Explore the vast range of titles available.

We propose BrainNetCNN, a convolutional neural network (CNN) framework to predict clinical neurodevelopmental outcomes from brain networks. In contrast to the spatially local convolutions done in traditional image-based CNNs, our BrainNetCNN is composed of novel edge-to-edge, edge-to-node and node-to-graph convolutional filters that leverage the topological locality of structural brain networks. We apply the BrainNetCNN framework to predict cognitive and motor developmental outcome scores from structural brain networks of infants born preterm. Diffusion tensor images (DTI) of preterm infants, acquired between 27 and 46 weeks gestational age, were used to construct a dataset of structural brain connectivity networks. We first demonstrate the predictive capabilities of BrainNetCNN on synthetic phantom networks with simulated injury patterns and added noise. BrainNetCNN outperforms a fully connected neural-network with the same number of model parameters on both phantoms with focal and diffuse injury patterns. We then apply our method to the task of joint prediction of Bayley-III cognitive and motor scores, assessed at 18 months of age, adjusted for prematurity. We show that our BrainNetCNN framework outperforms a variety of other methods on the same data. Furthermore, BrainNetCNN is able to identify an infant's postmenstrual age to within about 2 weeks. Finally, we explore the high-level features learned by BrainNetCNN by visualizing the importance of each connection in the brain with respect to predicting the outcome scores. These findings are then discussed in the context of the anatomy and function of the developing preterm infant brain. •First deep convolutional neural network architecture designed for connectomes.•Novel convolutional layers for leveraging topological locality in brain networks.•Prediction of neurodevelopmental outcomes in preterm infants.•Visualization of brain connections learned to be important for prediction.

Altered brain development is evident in children born very preterm (24-32 weeks gestational age), including reduction in gray and white matter volumes, and thinner cortex, from infancy to adolescence compared to term-born peers. However, many questions remain regarding the etiology. Infants born very preterm are exposed to repeated procedural pain-related stress during a period of very rapid brain development. In this vulnerable population, we have previously found that neonatal pain-related stress is associated with atypical brain development from birth to term-equivalent age. Our present aim was to evaluate whether neonatal pain-related stress (adjusted for clinical confounders of prematurity) is associated with altered cortical thickness in very preterm children at school age. 42 right-handed children born very preterm (24-32 weeks gestational age) followed longitudinally from birth underwent 3-D T1 MRI neuroimaging at mean age 7.9 yrs. Children with severe brain injury and major motor/sensory/cognitive impairment were excluded. Regional cortical thickness was calculated using custom developed software utilizing FreeSurfer segmentation data. The association between neonatal pain-related stress (defined as the number of skin-breaking procedures) accounting for clinical confounders (gestational age, illness severity, infection, mechanical ventilation, surgeries, and morphine exposure), was examined in relation to cortical thickness using constrained principal component analysis followed by generalized linear modeling. After correcting for multiple comparisons and adjusting for neonatal clinical factors, greater neonatal pain-related stress was associated with significantly thinner cortex in 21/66 cerebral regions (p-values ranged from 0.00001 to 0.014), predominately in the frontal and parietal lobes. In very preterm children without major sensory, motor or cognitive impairments, neonatal pain-related stress appears to be associated with thinner cortex in multiple regions at school age, independent of other neonatal risk factors.

Altered hippocampal morphology and reduced volumes have been found in children born preterm compared to full-term. Stress inhibits neurogenesis in the hippocampus, and neonatal stress/noxious stimulation in rodent pups are associated with long-term alterations in hippocampal volumes. We have previously shown reduced cortical thickness and cerebellar volumes in relation to more exposure to pain-related stress of neonatal invasive procedures in children born very preterm. We have reported targeted gene-by-pain environment interactions that contribute to long-term brain development and outcomes in this population. We now aim to determine whether exposure to pain-related stress (adjusted for clinical factors and genotype) differentially impacts regional structures within the limbic system and thalamus, and investigate relationships with outcomes in very preterm children. Our study included 57 children born very preterm (<32 weeks GA) followed longitudinally from birth who underwent 3-D T1 MRI neuroimaging at ∼8 years. Hippocampal subfields and white matter tracts, thalamus and amygdala were automatically segmented using the MAGeT Brain algorithm. The relationship between those subcortical brain volumes (adjusted for total brain volume) and neonatal invasive procedures, gestational age (GA), illness severity, postnatal infection, days of mechanical ventilation, number of surgeries, morphine exposure, and genotype ( , and ) was examined using constrained principal component analysis. We found that neonatal clinical factors and genotypes accounted for 46% of the overall variance in volumes of hippocampal subregions, tracts, basal ganglia, thalamus and amygdala. After controlling for clinical risk factors and total brain volume, greater neonatal invasive procedures was associated with lower volumes in the amygdala and thalamus ( = 0.0001) and an interaction with genotype predicted smaller hippocampal subregional volume ( = 0.0001). More surgeries, days of ventilation, and lower GA were also related to smaller volumes in various subcortical regions ( < 0.002). These reduced volumes were in turn differentially related to poorer cognitive, visual-motor and behavioral outcomes. Our findings highlight the complexity that interplays when examining how exposure to early-life stress may impact brain development both at the structural and functional level, and provide new insight on possible novel avenues of research to discover brain-protective treatments to improve the care of children born preterm.

