EUVIMEDEUVIMED entdecken
Open Access

Individual cognitive traits can be predicted from task-based dynamic functional connectivity with a deep convolutional-recurrent model

Erick Almeida de Souza iD, Bruno Hebling Vieira, Carlos Ernesto Garrido Salmon iD

Cerebral Cortex · 2024

DOI: 10.1093/cercor/bhae412 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cerebral Cortex, 2024. Verfasst von Erick Almeida de Souza und 2 weiteren Autor:innen. Beteiligte Einrichtung: InBrain Lab, Departamento de Física, FFCLRP, Universidade de São Paulo, Prof. Aymar Batista Prado Street, Vila Monte Alegre, Ribeirão Preto - SP, 140…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Connectome, Cognition, Brain. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Dean's Office for Research of the University of São Paulo, São Paulo Research Foundation, Human Connectome Project, WU-Minn Consortium.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

There has been increased interest in understanding the neural substrates of intelligence and several human traits from neuroimaging data. Deep learning can be used to predict different cognitive measures, such as general and fluid intelligence, from different functional magnetic resonance imaging experiments providing information about the main brain areas involved in these predictions. Using neuroimaging and behavioral data from 874 subjects provided by the Human Connectome Project, we predicted various cognitive scores using dynamic functional connectivity derived from language and working memory functional magnetic resonance imaging task states, using a 360-region multimodal atlas. The deep model joins multiscale convolutional and long short-term memory layers and was trained under a 10-fold stratified cross-validation. We removed the confounding effects of gender, age, total brain volume, motion and the multiband reconstruction algorithm using multiple linear regression. We can explain 17.1% and 16% of general intelligence variance for working memory and language tasks, respectively. We showed that task-based dynamic functional connectivity has more predictive power than resting-state dynamic functional connectivity when compared to the literature and that removing confounders significantly reduces the prediction performance. No specific cortical network showed significant relevance in the prediction of general and fluid intelligence, suggesting a spatial homogeneous distribution of the intelligence construct in the brain.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingConnectomeCognitionBrainIntelligenceDeep LearningHumansMaleFemaleAdultYoung AdultLanguageNeural Networks, Computer

Stichwörter der Autor:innen

deep learningdynamic functional connectivityintelligencetask-fmri

Autor:innen und Institutionen

  • InBrain Lab, Departamento de Física, FFCLRP, Universidade de São Paulo, Prof. Aymar Batista Prado Street, Vila Monte Alegre, Ribeirão Preto - SP, 14040-900, Brazil.
  • Methods of Plasticity Research, Department of Psychology, University of Zurich, Binzmühlestrasse 14, 8050 Zurich, Switzerland.
  • Neuroscience Center Zurich (ZNZ), University of Zurich & ETH Zurich, Winterthurerstrasse 190, 8057 Zurich, Switzerland.
  • Departamento de Imagens Médicas, Hematologia e Oncologia Clínica, FMRP, Universidade de São Paulo, Bandeirantes avenue 3900, Hospital das Clínicas - 7th Floor, Vila Monte Alegre, Ribeirão Preto, Brazil.

ORCID-Profile: Erick Almeida de Souza, Carlos Ernesto Garrido Salmon

Förderung

  • Dean's Office for Research of the University of São Paulo
  • São Paulo Research Foundation
  • Human Connectome Project, WU-Minn Consortium
  • Swiss National Science Foundation
  • NIMH NIH HHS
  • Dean’s Office for Research of the University of São Paulo
  • NIH

Zitieren

APA

Almeida de Souza, E., Vieira, B. H., & Salmon, C. E. G. (2024). Individual cognitive traits can be predicted from task-based dynamic functional connectivity with a deep convolutional-recurrent model. Cerebral Cortex. https://doi.org/10.1093/cercor/bhae412

Vancouver

Almeida de Souza E, Vieira BH, Salmon CEG. Individual cognitive traits can be predicted from task-based dynamic functional connectivity with a deep convolutional-recurrent model. Cerebral Cortex. 2024. doi:10.1093/cercor/bhae412

BibTeX
@article{AlmeidadeSouza2024,
  author = {Almeida de Souza, Erick and Vieira, Bruno Hebling and Salmon, Carlos Ernesto Garrido},
  title = {Individual cognitive traits can be predicted from task-based dynamic functional connectivity with a deep convolutional-recurrent model},
  journal = {Cerebral Cortex},
  year = {2024},
  doi = {10.1093/cercor/bhae412}
}
Kostenlos starten →