during the scanning period, most of the resting-state functional magnetic resonance imaging (fMRI) studies are conducted on static functional network connectivity (sFNC). Dynamic functional network connectivity (dFNC) that explores temporal patterns of functional connectivity (FC) might provide additional information to its static counterpart. In this work, we first estimate latent features (called connectivity states) by applying k-means clustering on dFNC. Next, using the estimated latent features, we trained and tested a classifier, which can differentiate SZ from healthy control (HC) subjects with 71% accuracy. Using a feature selection method embedded in the classifier, we have highlighted the role of transition probabilities between states as potential biomarkers and identified the role of lightly modularized transient connectivity state in pulling healthy subjects out of both highly modularized and very disconnected states. This will offer some new understandings about the way the healthy brain shifts between the most and the least connected states of whole brain connectivity.

Original language	English (US)
Title of host publication	2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	112-115
Number of pages	4
ISBN (Electronic)	9781728157450
DOIs	https://doi.org/10.1109/SSIAI49293.2020.9094620
State	Published - Mar 2020
Externally published	Yes
Event	2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Santa Fe, United States Duration: Mar 29 2020 → Mar 31 2020

Publication series

Name	Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume	2020-March

Conference

Conference	2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020
Country	United States
City	Santa Fe
Period	3/29/20 → 3/31/20

Keywords

dynamic functional network connectivity
feature learning
machine learning
resting-state fMRI
Schizophrenia

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/SSIAI49293.2020.9094620

Fingerprint Dive into the research topics of 'A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia'. Together they form a unique fingerprint.

Cite this

Sendi, M. S. E., Zendehrouh, E., Fu, Z., Mahmoudi, B., Miller, R. L., & Calhoun, V. D. (2020). A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia. In 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings (pp. 112-115). [9094620] (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2020-March). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSIAI49293.2020.9094620

A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia. / Sendi, Mohammad S.E.; Zendehrouh, Elaheh; Fu, Zening; Mahmoudi, Babak; Miller, Robyn L.; Calhoun, Vince D.

2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. p. 112-115 9094620 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation; Vol. 2020-March).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sendi, MSE, Zendehrouh, E, Fu, Z, Mahmoudi, B, Miller, RL & Calhoun, VD 2020, A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia. in 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings., 9094620, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, vol. 2020-March, Institute of Electrical and Electronics Engineers Inc., pp. 112-115, 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020, Santa Fe, United States, 3/29/20. https://doi.org/10.1109/SSIAI49293.2020.9094620

Sendi MSE, Zendehrouh E, Fu Z, Mahmoudi B, Miller RL, Calhoun VD. A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia. In 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 112-115. 9094620. (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation). https://doi.org/10.1109/SSIAI49293.2020.9094620

Sendi, Mohammad S.E. ; Zendehrouh, Elaheh ; Fu, Zening ; Mahmoudi, Babak ; Miller, Robyn L. ; Calhoun, Vince D. / A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia. 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 112-115 (Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation).

@inproceedings{00e95670cfd843fc9a6392ab2c50107f,

title = "A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia",

abstract = "Schizophrenia (SZ) is a severe neuropsychiatric disorder with a hallmark of functional dysconnectivity between numerous brain regions. With an implicit assumption of stationary brain interactions during the scanning period, most of the resting-state functional magnetic resonance imaging (fMRI) studies are conducted on static functional network connectivity (sFNC). Dynamic functional network connectivity (dFNC) that explores temporal patterns of functional connectivity (FC) might provide additional information to its static counterpart. In this work, we first estimate latent features (called connectivity states) by applying k-means clustering on dFNC. Next, using the estimated latent features, we trained and tested a classifier, which can differentiate SZ from healthy control (HC) subjects with 71% accuracy. Using a feature selection method embedded in the classifier, we have highlighted the role of transition probabilities between states as potential biomarkers and identified the role of lightly modularized transient connectivity state in pulling healthy subjects out of both highly modularized and very disconnected states. This will offer some new understandings about the way the healthy brain shifts between the most and the least connected states of whole brain connectivity.",

keywords = "dynamic functional network connectivity, feature learning, machine learning, resting-state fMRI, Schizophrenia",

author = "Sendi, {Mohammad S.E.} and Elaheh Zendehrouh and Zening Fu and Babak Mahmoudi and Miller, {Robyn L.} and Calhoun, {Vince D.}",

year = "2020",

month = mar,

doi = "10.1109/SSIAI49293.2020.9094620",

language = "English (US)",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "112--115",

booktitle = "2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings",

note = "2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 ; Conference date: 29-03-2020 Through 31-03-2020",

}

TY - GEN

T1 - A Machine Learning Model for Exploring Aberrant Functional Network Connectivity Transition in Schizophrenia

AU - Sendi, Mohammad S.E.

AU - Zendehrouh, Elaheh

AU - Fu, Zening

AU - Mahmoudi, Babak

AU - Miller, Robyn L.

AU - Calhoun, Vince D.

PY - 2020/3

Y1 - 2020/3

N2 - Schizophrenia (SZ) is a severe neuropsychiatric disorder with a hallmark of functional dysconnectivity between numerous brain regions. With an implicit assumption of stationary brain interactions during the scanning period, most of the resting-state functional magnetic resonance imaging (fMRI) studies are conducted on static functional network connectivity (sFNC). Dynamic functional network connectivity (dFNC) that explores temporal patterns of functional connectivity (FC) might provide additional information to its static counterpart. In this work, we first estimate latent features (called connectivity states) by applying k-means clustering on dFNC. Next, using the estimated latent features, we trained and tested a classifier, which can differentiate SZ from healthy control (HC) subjects with 71% accuracy. Using a feature selection method embedded in the classifier, we have highlighted the role of transition probabilities between states as potential biomarkers and identified the role of lightly modularized transient connectivity state in pulling healthy subjects out of both highly modularized and very disconnected states. This will offer some new understandings about the way the healthy brain shifts between the most and the least connected states of whole brain connectivity.

AB - Schizophrenia (SZ) is a severe neuropsychiatric disorder with a hallmark of functional dysconnectivity between numerous brain regions. With an implicit assumption of stationary brain interactions during the scanning period, most of the resting-state functional magnetic resonance imaging (fMRI) studies are conducted on static functional network connectivity (sFNC). Dynamic functional network connectivity (dFNC) that explores temporal patterns of functional connectivity (FC) might provide additional information to its static counterpart. In this work, we first estimate latent features (called connectivity states) by applying k-means clustering on dFNC. Next, using the estimated latent features, we trained and tested a classifier, which can differentiate SZ from healthy control (HC) subjects with 71% accuracy. Using a feature selection method embedded in the classifier, we have highlighted the role of transition probabilities between states as potential biomarkers and identified the role of lightly modularized transient connectivity state in pulling healthy subjects out of both highly modularized and very disconnected states. This will offer some new understandings about the way the healthy brain shifts between the most and the least connected states of whole brain connectivity.

KW - dynamic functional network connectivity

KW - feature learning

KW - machine learning

KW - resting-state fMRI

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85085522569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85085522569&partnerID=8YFLogxK

U2 - 10.1109/SSIAI49293.2020.9094620

DO - 10.1109/SSIAI49293.2020.9094620

M3 - Conference contribution

AN - SCOPUS:85085522569

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 112

EP - 115

BT - 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Southwest Symposium on Image Analysis and Interpretation, SSIAI 2020

Y2 - 29 March 2020 through 31 March 2020

ER -