Deep-learning based Embedding of Functional Connectivity Profiles for Precision Functional Mapping DOI Creative Commons
Jiaxin Cindy Tu,

Jung‐Hoon Kim,

Patrick H. Luckett

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 30, 2025

Abstract Spatial correlation of functional connectivity profiles across matching anatomical locations in individuals is often calculated to delineate individual differences networks. Likewise, spatial assessed average groups evaluate the maturity networks during development. Despite its widespread use, limited comparing two samples at a time. In this study, we employed variational autoencoder embed from various locations, individuals, and group averages for simultaneous comparison. We demonstrate that our autoencoder, with pre-trained weights, can project new vertex space latent as few dimensions, yet still retain meaningful global local structures data. Functional occupy distinct compartments space. Moreover, variability same location readily captured believe approach could be useful visualization exploratory analyses precision mapping.

Language: Английский

The connecting brain in context: How adolescent plasticity supports experiential learning and development DOI Creative Commons
Amanda E. Baker, Adriana Galván, Andrew J. Fuligni

et al.

Developmental Cognitive Neuroscience, Journal Year: 2024, Volume and Issue: 71, P. 101486 - 101486

Published: Nov. 28, 2024

Language: Английский

Citations

3

Deep-learning based Embedding of Functional Connectivity Profiles for Precision Functional Mapping DOI Creative Commons
Jiaxin Cindy Tu,

Jung‐Hoon Kim,

Patrick H. Luckett

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 30, 2025

Abstract Spatial correlation of functional connectivity profiles across matching anatomical locations in individuals is often calculated to delineate individual differences networks. Likewise, spatial assessed average groups evaluate the maturity networks during development. Despite its widespread use, limited comparing two samples at a time. In this study, we employed variational autoencoder embed from various locations, individuals, and group averages for simultaneous comparison. We demonstrate that our autoencoder, with pre-trained weights, can project new vertex space latent as few dimensions, yet still retain meaningful global local structures data. Functional occupy distinct compartments space. Moreover, variability same location readily captured believe approach could be useful visualization exploratory analyses precision mapping.

Language: Английский

Citations

0