Brain age predicted using graph convolutional neural network explains neurodevelopmental trajectory in preterm neonates.
Brain age prediction
Brain morphology
Graph convolutional network
Preterm neonates
Structural equation modelling
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
14 Nov 2023
14 Nov 2023
Historique:
received:
31
03
2023
accepted:
16
09
2023
revised:
06
09
2023
pubmed:
14
11
2023
medline:
14
11
2023
entrez:
13
11
2023
Statut:
aheadofprint
Résumé
Dramatic brain morphological changes occur throughout the third trimester of gestation. In this study, we investigated whether the predicted brain age (PBA) derived from graph convolutional network (GCN) that accounts for cortical morphometrics in third trimester is associated with postnatal abnormalities and neurodevelopmental outcome. In total, 577 T1 MRI scans of preterm neonates from two different datasets were analyzed; the NEOCIVET pipeline generated cortical surfaces and morphological features, which were then fed to the GCN to predict brain age. The brain age index (BAI; PBA minus chronological age) was used to determine the relationships among preterm birth (i.e., birthweight and birth age), perinatal brain injuries, postnatal events/clinical conditions, BAI at postnatal scan, and neurodevelopmental scores at 30 months. Brain morphology and GCN-based age prediction of preterm neonates without brain lesions (mean absolute error [MAE]: 0.96 weeks) outperformed conventional machine learning methods using no topological information. Structural equation models (SEM) showed that BAI mediated the influence of preterm birth and postnatal clinical factors, but not perinatal brain injuries, on neurodevelopmental outcome at 30 months of age. Brain morphology may be clinically meaningful in measuring brain age, as it relates to postnatal factors, and predicting neurodevelopmental outcome. Understanding the neurodevelopmental trajectory of preterm neonates through the prediction of brain age using a graph convolutional neural network may allow for earlier detection of potential developmental abnormalities and improved interventions, consequently enhancing the prognosis and quality of life in this vulnerable population. •Brain age in preterm neonates predicted using a graph convolutional network with brain morphological changes mediates the pre-scan risk factors and post-scan neurodevelopmental outcomes. •Predicted brain age oriented from conventional deep learning approaches, which indicates the neurodevelopmental status in neonates, shows a lack of sensitivity to perinatal risk factors and predicting neurodevelopmental outcomes. •The new brain age index based on brain morphology and graph convolutional network enhances the accuracy and clinical interpretation of predicted brain age for neonates.
Identifiants
pubmed: 37957363
doi: 10.1007/s00330-023-10414-8
pii: 10.1007/s00330-023-10414-8
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Commentaires et corrections
Type : CommentIn
Informations de copyright
© 2023. The Author(s).
Références
Jónsson BA, Bjornsdottir G, Thorgeirsson T et al (2019) Brain age prediction using deep learning uncovers associated sequence variants. Nat Commun 10:5409. https://doi.org/10.1038/s41467-019-13163-9
doi: 10.1038/s41467-019-13163-9
pubmed: 31776335
pmcid: 6881321
Ment LR, Vohr BR (2008) Preterm birth and the developing brain. Lancet Neurol 7:378–379. https://doi.org/10.1016/S1474-4422(08)70073-5
doi: 10.1016/S1474-4422(08)70073-5
