EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Toward a more informative representation of the fetal–neonatal brain connectome using variational autoencoder

Jung-Hoon Kim iD, Josepheen De Asis-Cruz, Dhineshvikram Krishnamurthy, Catherine Limperopoulos iD

eLife · 2023

DOI: 10.7554/elife.80878 ↗

Kurz gefasst

Fachartikel in der Zeitschrift eLife, 2023. Verfasst von Jung-Hoon Kim und 3 weiteren Autor:innen. Beteiligte Einrichtung: Developing Brain Institute, Children's National Hospital, Washington, United States. Hauptthemen laut MEDLINE: Connectome. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NICHD NIH HHS, NHLBI NIH HHS, National Heart, Lung, and Blood Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in functional magnetic resonance imaging (fMRI) have helped elucidate previously inaccessible trajectories of early-life prenatal and neonatal brain development. To date, the interpretation of fetal–neonatal fMRI data has relied on linear analytic models, akin to adult neuroimaging data. However, unlike the adult brain, the fetal and newborn brain develops extraordinarily rapidly, far outpacing any other brain development period across the life span. Consequently, conventional linear computational models may not adequately capture these accelerated and complex neurodevelopmental trajectories during this critical period of brain development along the prenatal-neonatal continuum. To obtain a nuanced understanding of fetal–neonatal brain development, including nonlinear growth, for the first time, we developed quantitative, systems-wide representations of brain activity in a large sample (>500) of fetuses, preterm, and full-term neonates using an unsupervised deep generative model called variational autoencoder (VAE), a model previously shown to be superior to linear models in representing complex resting-state data in healthy adults. Here, we demonstrated that nonlinear brain features, that is, latent variables, derived with the VAE pretrained on rsfMRI of human adults, carried important individual neural signatures, leading to improved representation of prenatal-neonatal brain maturational patterns and more accurate and stable age prediction in the neonate cohort compared to linear models. Using the VAE decoder, we also revealed distinct functional brain networks spanning the sensory and default mode networks. Using the VAE, we are able to reliably capture and quantify complex, nonlinear fetal–neonatal functional neural connectivity. This will lay the critical foundation for detailed mapping of healthy and aberrant functional brain signatures that have their origins in fetal life.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ConnectomeAdultPregnancyFemaleInfant, NewbornHumansBrainMagnetic Resonance ImagingNeuroimagingFetus

Stichwörter der Autor:innen

VAEdeep learningfMRIfetal–neonatalfunctional brain networkhumanneurodevelopmentneuroscience

Autor:innen und Institutionen

  • Developing Brain Institute, Children's National Hospital, Washington, United States.

ORCID-Profile: Jung-Hoon Kim, Catherine Limperopoulos

Förderung

  • NICHD NIH HHS
  • NHLBI NIH HHS
  • National Heart, Lung, and Blood Institute
  • Canadian Institutes of Health Research

Zitieren

APA

Kim, J. H., De Asis-Cruz, J., Krishnamurthy, D., & Limperopoulos, C. (2023). Toward a more informative representation of the fetal–neonatal brain connectome using variational autoencoder. eLife. https://doi.org/10.7554/elife.80878

Vancouver

Kim JH, De Asis-Cruz J, Krishnamurthy D, Limperopoulos C. Toward a more informative representation of the fetal–neonatal brain connectome using variational autoencoder. eLife. 2023. doi:10.7554/elife.80878

BibTeX
@article{Kim2023,
  author = {Kim, Jung-Hoon and De Asis-Cruz, Josepheen and Krishnamurthy, Dhineshvikram and Limperopoulos, Catherine},
  title = {Toward a more informative representation of the fetal–neonatal brain connectome using variational autoencoder},
  journal = {eLife},
  year = {2023},
  doi = {10.7554/elife.80878}
}
Kostenlos starten →