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 language | English (US) |
|---|---|
| Title of host publication | Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 |
| Editors | Michael B. Matthews |
| Publisher | IEEE Computer Society |
| Pages | 1197-1201 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781538692189 |
| DOIs | |
| State | Published - Feb 19 2019 |
| Event | 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States Duration: Oct 28 2018 → Oct 31 2018 |
Publication series
| Name | Conference Record - Asilomar Conference on Signals, Systems and Computers |
|---|---|
| Volume | 2018-October |
| ISSN (Print) | 1058-6393 |
Conference
| Conference | 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 |
|---|---|
| Country | United States |
| City | Pacific Grove |
| Period | 10/28/18 → 10/31/18 |
Fingerprint
Cite this
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 proceeding › Conference contribution
}
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
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 -