pubmed: 18420149
pmcid: 2762422
Ajayi-Obe M, Saeed N, Cowan F, Rutherford M, Edwards A (2000) Reduced development of cerebral cortex in extremely preterm infants. Lancet 356:1162–1163. https://doi.org/10.1016/s0140-6736(00)02761-6
doi: 10.1016/s0140-6736(00)02761-6
pubmed: 11030298
Ball G, Srinivasan L, Aljabar P et al (2013) Development of cortical microstructure in the preterm human brain. Proc Natl Acad Sci U S A 110:9541–9546. https://doi.org/10.1073/pnas.1301652110
doi: 10.1073/pnas.1301652110
pubmed: 23696665
pmcid: 3677430
Pandit A, Robinson E, Aljabar P et al (2014) Whole-brain mapping of structural connectivity in infants reveals altered connection strength associated with growth and preterm birth. Cereb Cortex 24:2324–2333. https://doi.org/10.1093/cercor/bht086
doi: 10.1093/cercor/bht086
pubmed: 23547135
Smyser CD, Snyder AZ, Shimony JS, Mitra A, Inder TE, Neil JJ (2016) Resting-state network complexity and magnitude are reduced in prematurely born infants. Cereb Cortex 26:322–333. https://doi.org/10.1093/cercor/bhu251
doi: 10.1093/cercor/bhu251
pubmed: 25331596
Ylijoki MK, Ekholm E, Ekblad M, Lehtonen L (2019) Prenatal risk factors for adverse developmental outcome in preterm infants-systematic review. Front Psychol 10:595. https://doi.org/10.3389/fpsyg.2019.00595
doi: 10.3389/fpsyg.2019.00595
pubmed: 30971974
pmcid: 6445261
Franke K, Luders E, May A, Wilke M, Gaser C (2012) Brain maturation: predicting individual BrainAGE in children and adolescents using structural MRI. Neuroimage 63:1305–1312. https://doi.org/10.1016/j.neuroimage.2012.08.001
doi: 10.1016/j.neuroimage.2012.08.001
pubmed: 22902922
Cole JH, Franke K (2017) Predicting age using neuroimaging: innovative brain ageing biomarkers. Trends Neurosci 40:681–690. https://doi.org/10.1016/j.tins.2017.10.001
doi: 10.1016/j.tins.2017.10.001
pubmed: 29074032
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
doi: 10.1038/nature14539
pubmed: 26017442
Peng H, Gong W, Beckmann CF, Vedaldi A, Smith SM (2019) Accurate brain age prediction with lightweight deep neural networks. Med Image Anal 68:101871. https://doi.org/10.1016/j.media.2020.101871
doi: 10.1016/j.media.2020.101871
Ning K, Zhao L, Matloff W, Sun F, Toga AW (2020) Association of relative brain age with tobacco smoking, alcohol consumption, and genetic variants. Sci Rep 10:10. https://doi.org/10.1038/s41598-019-56089-4
doi: 10.1038/s41598-019-56089-4
pubmed: 32001736
pmcid: 6992742
Huang T-W, Chen H-T, Huang T-W et al (2017) Age estimation from brain MRI images using deep learning. In: 2017 IEEE 14th International symposium on biomedical imaging (ISBI 2017). IEEE, Melbourne, VIC, Australia, pp 849–852. https://doi.org/10.1109/ISBI.2017.7950650
Cole JH, Poudel RP, Tsagkrasoulis D et al (2017) Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. Neuroimage 163:115–124. https://doi.org/10.1016/j.neuroimage.2017.07.059
doi: 10.1016/j.neuroimage.2017.07.059
pubmed: 28765056
Kawahara J, Brown CJ, Miller SP et al (2017) BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment. Neuroimage 146:1038–1049. https://doi.org/10.1016/j.neuroimage.2016.09.046
doi: 10.1016/j.neuroimage.2016.09.046
pubmed: 27693612
Brown CJ, Moriarty KP, Miller SP et al (2017) Prediction of brain network age and factors of delayed maturation in very preterm infants. In: Medical image computing and computer assisted intervention − MICCAI 2017. Lecture notes in computer science, vol 10433. Springer, Cham. https://doi.org/10.1007/978-3-319-66182-7_10
