Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model

2023-11-18

AI Summary

This study addresses the limited diagnostic utility of structural neuroimaging for major depressive disorder (MDD), particularly regarding cross-site generalizability. Method: Leveraging the ENIGMA-MDD multisite cohort (N = 7,012), we systematically evaluated the discriminative power of vertex-wise sulcal depth, cortical curvature, and cortical thickness—integrated via feature fusion—for MDD classification. Morphometric features were extracted using FreeSurfer, and models (DenseNet and SVM) were rigorously validated using strict leave-one-site-out cross-validation. Contribution/Results: Both models achieved near-chance balanced accuracy on independent test sites (DenseNet: 51%; SVM: 53%), indicating that current combinations of static structural morphometric features lack robustness and generalizability across centers. This finding underscores a fundamental limitation of unimodal structural biomarkers in clinical translation and provides empirical impetus for integrating functional, connectivity-based, or dynamic neuroimaging features in future MDD diagnostic frameworks.

Abstract

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. Here, we used globally representative data from the ENIGMA-MDD working group containing 7,012 participants from 30 sites (N=2,772 MDD and N=4,240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of such features and classifiers is unfeasible. Perhaps more sophisticated integration of multimodal information may lead to a higher performance in this diagnostic task.

Problem

• Brain Morphology Analysis
• Major Depressive Disorder (MDD)
• Diagnosis and Treatment Improvement

Innovation

• Deep Learning
• DenseNet SVM
• MDD Diagnosis