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.
N1 - Publisher Copyright:
© 2020 IEEE.
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 - Schizophrenia
KW - dynamic functional network connectivity
KW - feature learning
KW - machine learning
KW - resting-state fMRI
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 -