Chen JV, Chaudhari G, Hess CP et al (2022) Deep learning to predict neonatal and infant brain age from myelination on brain MRI scans. Radiology 305:678–687. https://doi.org/10.1148/radiol.211860
doi: 10.1148/radiol.211860
pubmed: 35852429
He T, Kong R, Holmes A et al (2018) Is deep learning better than kernel regression for functional connectivity prediction of fluid intelligence? In: 2018 international workshop on pattern recognition in neuroimaging (PRNI). IEEE, Singapore, pp 1–4. https://doi.org/10.1109/PRNI.2018.8423958
Kim SY, Liu M, Hong S-J et al (2020) Disruption and compensation of sulcation-based covariance networks in neonatal brain growth after perinatal injury. Cereb Cortex 30:6238–6253. https://doi.org/10.1093/cercor/bhaa181
doi: 10.1093/cercor/bhaa181
pubmed: 32656563
pmcid: 7609941
Liu M, Duffy BA, Sun Z et al (2020) Deep learning of cortical surface features using graph-convolution predicts neonatal brain age and neurodevelopmental outcome. 2020 IEEE 17th international symposium on biomedical imaging (ISBI). IEEE, pp 1335–1338. https://doi.org/10.1109/ISBI45749.2020.9098556
Kang SH, Liu M, Park G et al (2023) Different effects of cardiometabolic syndrome on brain age in relation to gender and ethnicity. Alzheimer’s research & therapy 15:1–10. https://doi.org/10.1186/s13195-023-01215-8
doi: 10.1186/s13195-023-01215-8
Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems 29. In: 30th Conference on neural information processing systems (NIPS 2016). NIPS, Barcelona, Spain. https://doi.org/10.5555/3157382.3157527
Lewis JD, Evans AC, Tohka J, Group BDC (2018) T1 white/gray contrast as a predictor of chronological age, and an index of cognitive performance. Neuroimage 173:341–350. https://doi.org/10.1016/j.neuroimage.2018.02.050
doi: 10.1016/j.neuroimage.2018.02.050
pubmed: 29501876
Kliegman RM, Hack M, Jones P, Fanaroff AA (1982) Epidemiologic study of necrotizing enterocolitis among low-birth-weight infants. Absence of identifiable risk factors. J Pediatr 100:440–444
doi: 10.1016/S0022-3476(82)80456-3
pubmed: 7062181
Hughes EJ, Winchman T, Padormo F et al (2017) A dedicated neonatal brain imaging system. Magn Reson Med 78:794–804. https://doi.org/10.1002/mrm.26462
doi: 10.1002/mrm.26462
pubmed: 27643791
Makropoulos A, Robinson EC, Schuh A et al (2018) The developing human connectome project: a minimal processing pipeline for neonatal cortical surface reconstruction. Neuroimage 173:88–112. https://doi.org/10.1016/j.neuroimage.2018.01.054
doi: 10.1016/j.neuroimage.2018.01.054
pubmed: 29409960
Kim H, Lepage C, Maheshwary R et al (2016) NEOCIVET: Towards accurate morphometry of neonatal gyrification and clinical applications in preterm newborns. Neuroimage 138:28–42. https://doi.org/10.1016/j.neuroimage.2016.05.034
doi: 10.1016/j.neuroimage.2016.05.034
pubmed: 27184202
Liu M, Lepage C, Jeon S et al (2019) A skeleton and deformation based model for neonatal pial surface reconstruction in preterm newborns. In: 2019 IEEE 16th International symposium on biomedical imaging (ISBI 2019). IEEE, Venice, Italy, pp 352–355. https://doi.org/10.1109/ISBI.2019.8759183
Liu M, Lepage C, Kim SY et al (2021) Robust cortical thickness morphometry of neonatal brain and systematic evaluation using multi-site MRI datasets. Front Neurosci 15:650082. https://doi.org/10.3389/fnins.2021.650082
doi: 10.3389/fnins.2021.650082
pubmed: 33815050
pmcid: 8010150
