EUVIMEDEUVIMED entdecken
Crossref

Spatio-temporal learning and explaining for dynamic functional connectivity analysis: Application to depression

Jinlong Hu, Jianmiao Luo, Ziyun Xu, Bin Liao, Shoubin Dong, Bo Peng, Gangqiang Hou

Journal of Affective Disorders · 2024-11 · 364 · 266-273

DOI: 10.1016/j.jad.2024.08.014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2024-11. Verfasst von Jinlong Hu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Guangzhou,…. Hauptthemen laut MEDLINE: Major Depressive Disorder, Magnetic Resonance Imaging. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Shenzhen Municipal Health Commission, Zhongshan Science and Technology Bureau, Ministry of Science and Technology of the People's Republic of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Functional connectivity has been shown to fluctuate over time. The present study aimed to identifying major depressive disorders (MDD) with dynamic functional connectivity (dFC) from resting-state fMRI data, which would be helpful to produce tools of early depression diagnosis and enhance our understanding of depressive etiology. METHODS: The resting-state fMRI data of 178 subjects were collected, including 89 MDD and 89 healthy controls. We propose a spatio-temporal learning and explaining framework for dFC analysis. A yet effective spatio-temporal model is developed to classifying MDD from healthy controls with dFCs. The model is a stacking neural network model, which learns network structure information by a multi-layer perceptron based spatial encoder, and learns time-varying patterns by a Transformer based temporal encoder. We propose to explain the spatio-temporal model with a two-stage explanation method of importance feature extracting and disorder-relevant pattern exploring. The layer-wise relevance propagation (LRP) method is introduced to extract the most relevant input features in the model, and the attention mechanism with LRP is applied to extract the important time steps of dFCs. The disorder-relevant functional connections, brain regions, and brain states in the model are further explored and identified. RESULTS: We achieved the best classification performance in identifying MDD from healthy controls with dFC data. The top important functional connectivity, brain regions, and dynamic states closely related to MDD have been identified. LIMITATIONS: The data preprocessing may affect the classification performance of the model, and this study needs further validation in a larger patient population. CONCLUSIONS: The experimental results demonstrate that the proposed spatio-temporal model could effectively classify MDD, and uncover structural and temporal patterns of dFCs in depression.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Major Depressive DisorderMagnetic Resonance ImagingHumansAdultFemaleMaleBrainNeural Networks, ComputerConnectomeSpatio-Temporal AnalysisYoung AdultBrain MappingCase-Control Studies

Stichwörter der Autor:innen

Deep learningDynamic functional connectivityMajor depressive disorderModel explanationSpatio-temporal learning model

Autor:innen und Institutionen

  • Guangdong Key Lab of Communication and Computer Network, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China.
  • Neuropsychiatry Imaging Center, Department of Radiology, Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China.
  • College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China. Electronic address: liaobin_lb@163.com.
  • Department of Depressive Disorder, Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China.
  • Neuropsychiatry Imaging Center, Department of Radiology, Shenzhen Kangning Hospital, Shenzhen Mental Health Center, Shenzhen, China. Electronic address: nihaohgq@163.com.

Förderung

  • Shenzhen Municipal Health Commission
  • Zhongshan Science and Technology Bureau
  • Ministry of Science and Technology of the People's Republic of China
  • Natural Science Foundation of Guangdong Province
  • National Key Research and Development Program of China

Zitieren

APA

Hu, J., Luo, J., Xu, Z., Liao, B., Dong, S., Peng, B., & Hou, G. (2024). Spatio-temporal learning and explaining for dynamic functional connectivity analysis: Application to depression. Journal of Affective Disorders, 364, 266-273. https://doi.org/10.1016/j.jad.2024.08.014

Vancouver

Hu J, Luo J, Xu Z, Liao B, Dong S, Peng B, et al. Spatio-temporal learning and explaining for dynamic functional connectivity analysis: Application to depression. Journal of Affective Disorders. 2024;364:266-273. doi:10.1016/j.jad.2024.08.014

BibTeX
@article{Hu2024,
  author = {Hu, Jinlong and Luo, Jianmiao and Xu, Ziyun and Liao, Bin and Dong, Shoubin and Peng, Bo and Hou, Gangqiang},
  title = {Spatio-temporal learning and explaining for dynamic functional connectivity analysis: Application to depression},
  journal = {Journal of Affective Disorders},
  year = {2024},
  volume = {364},
  pages = {266--273},
  doi = {10.1016/j.jad.2024.08.014}
}
Kostenlos starten →