Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Oct 3.
doi: 10.1038/s41380-025-03273-w. Online ahead of print.

Classification of major depressive disorder using vertex-wise brain sulcal depth, curvature, and thickness with a deep and a shallow learning model

Roberto Goya-Maldonado  1 Tracy Erwin-Grabner  2 Ling-Li Zeng  3   4 Christopher R K Ching  4 Andre Aleman  5 Alyssa R Amod  6 Zeynep Basgoze  7 Francesco Benedetti  8 Bianca Besteher  9 Katharina Brosch  10 Robin Bülow  11 Romain Colle  12   13 Colm G Connolly  14 Emmanuelle Corruble  12   13 Baptiste Couvy-Duchesne  15   16 Kathryn Cullen  7 Udo Dannlowski  17 Christopher G Davey  18 Annemiek Dols  19   20 Jan Ernsting  17 Jennifer W Evans  21 Lukas Fisch  17 Paola Fuentes-Claramonte  22 Ali Saffet Gonul  23 Ian H Gotlib  24 Hans J Grabe  25 Nynke A Groenewold  6 Dominik Grotegerd  17 Tim Hahn  17 J Paul Hamilton  26 Laura K M Han  27   28 Ben J Harrison  18 Tiffany C Ho  29   30 Neda Jahanshad  4 Alec J Jamieson  18 Andriana Karuk  22 Tilo Kircher  10 Bonnie Klimes-Dougan  31 Sheri-Michelle Koopowitz  6 Thomas Lancaster  32   33 Ramona Leenings  17 Meng Li  9 David E J Linden  32   33   34   35 Frank P MacMaster  36 David M A Mehler  17   32   33   37 Susanne Meinert  17   38 Elisa Melloni  8 Bryon A Mueller  7 Benson Mwangi  39 Igor Nenadić  10 Amar Ojha  40   41 Yasumasa Okamoto  42 Mardien L Oudega  19   43 Brenda W J H Penninx  19 Sara Poletti  8 Edith Pomarol-Clotet  22 Maria J Portella  44   45 Joaquim Radua  46 Elena Rodríguez-Cano  22 Matthew D Sacchet  47 Raymond Salvador  22 Anouk Schrantee  48 Kang Sim  49   50   51 Jair C Soares  39 Aleix Solanes  46 Dan J Stein  6 Frederike Stein  10 Aleks Stolicyn  52 Sophia I Thomopoulos  4 Yara J Toenders  27   28   53   54 Aslihan Uyar-Demir  23 Eduard Vieta  55 Yolanda Vives-Gilabert  56 Henry Völzke  57 Martin Walter  9 Heather C Whalley  52 Sarah Whittle  18 Nils Winter  17 Katharina Wittfeld  25 Margaret J Wright  58   59 Mon-Ju Wu  39 Tony T Yang  29 Carlos Zarate  60 Dick J Veltman  19 Lianne Schmaal  27   28 Paul M Thompson  4 ENIGMA Major Depressive Disorder working group
Collaborators, Affiliations

Classification of major depressive disorder using vertex-wise brain sulcal depth, curvature, and thickness with a deep and a shallow learning model

Roberto Goya-Maldonado et al. Mol Psychiatry. .

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. In this study, we used globally representative data from the ENIGMA-MDD working group containing 7012 participants from 31 sites (N = 2772 MDD and N = 4240 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. As we analyzed a multi-site sample, we additionally applied the ComBat harmonization tool to remove potential nuisance effects of site. 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 features and classifiers is unfeasible. Future studies are needed to determine whether more sophisticated integration of information from other MRI modalities such as fMRI and DWI will lead to a higher performance in this diagnostic task.