Fortin JP, Cullen N, Sheline YI et al (2018) Harmonization of cortical thickness measurements across scanners and sites. Neuroimage 167:104–120. https://doi.org/10.1016/j.neuroimage.2017.11.024
doi: 10.1016/j.neuroimage.2017.11.024
pubmed: 29155184
Gupta U, Lam PK, Steeg GV, Thompson PM (2021) Improved brain age estimation with slice-based set networks. In: 2021 IEEE 18th International symposium on biomedical imaging (ISBI). IEEE, Nice, France, pp 840–844. https://doi.org/10.1109/ISBI48211.2021.9434081
Smith SM, Vidaurre D, Alfaro-Almagro F, Nichols TE, Miller KL (2019) Estimation of brain age delta from brain imaging. Neuroimage 200:528–539. https://doi.org/10.1016/j.neuroimage.2019.06.017
doi: 10.1016/j.neuroimage.2019.06.017
pubmed: 31201988
Dempsey E, Barrington K (2007) Treating hypotension in the preterm infant: when and with what: a critical and systematic review. J Perinatol 27:469–478. https://doi.org/10.1038/sj.jp.7211774
doi: 10.1038/sj.jp.7211774
pubmed: 17653217
Galinsky R, Lear CA, Dean JM et al (2018) Complex interactions between hypoxia-ischemia and inflammation in preterm brain injury. Dev Med Child Neurol 60:126–133. https://doi.org/10.1111/dmcn.13629
doi: 10.1111/dmcn.13629
pubmed: 29194585
Lemmers PM, Benders MJ, D'Ascenzo R et al (2016) Patent Ductus Arteriosus and Brain Volume. Pediatrics 137(4):e20153090. https://doi.org/10.1542/peds.2015-3090
van Vliet EO, de Kieviet JF, Oosterlaan J, van Elburg RM (2013) Perinatal infections and neurodevelopmental outcome in very preterm and very low-birth-weight infants: a meta-analysis. JAMA Pediatr 167:662–668. https://doi.org/10.1001/jamapediatrics.2013.1199
doi: 10.1001/jamapediatrics.2013.1199
pubmed: 23689313
Zonnenberg I, van Dijk-Lokkart E, van Den Dungen F, Vermeulen R, van Weissenbruch M (2019) Neurodevelopmental outcome at 2 years of age in preterm infants with late-onset sepsis. Eur J Pediatr 178:673–680. https://doi.org/10.1007/s00431-019-03339-2
doi: 10.1007/s00431-019-03339-2
pubmed: 30778747
pmcid: 6459788
Gallini F, Coppola M, Umberto De Rose D et al (2021) Neurodevelopmental outcomes in very preterm infants. The role of severity of Bronchopulmonary Dysplasia. Early Hum Dev 152:105275. https://doi.org/10.1016/j.earlhumdev.2020.105275
Kinsella JP, Greenough A, Abman SH (2006) Bronchopulmonary dysplasia. Lancet 367:1421–1431. https://doi.org/10.1016/S0140-6736(06)68615-7
doi: 10.1016/S0140-6736(06)68615-7
pubmed: 16650652
Albertine KH (2012) Brain injury in chronically ventilated preterm neonates: collateral damage related to ventilation strategy. Clin Perinatol 39:727–740. https://doi.org/10.1016/j.clp.2012.06.017
doi: 10.1016/j.clp.2012.06.017
pubmed: 22954278
pmcid: 3437037
Malavolti AM, Bassler D, Arlettaz-Mieth R et al ( 2018) Bronchopulmonary dysplasia—impact of severity and timing of diagnosis on neurodevelopment of preterm infants: a retrospective cohort study. BMJ Paediatrics Open 2:e000165. https://doi.org/10.1136/bmjpo-2017-000165
Lean RE, Han RH, Smyser TA et al (2019) Altered neonatal white and gray matter microstructure is associated with neurodevelopmental impairments in very preterm infants with high-grade brain injury. Pediatr Res 86:365–374. https://doi.org/10.1038/s41390-019-0461-1
doi: 10.1038/s41390-019-0461-1
pubmed: 31212303
pmcid: 6702093
Weeke LC, Groenendaal F, Mudigonda K et al (2018) A novel magnetic resonance imaging score predicts neurodevelopmental outcome after perinatal asphyxia and therapeutic hypothermia. J Pediatr 192(33–40):e32. https://doi.org/10.1016/j.jpeds.2017.09.043