ObjectivesTo assess the association of head circumference (HC) <10th percentile at birth and discharge from the neonatal intensive care unit (NICU) with neurodevelopment in very preterm (24–32 weeks’ gestational age) neonates, and to compare the association of HC and total cerebral volume (TCV) with neurodevelopmental outcomes.DesignIn a prospective cohort, semiautomatically segmented TCV and manually segmented white matter injury (WMI) volumes were obtained. Multivariable regressions were used to study the association of HC and TCV with neurodevelopmental outcomes, accounting for birth gestational age, WMI and postnatal illness.SettingParticipants born in 2006–2013 at British Columbia Women’s Hospital were recruited.Patients168 neonates had HC measurements at birth and discharge and MRI at term-equivalent age (TEA). 143 children were assessed at 4.5 years.Main outcome measuresMotor, cognitive and language outcomes at 4.5 years were assessed using the Movement Assessment Battery for Children Second Edition (M-ABC) and Wechsler Preschool and Primary Scale of Intelligence Third Edition Full Scale IQ (FSIQ) and Verbal IQ (VIQ).ResultsSmall birth HC was associated with lower M-ABC and FSIQ scores. In children with small birth HC, small discharge HC was associated with lower M-ABC, FSIQ and VIQ scores, while normal HC at discharge was no longer associated with adverse outcomes. HC strongly correlated with TCV at TEA. TCV did not correlate with outcomes.ConclusionsSmall birth HC is associated with poorer neurodevelopment, independent of postnatal illness and WMI. Normalisation of HC during NICU care appears to moderate this risk.

ObjectiveTo determine whether severe retinopathy of prematurity (ROP) is associated with (1) abnormal white matter maturation and (2) neurodevelopmental outcomes at 18 months’ corrected age (CA) compared with neonates without severe ROP.DesignWe conducted a prospective longitudinal cohort of extremely preterm neonates born 24–28 weeks’ gestational age recruited between 2006 and 2013 with brain MRIs obtained both early in life and at term-equivalent age. Severe ROP was defined as ROP treated with retinal laser photocoagulation. Using diffusion tensor imaging and tract-based spatial statistics (TBSS), white matter maturation was assessed by mean fractional anisotropy (FA) in seven predefined regions of interest. Neurodevelopmental outcomes were assessed with Bayley Scales of Infant and Toddler Development-III (Bayley-III) composite scores at 18 months’ CA. Subjects were compared using Fisher’s exact, Kruskal-Wallis and generalised estimating equations.SettingFamilies were recruited from the neonatal intensive care unit at BC Women’s Hospital.PatientsOf 98 extremely preterm neonates (median: 26.0 weeks) assessed locally for ROP, 19 (19%) had severe ROP and 83 (85%) were assessed at 18 months’ CA.ResultsSevere ROP was associated with lower FA in the posterior white matter, and with decreased measures of brain maturation in the optic radiations, posterior limb of the internal capsule (PLIC) and external capsule on TBSS. Bayley-III cognitive and motor scores were lower in infants with severe ROP.ConclusionsSevere ROP is associated with maturational delay in the optic radiations, PLIC, external capsule and posterior white matter, housing the primary visual and motor pathways, and is associated with poorer cognitive and motor outcomes at 18 months’ CA.

Neonatal pain-related stress is associated with elevated salivary cortisol levels to age 18 months in children born very preterm, compared to full-term, suggesting early programming effects. Importantly, interactions between immune/inflammatory and neuroendocrine systems may underlie programming effects. We examined whether cortisol changes persist to school age, and if common genetic variants in the promoter region of the NFKBIA gene involved in regulation of immune and inflammatory responses, modify the association between early experience and later life stress as indexed by hair cortisol levels, which provide an integrated index of endogenous HPA axis activity. Cortisol was assayed in hair samples from 128 children (83 born preterm ≤ 32 weeks gestation and 45 born full-term) without major sensory, motor or cognitive impairments at age 7 years. We found that hair cortisol levels were lower in preterm compared to term-born children. Downregulation of the HPA axis in preterm children without major impairment, seen years after neonatal stress terminated, suggests persistent alteration of stress system programming. Importantly, the etiology was gender-specific such that in preterm boys but not girls, specifically those with the minor allele for NFKBIA rs2233409, lower hair cortisol was associated with greater neonatal pain (number of skin-breaking procedures from birth to term), independent of medical confounders. Moreover, the minor allele (CT or TT) of NFKBIA rs2233409 was associated with higher secretion of inflammatory cytokines, supporting the hypothesis that neonatal pain-related stress may act as a proinflammatory stimulus that induces long-term immune cell activation. These findings are the first evidence that a long-term association between early pain-related stress and cortisol may be mediated by a genetic variants that regulate the activity of NF-κB, suggesting possible involvement of stress/inflammatory mechanisms in HPA programming in boys born very preterm.

