EUVIMEDEUVIMED entdecken
Crossref

Attention-Enhanced static-dynamic fusion network for major depressive disorder diagnosis

Qian Fu iD, Ling He iD, Mingyao Gao iD, Yajing Meng iD, Changjian Qiu iD, Qing Li, Jing Zhang iD

Physiological Measurement · 31.08.2026 · 47 (8) · 085014

DOI: 10.1088/1361-6579/ae8a0f ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physiological Measurement, online erschienen am 07.08.2026. Verfasst von Qian Fu und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Biomedical Engineering, Sichuan University, Chengdu, People's Republic of China. Hauptthemen laut MEDLINE: Major Depressive Disorder, Attention, Signal Processing, Computer-Assisted. Die Arbeit nennt 39 Literaturangaben. Gefördert von: STI2030-Major Projects Prospective Clinical Cohort Study of Depression.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . Accurate depression classification using fNIRS signals is critical for objective auxiliary diagnosis, yet many existing methods separately model static characteristics or temporal dynamics, limiting their ability to capture coordinated brain activity. Approach . This study proposes a static–dynamic fusion network for fNIRS-based depression classification that jointly models stable hemodynamic and network properties together with time-varying functional connectivity. A static feature encoder captures global and channel-wise traits, while a dynamic feature encoder employs sequential modeling with attention mechanisms to identify temporally salient neural variations. A channel-aware fusion module is further introduced to adaptively integrate static and dynamic features based on their diagnostic relevance. Main results . Validated on 352 subjects undergoing verbal fluency tasks, static and dynamic feature-fusion network achieved 91.2% accuracy on 90 s signal segments and 81.5% on 160 s segments. Significance . The proposed framework demonstrates improved classification performance over existing methods by explicitly modeling complementary static and dynamic neural features within an interpretable architecture for depression analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Major Depressive DisorderAttentionSignal Processing, Computer-AssistedHumansSpectroscopy, Near-Infrared

Stichwörter der Autor:innen

attention mechanismdeep learningdepression classificationfeature fusionfunctional near-infrared spectroscopy (fNIRS)

Autor:innen und Institutionen

  • College of Biomedical Engineering, Sichuan University, Chengdu, People's Republic of China.
  • Mental Health Center, West China Hospital, Sichuan University and Sichuan Clinical Medical Research Center for Mental Disorders, Chengdu, People's Republic of China.

ORCID-Profile: Qian Fu, Ling He, Mingyao Gao, Yajing Meng, Changjian Qiu, Jing Zhang

Förderung

  • STI2030-Major Projects Prospective Clinical Cohort Study of Depression

Zitieren

APA

Fu, Q., He, L., Gao, M., Meng, Y., Qiu, C., Li, Q., & Zhang, J. (2026). Attention-Enhanced static-dynamic fusion network for major depressive disorder diagnosis. Physiological Measurement, 47(8), 085014. https://doi.org/10.1088/1361-6579/ae8a0f

Vancouver

Fu Q, He L, Gao M, Meng Y, Qiu C, Li Q, et al. Attention-Enhanced static-dynamic fusion network for major depressive disorder diagnosis. Physiological Measurement. 2026;47(8):085014. doi:10.1088/1361-6579/ae8a0f

BibTeX
@article{Fu2026,
  author = {Fu, Qian and He, Ling and Gao, Mingyao and Meng, Yajing and Qiu, Changjian and Li, Qing and Zhang, Jing},
  title = {Attention-Enhanced static-dynamic fusion network for major depressive disorder diagnosis},
  journal = {Physiological Measurement},
  year = {2026},
  volume = {47},
  number = {8},
  pages = {085014},
  doi = {10.1088/1361-6579/ae8a0f}
}
Kostenlos starten →