doi: 10.1016/j.jpeds.2017.09.043
Singer LT, Siegel AC, Lewis B, Hawkins S, Yamashita T, Baley J (2001) Preschool language outcomes of children with history of bronchopulmonary dysplasia and very low birth weight. J Dev Behav Pediatr 22:19–26. https://doi.org/10.1097/00004703-200102000-00003
doi: 10.1097/00004703-200102000-00003
pubmed: 11265919
pmcid: 10246333
Natarajan G, Pappas A, Shankaran S et al (2012) Outcomes of extremely low birth weight infants with bronchopulmonary dysplasia: impact of the physiologic definition. Early Hum Dev 88:509–515. https://doi.org/10.1016/j.earlhumdev.2011.12.013
doi: 10.1016/j.earlhumdev.2011.12.013
pubmed: 22236557
pmcid: 3686277
Short EJ, Klein NK, Lewis BA et al (2003) Cognitive and academic consequences of bronchopulmonary dysplasia and very low birth weight: 8-year-old outcomes. Pediatrics 112:e359–e359. https://doi.org/10.1542/peds.112.5.e359
doi: 10.1542/peds.112.5.e359
pubmed: 14595077
Singer L, Yamashita T, Lilien L, Collin M, Baley J (1997) A longitudinal study of developmental outcome of infants with bronchopulmonary dysplasia and very low birth weight. Pediatrics 100:987–993. https://doi.org/10.1542/peds.100.6.987
doi: 10.1542/peds.100.6.987
pubmed: 9374570
Malavolti AM, Bassler D, Arlettaz-Mieth R et al (2018) Bronchopulmonary dysplasia—impact of severity and timing of diagnosis on neurodevelopment of preterm infants: a retrospective cohort study. BMJ Paediatrics Open 2:e000165. https://doi.org/10.1136/bmjpo-2017-000165
Tam EW, Chau V, Ferriero DM et al (2011) Preterm Cerebellar Growth Impairment After Postnatal Exposure to Glucocorticoids. Sci Transl Med 3:105ra105-105ra105. https://doi.org/10.1126/scitranslmed.3002884
Cheong JLY, Doyle LW (2019) Long-term effects of postnatal corticosteroids to prevent or treat bronchopulmonary dysplasia. Balancing the risks and benefits. Semin Fetal Neonatal Med 24(3):197–201. https://doi.org/10.1016/j.siny.2019.03.002
Jobe AH (2004) Postnatal corticosteroids for preterm infants–do what we say, not what we do. New Eng J Med 350:1349–1350. https://doi.org/10.1056/NEJMe048031
doi: 10.1056/NEJMe048031
pubmed: 15044647
Doyle LW (2021) Postnatal corticosteroids to prevent or treat bronchopulmonary dysplasia. Neonatology 118:244–251. https://doi.org/10.1159/000515950
doi: 10.1159/000515950
pubmed: 33975319
Guo T, Duerden EG, Adams E et al (2017) Quantitative assessment of white matter injury in preterm neonates: association with outcomes. Neurology 88:614–622. https://doi.org/10.1212/wnl.0000000000003606
doi: 10.1212/wnl.0000000000003606
pubmed: 28100727
pmcid: 5317385
Saha S, Pagnozzi A, Bourgeat P et al (2020) Predicting motor outcome in preterm infants from very early brain diffusion MRI using a deep learning convolutional neural network (CNN) model. Neuroimage 215:116807. https://doi.org/10.1016/j.neuroimage.2020.116807
doi: 10.1016/j.neuroimage.2020.116807
pubmed: 32278897
Messerschmidt A, Prayer D, Brugger PC et al (2008) Preterm birth and disruptive cerebellar development: assessment of perinatal risk factors. Eur J Paediatr Neurol 12:455–460. https://doi.org/10.1016/j.ejpn.2007.11.003
doi: 10.1016/j.ejpn.2007.11.003
pubmed: 18222715
Le TT, Kuplicki RT, McKinney BA, Yeh HW, Thompson WK, Paulus MP (2018) A nonlinear simulation framework supports adjusting for age when analyzing BrainAGE. Front Aging Neurosci 10:317. https://doi.org/10.3389/fnagi.2018.00317
doi: 10.3389/fnagi.2018.00317
pubmed: 30405393
pmcid: 6208001