Universum Inspired Graph Contrast Learning for Major Depressive Disorder Identification: In Functional Brain Network View
CNS Neuroscience & Therapeutics · 2026-09 · 32 (9)
DOI: 10.1002/cns.71158 ↗Kurz gefasst
Fachartikel in der Zeitschrift CNS Neuroscience & Therapeutics, online erschienen am 21.09.2026. Verfasst von Hao Qin und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China. Hauptthemen laut MEDLINE: Major Depressive Disorder, Brain, Nerve Net. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Research Project of Shanghai Municipal Health Commission, Scientific and the Technological Research Program of Chongqing Municipal Education Commission.
Abstract (Originalsprache)
Background
Major depressive disorder (MDD) is a serious psychological disorder marked by persistent feelings of sadness and a notable decline in daily functioning. Functional Brain Networks (FBNs) have become crucial biomarkers for the diagnosis of MDD, and Graph Convolutional Networks (GCNs) have demonstrated great potential in extracting FBN features. However, existing GCN methods typically depend on large‐scale labeled datasets and lack clinical interpretability in MDD identification, which limits their application.
Methods
We introduce Universum Inspired Graph Contrast Learning (Uni‐GCL), a novel graph‐based self‐supervised learning framework to relieve the demand for training sample size. Additionally, to enhance the clinical interpretability of GCNs, we optimized the Gradient‐weighted Class Activation Mapping (Grad‐CAM) method to enable it to effectively pinpoint the crucial nodes within the GCN.
Results
The Uni‐GCL method outperformed previous state‐of‐the‐art approaches. It improved accuracy by 3% at Site 21 and 5% at Site 1. Additionally, Uni‐GCL identified that brain regions FGoperc. R, CAU. L, FFG. R, AMYG. L, PUT. L, AMYG. R, PUT. R, THA. L, IFGtriang. R, FFG. L, INS. L, INS. R, HIP. L and HIP. R make significant contributions to the diagnosis of MDD.
Conclusions
Uni‐GCL can effectively reduce the sample size for model training and improve the diagnostic performance of MDD. Meanwhile, the adapted Grad‐CAM provides an effective tool to enhance the interpretability of GCN.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Science and Engineering, Chongqing Jiaotong University, Chongqing, China.
- Department of Radiology and Nuclear Medicine, School of Medicine, Tongji Hospital, Tongji University, Shanghai, China.
- Institute of Medical Imaging Artificial Intelligence, Tongji University School of Medicine, Shanghai, China.
- Department of Neurosurgery, The First Affiliated Hospital of Fujian Medical University, Fuzhou, China.
- College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University, Nanjing, China.
- School of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing, China.
ORCID-Profile: Di Ma, Weikai Li, Xiaowen Xu
Förderung
- National Natural Science Foundation of China
- Research Project of Shanghai Municipal Health Commission
- Scientific and the Technological Research Program of Chongqing Municipal Education Commission
- Taishan Scholars Foundation of Shandong Province
- Joint Training Base Construction Project for Graduate Students in Chongqing
- the Clinical Research Plan of SHDC
- the Shanghai Municipal Health and Family Planning Commission Smart Medical Special Research Project
- the Science and Technology Commission of Shanghai Municipality
Zitieren
APA
Qin, H., Hong, G., Ma, D., Wang, Z., Zhao, L., Li, W., & Xu, X. (2026). Universum Inspired Graph Contrast Learning for Major Depressive Disorder Identification: In Functional Brain Network View. CNS Neuroscience & Therapeutics, 32(9). https://doi.org/10.1002/cns.71158
Vancouver
Qin H, Hong G, Ma D, Wang Z, Zhao L, Li W, et al. Universum Inspired Graph Contrast Learning for Major Depressive Disorder Identification: In Functional Brain Network View. CNS Neuroscience & Therapeutics. 2026;32(9). doi:10.1002/cns.71158
BibTeX
@article{Qin2026,
author = {Qin, Hao and Hong, Guanghui and Ma, Di and Wang, Zeyi and Zhao, Leina and Li, Weikai and Xu, Xiaowen},
title = {Universum Inspired Graph Contrast Learning for Major Depressive Disorder Identification: In Functional Brain Network View},
journal = {CNS Neuroscience & Therapeutics},
year = {2026},
volume = {32},
number = {9},
doi = {10.1002/cns.71158}
}
EUVIMED