Identifying resting‐state effective connectivity abnormalities in drug‐naïve major depressive disorder diagnosis via graph convolutional networks

• Published in: Human brain mapping Vol. 41; no. 17; pp. 4997 - 5014
• Main Authors: Jun, Eunji, Na, Kyoung‐Sae, Kang, Wooyoung, Lee, Jiyeon, Suk, Heung‐Il, Ham, Byung‐Joo
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.12.2020
• Subjects: Abnormalities; Artificial neural networks; Brain; Brain mapping; deep learning; Diagnosis; effective connectivity; Functional magnetic resonance imaging; graph convolutional networks (GCNs); Magnetic resonance imaging; major depressive disorder (MDD); Medical imaging; Mental depression; Neural networks; Neuroimaging; Phenotypes; resting‐state functional magnetic resonance imaging (rs‐fMRI); Sensitivity analysis; Signs and symptoms; Sparse Group LASSO; deep learning; Sparse Group LASSO; resting-state functional magnetic resonance imaging (rs-fMRI); graph convolutional networks (GCNs); major depressive disorder (MDD); effective connectivity
• ISSN: 1065-9471; 1097-0193
• DOI: 10.1002/hbm.25175

Major depressive disorder (MDD) is a leading cause of disability; its symptoms interfere with social, occupational, interpersonal, and academic functioning. However, the diagnosis of MDD is still made by phenomenological approach. The advent of neuroimaging techniques allowed numerous studies to use resting‐state functional magnetic resonance imaging (rs‐fMRI) and estimate functional connectivity for brain‐disease identification. Recently, attempts have been made to investigate effective connectivity (EC) that represents causal relations among regions of interest. In the meantime, to identify meaningful phenotypes for clinical diagnosis, graph‐based approaches such as graph convolutional networks (GCNs) have been leveraged recently to explore complex pairwise similarities in imaging/nonimaging features among subjects. In this study, we validate the use of EC for MDD identification by estimating its measures via a group sparse representation along with a structured equation modeling approach in a whole‐brain data‐driven manner from rs‐fMRI. To distinguish drug‐naïve MDD patients from healthy controls, we utilize spectral GCNs based on a population graph to successfully integrate EC and nonimaging phenotypic information. Furthermore, we devise a novel sensitivity analysis method to investigate the discriminant connections for MDD identification in our trained GCNs. Our experimental results validated the effectiveness of our method in various scenarios, and we identified altered connectivities associated with the diagnosis of MDD. This study validated the use of effective connectivity (EC) for major depressive disorder (MDD) identification by estimating its measures via a group sparse representation along with a structured equation modeling approach in a whole‐brain data‐driven manner from resting‐state functional magnetic resonance imaging. To distinguish drug‐naive MDD patients from healthy controls, we utilize spectral graph convolutional networks (GCNs) based on a population graph to successfully integrate EC and nonimaging phenotypic information. Furthermore, we devise a novel sensitivity analysis method to investigate the discriminant connections for MDD identification in our trained GCNs.