Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging

Shu Hsien Chu, Christophe Lenglet, Mindy Westlund Schreiner, Bonnie Klimes-Dougan, Kathryn R Cullen, Keshab K Parhi

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

Abstract

Adolescence is a period of rapid brain maturation and a critical period for the onset of Major Depressive Disorder (MDD) that usually leads to serious outcomes such as suicide. Although changes in anatomical connectivity in MDD have been reported, changes in network topology for MDD remain unclear. Additionally, whether the changes are the same for adolescent MDD and adult MDD remains unclear as well. This paper explores anatomical features including: a) anatomical connectivity defined by diffusion tensor imaging measurements between a pair of brain regions, and b) topological measurements from anatomical networks, and apply machine learning approaches to identify responsive biomarkers distinguishing MDD patients from healthy subjects. In addition to statistical tests, univariate classifiers are designed to evaluate the discriminating power of features. Furthermore, multivariate classifiers are trained for distinguishing healthy subjects from MDD patients. The best classifier achieves an accuracy of 76.56%, 81.08% sensitivity, 70.37% specificity and 78.95% precision for 64 subjects (37 MDD and 27 matched healthy control). The selected features include: 1) betweenness centrality of the right lingual gyrus of the ADC network at 12% sparsity, 2) participation coefficient of the right pars opercularis of the AD network at 16% sparsity, 3) participation coefficient of the left insular cortex of the MD network at 21% sparsity, and 4) participation coefficient of the right lateral orbitofrontal cortex in the ADC network at 10% sparsity. These features reflect changes in the topological structure of the brain anatomical network in MDD.

Original languageEnglish (US)
Title of host publicationConference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages1197-1201
Number of pages5
ISBN (Electronic)9781538692189
DOIs
StatePublished - Feb 19 2019
Event52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States
Duration: Oct 28 2018Oct 31 2018

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2018-October
ISSN (Print)1058-6393

Conference

Conference52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
CountryUnited States
CityPacific Grove
Period10/28/1810/31/18

Fingerprint

Brain
Classifiers
Imaging techniques
Diffusion tensor imaging
Statistical tests
Biomarkers
Learning systems
Topology

Cite this

Chu, S. H., Lenglet, C., Schreiner, M. W., Klimes-Dougan, B., Cullen, K. R., & Parhi, K. K. (2019). Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging. In M. B. Matthews (Ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 (pp. 1197-1201). [8645542] (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2018.8645542

Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging. / Chu, Shu Hsien; Lenglet, Christophe; Schreiner, Mindy Westlund; Klimes-Dougan, Bonnie; Cullen, Kathryn R; Parhi, Keshab K.

Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. ed. / Michael B. Matthews. IEEE Computer Society, 2019. p. 1197-1201 8645542 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October).

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

Chu, SH, Lenglet, C, Schreiner, MW, Klimes-Dougan, B, Cullen, KR & Parhi, KK 2019, Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging. in MB Matthews (ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018., 8645542, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2018-October, IEEE Computer Society, pp. 1197-1201, 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018, Pacific Grove, United States, 10/28/18. https://doi.org/10.1109/ACSSC.2018.8645542
Chu SH, Lenglet C, Schreiner MW, Klimes-Dougan B, Cullen KR, Parhi KK. Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging. In Matthews MB, editor, Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. IEEE Computer Society. 2019. p. 1197-1201. 8645542. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2018.8645542
Chu, Shu Hsien ; Lenglet, Christophe ; Schreiner, Mindy Westlund ; Klimes-Dougan, Bonnie ; Cullen, Kathryn R ; Parhi, Keshab K. / Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging. Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. editor / Michael B. Matthews. IEEE Computer Society, 2019. pp. 1197-1201 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
@inproceedings{e7e341be127744f396b12c6e0c6747fb,
title = "Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging",
abstract = "Adolescence is a period of rapid brain maturation and a critical period for the onset of Major Depressive Disorder (MDD) that usually leads to serious outcomes such as suicide. Although changes in anatomical connectivity in MDD have been reported, changes in network topology for MDD remain unclear. Additionally, whether the changes are the same for adolescent MDD and adult MDD remains unclear as well. This paper explores anatomical features including: a) anatomical connectivity defined by diffusion tensor imaging measurements between a pair of brain regions, and b) topological measurements from anatomical networks, and apply machine learning approaches to identify responsive biomarkers distinguishing MDD patients from healthy subjects. In addition to statistical tests, univariate classifiers are designed to evaluate the discriminating power of features. Furthermore, multivariate classifiers are trained for distinguishing healthy subjects from MDD patients. The best classifier achieves an accuracy of 76.56{\%}, 81.08{\%} sensitivity, 70.37{\%} specificity and 78.95{\%} precision for 64 subjects (37 MDD and 27 matched healthy control). The selected features include: 1) betweenness centrality of the right lingual gyrus of the ADC network at 12{\%} sparsity, 2) participation coefficient of the right pars opercularis of the AD network at 16{\%} sparsity, 3) participation coefficient of the left insular cortex of the MD network at 21{\%} sparsity, and 4) participation coefficient of the right lateral orbitofrontal cortex in the ADC network at 10{\%} sparsity. These features reflect changes in the topological structure of the brain anatomical network in MDD.",
author = "Chu, {Shu Hsien} and Christophe Lenglet and Schreiner, {Mindy Westlund} and Bonnie Klimes-Dougan and Cullen, {Kathryn R} and Parhi, {Keshab K}",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/ACSSC.2018.8645542",
language = "English (US)",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "1197--1201",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018",

