DFC-Igloo: A Dynamic Functional Connectome Learning Framework for Identifying Neurodevelopmental Biomarkers in Very Preterm Infants

Overview

Journal Comput Methods Programs Biomed

Specialty Medical Informatics

Date 2024 Nov 3

PMID 39489076

Authors

Junqi Wang

Hailong Li

Kim M Cecil

Mekibib Altaye

Nehal A Parikh

Lili He

Affiliations

Soon will be listed here.

Abstract

Background And Objective: Very preterm infants are susceptible to neurodevelopmental impairments, necessitating early detection of prognostic biomarkers for timely intervention. The study aims to explore possible functional biomarkers for very preterm infants at born that relate to their future cognitive and motor development using resting-state fMRI. Prior studies are limited by the sample size and suffer from efficient functional connectome (FC) construction algorithms that can handle the noisy data contained in neonatal time series, leading to equivocal findings. Therefore, we first propose an enhanced functional connectome construction algorithm as a prerequisite step. We then apply the new FC construction algorithm to our large prospective very preterm cohort to explore multi-level neurodevelopmental biomarkers.

Methods: There exists an intrinsic relationship between the structural connectome (SC) and FC, with a notable coupling between the two. This observation implies a putative property of graph signal smoothness on the SC as well. Yet, this property has not been fully exploited for constructing intrinsic dFC. In this study, we proposed an advanced dynamic FC (dFC) learning model, dFC-Igloo, which leveraged SC information to iteratively refine dFC estimations by applying graph signal smoothness to both FC and SC. The model was evaluated on artificial small-world graphs and simulated graph signals.

Results: The proposed model achieved the best and most robust recovery of the ground truth graph across different noise levels and simulated SC pairs from the simulation. The model was further applied to a cohort of very preterm infants from five Neonatal Intensive Care Units, where an enhanced dFC was obtained for each infant. Based on the improved dFC, we identified neurodevelopmental biomarkers for neonates across connectome-wide, regional, and subnetwork scales.

Conclusion: The identified markers correlate with cognitive and motor developmental outcomes, offering insights into early brain development and potential neurodevelopmental challenges.

References

Wheelock M, Austin N, Bora S, Eggebrecht A, Melzer T, Woodward L . Altered functional network connectivity relates to motor development in children born very preterm. Neuroimage. 2018; 183:574-583. PMC: 6258200. DOI: 10.1016/j.neuroimage.2018.08.051. View

Jaekel J, Baumann N, Wolke D . Effects of gestational age at birth on cognitive performance: a function of cognitive workload demands. PLoS One. 2013; 8(5):e65219. PMC: 3663809. DOI: 10.1371/journal.pone.0065219. View

Rogers C, Smyser T, Smyser C, Shimony J, Inder T, Neil J . Regional white matter development in very preterm infants: perinatal predictors and early developmental outcomes. Pediatr Res. 2015; 79(1-1):87-95. PMC: 4724306. DOI: 10.1038/pr.2015.172. View

Rubinov M, Sporns O . Complex network measures of brain connectivity: uses and interpretations. Neuroimage. 2009; 52(3):1059-69. DOI: 10.1016/j.neuroimage.2009.10.003. View

Lin Y, Yang D, Hou J, Yan C, Kim M, Laurienti P . Learning dynamic graph embeddings for accurate detection of cognitive state changes in functional brain networks. Neuroimage. 2021; 230:117791. PMC: 8091140. DOI: 10.1016/j.neuroimage.2021.117791. View

Li H, Parikh N, He L . A Novel Transfer Learning Approach to Enhance Deep Neural Network Classification of Brain Functional Connectomes. Front Neurosci. 2018; 12:491. PMC: 6066582. DOI: 10.3389/fnins.2018.00491. View

Glasser M, Coalson T, Robinson E, Hacker C, Harwell J, Yacoub E . A multi-modal parcellation of human cerebral cortex. Nature. 2016; 536(7615):171-178. PMC: 4990127. DOI: 10.1038/nature18933. View

Xiao L, Wang J, Kassani P, Zhang Y, Bai Y, Stephen J . Multi-Hypergraph Learning-Based Brain Functional Connectivity Analysis in fMRI Data. IEEE Trans Med Imaging. 2019; 39(5):1746-1758. PMC: 7376954. DOI: 10.1109/TMI.2019.2957097. View

Hoff G, van den Heuvel M, Benders M, Kersbergen K, de Vries L . On development of functional brain connectivity in the young brain. Front Hum Neurosci. 2013; 7:650. PMC: 3792361. DOI: 10.3389/fnhum.2013.00650. View

10.

He L, Li H, Wang J, Chen M, Gozdas E, Dillman J . A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants. Sci Rep. 2020; 10(1):15072. PMC: 7492237. DOI: 10.1038/s41598-020-71914-x. View

11.

Wang J, Xiao L, Wilson T, Stephen J, Calhoun V, Wang Y . Examining brain maturation during adolescence using graph Laplacian learning based Fourier transform. J Neurosci Methods. 2020; 338:108649. PMC: 7936225. DOI: 10.1016/j.jneumeth.2020.108649. View

12.

Fogassi L, Luppino G . Motor functions of the parietal lobe. Curr Opin Neurobiol. 2005; 15(6):626-31. DOI: 10.1016/j.conb.2005.10.015. View

13.

Shi F, Yap P, Wu G, Jia H, Gilmore J, Lin W . Infant brain atlases from neonates to 1- and 2-year-olds. PLoS One. 2011; 6(4):e18746. PMC: 3077403. DOI: 10.1371/journal.pone.0018746. View

14.

Ren H, Jiang X, Meng L, Lu C, Wang L, Dai C . fNIRS-Based Dynamic Functional Connectivity Reveals the Innate Musical Sensing Brain Networks in Preterm Infants. IEEE Trans Neural Syst Rehabil Eng. 2022; 30:1806-1816. DOI: 10.1109/TNSRE.2022.3178078. View

15.

Wang Z, Dai Z, Gong G, Zhou C, He Y . Understanding structural-functional relationships in the human brain: a large-scale network perspective. Neuroscientist. 2014; 21(3):290-305. DOI: 10.1177/1073858414537560. View

16.

Briggs R, Tanglay O, Dadario N, Young I, Fonseka R, Hormovas J . The Unique Fiber Anatomy of Middle Temporal Gyrus Default Mode Connectivity. Oper Neurosurg (Hagerstown). 2021; 21(1):E8-E14. PMC: 8203421. DOI: 10.1093/ons/opab109. View

17.

Watts D, Strogatz S . Collective dynamics of 'small-world' networks. Nature. 1998; 393(6684):440-2. DOI: 10.1038/30918. View

18.

Ment L, Hirtz D, Huppi P . Imaging biomarkers of outcome in the developing preterm brain. Lancet Neurol. 2009; 8(11):1042-55. DOI: 10.1016/S1474-4422(09)70257-1. View

19.

Hsu H, Yao Z, Hwang K, Hsieh S . Between-module functional connectivity of the salient ventral attention network and dorsal attention network is associated with motor inhibition. PLoS One. 2020; 15(12):e0242985. PMC: 7714245. DOI: 10.1371/journal.pone.0242985. View

20.

Catani M, Jones D, Donato R, Ffytche D . Occipito-temporal connections in the human brain. Brain. 2003; 126(Pt 9):2093-107. DOI: 10.1093/brain/awg203. View