Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects
Advanced Science · 2026
DOI: 10.1002/advs.202502817 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, 2026. Verfasst von Jianpo Su und 14 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China. Hauptthemen laut MEDLINE: Major Depressive Disorder, Magnetic Resonance Imaging, Connectome, Brain. Die Arbeit nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Sci-Tech Innovation 2030-Major Projects, Department of Science and Technology of Hunan Province, China.
Abstract (Originalsprache)
Imaging‐based automatic diagnosis of major depressive disorder (MDD) has received widespread attention in precision medicine. Increasing evidence suggests that the pathophysiology of MDD is associated with the abnormality in brain connectome, which could be an effective biomarker for classification. However, previous studies suffered from small number of samples and large multi‐site imaging divergences, as well as irregular graph architectures of the connectome, which challenges the diagnostic classification of MDD. Here, we propose a novel graph convolution network with sparse pooling (GCNSP) to learn the hierarchical features of the connectome graph to improve MDD classification. We applied the model to a multi‐site functional MRI sample (33 sites with 3335 subjects, the largest functional imaging dataset of MDD to date), and perform transfer learning classification for each site using the pre‐trained GCNSP on remaining sites to fit cross‐site divergences, achieving an average accuracy of 70.14%. Moreover, hierarchical dysfunction of default mode network (DMN) is detected by the GCNSP in the patients. The interaction between DMN and frontoparietal network exhibit high discriminative power between patients and controls. Accordingly, this study may provide an effective pipeline for multi‐site diagnostic classification and improve our understanding of hierarchical clues of brain network dysfunction in neuropsychiatric disorders.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China.
- School of Biomedical Engineering, Air Force Medical University, Xi'an, China.
- and National Clinical Research Center for Mental Disorders, The Second Xiangya Hospital of Central South University, Changsha, China.
- School of Medicine, Zhejiang University, Hangzhou, China.
- College of Electronic Engineering, National University of Defense Technology, Changsha, China.
- Department of Clinical Psychology, The Third Xiangya Hospital of Central South University, Changsha, China.
Förderung
- National Natural Science Foundation of China
- Sci-Tech Innovation 2030-Major Projects
- Department of Science and Technology of Hunan Province, China
Zitieren
APA
Su, J., Qin, J., Shen, H., Zeng, L. L., Li, B., Liu, J., Song, X., Liu, L., Pu, W., Bai, T., Wang, H., Yin, H., Wang, K., Li, L., & Hu, D. (2026). Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects. Advanced Science. https://doi.org/10.1002/advs.202502817
Vancouver
Su J, Qin J, Shen H, Zeng LL, Li B, Liu J, et al. Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects. Advanced Science. 2026. doi:10.1002/advs.202502817
BibTeX
@article{Su2026,
author = {Su, Jianpo and Qin, Jian and Shen, Hui and Zeng, Ling-Li and Li, Baojuan and Liu, Jin and Song, Xuemei and Liu, Li and Pu, Weidan and Bai, Tongjian and Wang, Huaning and Yin, Hong and Wang, Kai and Li, Lingjiang and Hu, Dewen},
title = {Multi‐Site Transfer Classification of Major Depressive Disorder: An fMRI Study in 3335 Subjects},
journal = {Advanced Science},
year = {2026},
doi = {10.1002/advs.202502817}
}
EUVIMED