}

TY - GEN

T1 - Classifying Adolescent Major Depressive Disorder using Linear SVM with Anatomical Features from Diffusion Weighted Imaging

AU - Chu, Shu Hsien

AU - Lenglet, Christophe

AU - Schreiner, Mindy Westlund

AU - Klimes-Dougan, Bonnie

AU - Cullen, Kathryn R

AU - Parhi, Keshab K

PY - 2019/2/19

Y1 - 2019/2/19

N2 - Adolescence is a period of rapid brain maturation and a critical period for the onset of Major Depressive Disorder (MDD) that usually leads to serious outcomes such as suicide. Although changes in anatomical connectivity in MDD have been reported, changes in network topology for MDD remain unclear. Additionally, whether the changes are the same for adolescent MDD and adult MDD remains unclear as well. This paper explores anatomical features including: a) anatomical connectivity defined by diffusion tensor imaging measurements between a pair of brain regions, and b) topological measurements from anatomical networks, and apply machine learning approaches to identify responsive biomarkers distinguishing MDD patients from healthy subjects. In addition to statistical tests, univariate classifiers are designed to evaluate the discriminating power of features. Furthermore, multivariate classifiers are trained for distinguishing healthy subjects from MDD patients. The best classifier achieves an accuracy of 76.56%, 81.08% sensitivity, 70.37% specificity and 78.95% precision for 64 subjects (37 MDD and 27 matched healthy control). The selected features include: 1) betweenness centrality of the right lingual gyrus of the ADC network at 12% sparsity, 2) participation coefficient of the right pars opercularis of the AD network at 16% sparsity, 3) participation coefficient of the left insular cortex of the MD network at 21% sparsity, and 4) participation coefficient of the right lateral orbitofrontal cortex in the ADC network at 10% sparsity. These features reflect changes in the topological structure of the brain anatomical network in MDD.

AB - Adolescence is a period of rapid brain maturation and a critical period for the onset of Major Depressive Disorder (MDD) that usually leads to serious outcomes such as suicide. Although changes in anatomical connectivity in MDD have been reported, changes in network topology for MDD remain unclear. Additionally, whether the changes are the same for adolescent MDD and adult MDD remains unclear as well. This paper explores anatomical features including: a) anatomical connectivity defined by diffusion tensor imaging measurements between a pair of brain regions, and b) topological measurements from anatomical networks, and apply machine learning approaches to identify responsive biomarkers distinguishing MDD patients from healthy subjects. In addition to statistical tests, univariate classifiers are designed to evaluate the discriminating power of features. Furthermore, multivariate classifiers are trained for distinguishing healthy subjects from MDD patients. The best classifier achieves an accuracy of 76.56%, 81.08% sensitivity, 70.37% specificity and 78.95% precision for 64 subjects (37 MDD and 27 matched healthy control). The selected features include: 1) betweenness centrality of the right lingual gyrus of the ADC network at 12% sparsity, 2) participation coefficient of the right pars opercularis of the AD network at 16% sparsity, 3) participation coefficient of the left insular cortex of the MD network at 21% sparsity, and 4) participation coefficient of the right lateral orbitofrontal cortex in the ADC network at 10% sparsity. These features reflect changes in the topological structure of the brain anatomical network in MDD.

UR - http://www.scopus.com/inward/record.url?scp=85063003284&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063003284&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2018.8645542

DO - 10.1109/ACSSC.2018.8645542

M3 - Conference contribution

AN - SCOPUS:85063003284

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1197

EP - 1201

BT - Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018

A2 - Matthews, Michael B.

PB - IEEE Computer Society

ER -