PubMed Disclaimer

Conflict of interest statement

Competing interests: PMT and NJ received a research grant from Biogen, Inc. for research unrelated to this manuscript. HJG has received travel grants and speakers’ honoraria from Fresenius Medical Care, Neuraxpharm, Servier and Janssen Cilag as well as research funding from Fresenius Medical Care unrelated to this manuscript. JCS has served as a consultant for Pfizer, Sunovion, Sanofi, Johnson & Johnson, Livanova, and Boehringer Ingelheim. The remaining authors declare no conflict of interest. Ethics approval and consent to participate: The study was approved by the Ethics Committee of the University Medical Center Göttingen (UMG), Germany. The study was approved by the Ethics Committee of the University Medical Center Göttingen (UMG), Germany. In accordance with the current version of the Declaration of Helsinki, all methods in the participating cohorts were approved by the respective institutional review boards and local ethics committees, and written informed consent was obtained from all participants. For participants under 18 years of age, written informed consent was additionally provided by a parent and/or legal guardian.

Update of

  • Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model.
    Goya-Maldonado R, Erwin-Grabner T, Zeng LL, Ching CRK, Aleman A, Amod AR, Basgoze Z, Benedetti F, Besteher B, Brosch K, Bülow R, Colle R, Connolly CG, Corruble E, Couvy-Duchesne B, Cullen K, Dannlowski U, Davey CG, Dols A, Ernsting J, Evans JW, Fisch L, Fuentes-Claramonte P, Gonul AS, Gotlib IH, Grabe HJ, Groenewold NA, Grotegerd D, Hahn T, Hamilton JP, Han LKM, Harrison BJ, Ho TC, Jahanshad N, Jamieson AJ, Karuk A, Kircher T, Klimes-Dougan B, Koopowitz SM, Lancaster T, Leenings R, Li M, Linden DEJ, MacMaster FP, Mehler DMA, Meinert S, Melloni E, Mueller BA, Mwangi B, Nenadić I, Ojha A, Okamoto Y, Oudega ML, Penninx BWJH, Poletti S, Pomarol-Clotet E, Portella MJ, Pozzi E, Radua J, Rodríguez-Cano E, Sacchet MD, Salvador R, Schrantee A, Sim K, Soares JC, Solanes A, Stein DJ, Stein F, Stolicyn A, Thomopoulos SI, Toenders YJ, Uyar-Demir A, Vieta E, Vives-Gilabert Y, Völzke H, Walter M, Whalley HC, Whittle S, Winter N, Wittfeld K, Wright MJ, Wu MJ, Yang TT, Zarate C, Veltman DJ, Schmaal L, Thompson PM; ENIGMA Major Depressive Disorder working group. Goya-Maldonado R, et al. ArXiv [Preprint]. 2025 Jan 24:arXiv:2311.11046v2. ArXiv. 2025. Update in: Mol Psychiatry. 2025 Oct 3. doi: 10.1038/s41380-025-03273-w. PMID: 39975425 Free PMC article. Updated. Preprint.

References

    1. Friedrich MJ. Depression is the leading cause of disability around the world. JAMA. 2017;317:1517 https://doi.org/10.1001/jama.2017.3826 - DOI - PubMed
    1. Machado M, Iskedjian M, Ruiz I, Einarson TR. Remission, dropouts, and adverse drug reaction rates in major depressive disorder: a meta-analysis of head-to-head trials. Curr Med Res Opin. 2006;22:1825–37. https://doi.org/10.1185/030079906X132415 - DOI - PubMed
    1. Mendlewicz J. Towards achieving remission in the treatment of depression. Dialogues Clin Neurosci. 2008;10:371–5. - DOI - PubMed - PMC
    1. Rush AJ, Trivedi MH, Wisniewski SR, Nierenberg AA, Stewart JW, Warden D, et al. Acute and longer-term outcomes in depressed outpatients requiring one or several treatment steps: a STAR*D report. Am J Psychiatry. 2006;163:1905–17. https://doi.org/10.1176/ajp.2006.163.11.1905 - DOI - PubMed
    1. Coffey CE, Wilkinson WE, Weiner RD, Parashos IA, Djang WT, Webb MC, et al. Quantitative cerebral anatomy in depression: a controlled magnetic resonance imaging study. Arch Gen Psychiatry. 1993;50:7–16. https://doi.org/10.1001/archpsyc.1993.01820130009002 - DOI - PubMed

LinkOut - more resources