To predict adverse neurodevelopmental outcome of very preterm neonates. A total of 166 preterm neonates born between 24–32 weeks’ gestation underwent brain MRI early in life. Radiomics features were extracted from T1- and T2- weighted images. Motor, cognitive, and language outcomes were assessed at a corrected age of 18 and 33 months and 4.5 years. Elastic Net was implemented to select the clinical and radiomic features that best predicted outcome. The area under the receiver operating characteristic (AUROC) curve was used to determine the predictive ability of each feature set. Clinical variables predicted cognitive outcome at 18 months with AUROC 0.76 and motor outcome at 4.5 years with AUROC 0.78. T1-radiomics features showed better prediction than T2-radiomics on the total motor outcome at 18 months and gross motor outcome at 33 months (AUROC: 0.81 vs 0.66 and 0.77 vs 0.7). T2-radiomics features were superior in two 4.5-year motor outcomes (AUROC: 0.78 vs 0.64 and 0.8 vs 0.57). Combining clinical parameters and radiomics features improved model performance in motor outcome at 4.5 years (AUROC: 0.84 vs 0.8). Radiomic features outperformed clinical variables for the prediction of adverse motor outcomes. Adding clinical variables to the radiomics model enhanced predictive performance.

Children born very preterm are exposed to repeated neonatal procedures that induce pain and stress during hospitalization in the neonatal intensive care unit (NICU). The COMT Val158Met genotype is involved with pain sensitivity, and early life stress is implicated in altered expression of methylation of the serotonin transporter. We examined: (1) whether methylation of the serotonin transporter gene (SLC6A4) promoter differs between very preterm children and full-term controls at school age, (2) relationships with child behavior problems, and (3) whether the extent of neonatal pain exposure interacts with the COMT Val158Met genotype to predict SLC6A4 methylation at 7 years in the very preterm children. We examined the associations between the COMT genotypes, neonatal pain exposure (adjusted for neonatal clinical confounders), SLC6A4 methylation and behavior problems. Very preterm children had significantly higher methylation at 7/10 CpG sites in the SLC6A4 promoter compared to full-term controls at 7 years. Neonatal pain (adjusted for clinical confounders) was significantly associated with total child behavior problems on the Child Behavior Checklist (CBCL) questionnaire (adjusted for concurrent stressors and 5HTTLPR genotype) (p = 0.035). CBCL Total Problems was significantly associated with greater SLC6A4 methylation in very preterm children (p = 0.01). Neonatal pain (adjusted for clinical confounders) and COMT Met/Met genotype were associated with SLC6A4 promoter methylation in very preterm children at 7 years (p = 0.001). These findings provide evidence that both genetic predisposition and early environment need to be considered in understanding susceptibility for developing behavioral problems in this vulnerable population.

Functional MRI studies suggest that healthy full-term newborn babies experience some aspects of pain in a similar way to adults.

The objective of this study was to investigate how patterns of maternal depressive symptoms from mid-pregnancy to 3 years postpartum are associated with children’s behavior at age 3 years and executive functions. Maternal depressive symptoms were measured from mid-pregnancy to 3 years postpartum. Growth mixture modeling was used on standardized maternal depression scores (n = 147) to identify trajectories. Children’s behavioral problems and mental health symptomatology (internalizing, externalizing, and attention deficit hyperactivity disorder) were obtained at 3 and 6 years. EFs were assessed by a laboratory-based computerized task and maternal-report at 6 years. Multivariable linear regressions of children’s outcomes against maternal depressive symptom trajectories were conducted (n = 103). Three distinct patterns of maternal depressive symptom trajectories were identified: low (n = 105), increasing (n = 27), and decreasing (n = 15). Children of mothers whose depressive symptoms increased reported more problem behaviors at 3 years and poorer EFs at 6 years as assessed by both instruments, but no significant differences in mental health symptomatology at 6 years, relative to those whose mothers had consistently low depressive symptoms. Children whose mothers became less depressed over time had comparable levels of behavioral problems at age 3, executive functions, and internalizing and externalizing scores at age 6; and fewer reported ADHD behaviors at age 6, than those whose mothers remained less depressed over time. If mothers’ depressive symptoms improve over the first 3 years postpartum, their children’s outlook may be comparable to those whose mothers had consistently low depressive symptoms.