1
|
Early brain magnetic resonance imaging findings and neurodevelopmental outcome in children with congenital heart disease: A systematic review. Dev Med Child Neurol 2023; 65:1557-1572. [PMID: 37035939 DOI: 10.1111/dmcn.15588] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/15/2022] [Revised: 02/27/2023] [Accepted: 03/01/2023] [Indexed: 04/11/2023]
Abstract
AIM To investigate the association between early brain magnetic resonance imaging (MRI) findings and neurodevelopmental outcome (NDO) in children with congenital heart disease (CHD). METHOD A search for studies was conducted in Embase, Medline, Web of Science, Cochrane Central, PsycINFO, and Google Scholar. Observational and interventional studies were included, in which patients with CHD underwent surgery before 2 months of age, a brain MRI scan in the first year of life, and neurodevelopmental assessment beyond the age of 1 year. RESULTS Eighteen studies were included. Thirteen found an association between either quantitative or qualitative brain metrics and NDO: 5 out of 7 studies showed decreased brain volume was significantly associated with worse NDO, as did 7 out of 10 studies on brain injury. Scanning protocols and neurodevelopmental tests varied strongly. INTERPRETATION Reduced brain volume and brain injury in patients with CHD can be associated with impaired NDO, yet standardized scanning protocols and neurodevelopmental assessment are needed to further unravel trajectories of impaired brain development and its effects on outcome.
Collapse
|
2
|
Altered In Utero Metabolic Brain Trajectories in CHD: Going Beyond Fetal Brain Structure and Physiology. J Am Coll Cardiol 2023; 82:1624-1627. [PMID: 37821173 DOI: 10.1016/j.jacc.2023.08.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Accepted: 08/31/2023] [Indexed: 10/13/2023]
|
3
|
Fetal MRI of the heart and brain in congenital heart disease. THE LANCET. CHILD & ADOLESCENT HEALTH 2023; 7:59-68. [PMID: 36343660 DOI: 10.1016/s2352-4642(22)00249-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/13/2022] [Revised: 08/12/2022] [Accepted: 08/22/2022] [Indexed: 11/06/2022]
Abstract
Antenatal assessment of congenital heart disease and associated anomalies by ultrasound has improved perinatal care. Fetal cardiovascular MRI and fetal brain MRI are rapidly evolving for fetal diagnostic testing of congenital heart disease. We give an overview on the use of fetal cardiovascular MRI and fetal brain MRI in congenital heart disease, focusing on the current applications and diagnostic yield of structural and functional imaging during pregnancy. Fetal cardiovascular MRI in congenital heart disease is a promising supplementary imaging method to echocardiography for the diagnosis of antenatal congenital heart disease in weeks 30-40 of pregnancy. Concomitant fetal brain MRI is superior to brain ultrasound to show the complex relationship between fetal haemodynamics in congenital heart disease and brain development.
Collapse
|
4
|
Effects of cognitive-motor dual task training on cognitive and physical performance in healthy children and adolescents: A scoping review. Acta Psychol (Amst) 2022; 224:103498. [PMID: 35091209 DOI: 10.1016/j.actpsy.2022.103498] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2021] [Revised: 12/18/2021] [Accepted: 01/04/2022] [Indexed: 12/16/2022] Open
Abstract
Simultaneous dual- or multitasking training has been used in manifold ways to improve cognitive-motor performance in different age groups. Dual task (DT) training is assumed to improve both, single task (ST) motor and cognitive performance, but particularly, performance under dual tasking conditions. Further, DT interventions have been shown to be beneficial for motor skill learning and cognitive performance as well as academic achievements in children and adolescents. The aim of this scoping review was to summarize current evidence on different cognitive-motor interventions that practice motor and cognitive performance simultaneously in children and adolescents and to identify training regimes that are most effective to improve cognitive or motor performance in this target group. METHODS Four electronic databases were searched (Pubmed, MEDLINE, Web of Science and APA Psycinfo) until May 2021. Following the PRISMA guidelines, title, abstract, and full-text screening as well as quality assessment was done by two independent reviewers. Studies were eligible if they (1) were published in English or German language, (2) accessible as a full-text version, (3) included at least one group of children or adolescents with a mean age of 4 to 21 years, (4) used dual-tasks as part of the intervention, (5) conducted one or more training sessions, and (6) reported at least one cognitive or motor outcome. The main outcome measures were cognitive and motor as well as cognitive-motor DT performance. Due to the heterogeneity in the characteristics of the included studies, we designed this review as a scoping review. RESULTS Seven studies met the inclusion criteria (n = 543, age four to 14 years, 47.1% female). One study reported two intervention experiments. Studies differed in sample size (20-189) as well as in type of training (specific or general DT training) and dose (frequency: one session/week to 110 sessions within 22 weeks). Overall, task-specific improvements in physical and cognitive functions were found, but not consistently across all interventions. Two interventions out of five interventions that measured motor performance demonstrated improvement in that domain, especially in balance. Three out of five interventions that measured cognitive functions found improved cognition. Only one study examined DT performance post training but failed to gain significant improvements in comparison to a control group. Studies only occasionally integrated training principles like individualization or progression in the design of their intervention. DISCUSSION The results indicate that DT training interventions may improve physical and/or cognitive functions in children and adolescents. Best practice recommendations for training regimes cannot be derived as outcomes differed a lot and were not systematically assessed across studies. Future studies should integrate more principles of training monitoring and aspects like individualization and progression to provide ideal training control and achieve better DT training results. Further, more high-quality trials are needed that adhere to the previous concepts. PSYCINFO CLASSIFICATION 2340 Cognitive Processes 2820 Cognitive & Perceptual Development. 3720 Sports.
Collapse
|
5
|
Brainstem and cerebellar volumes at magnetic resonance imaging are smaller in fetuses with congenital heart disease. Am J Obstet Gynecol 2022; 227:282.e1-282.e15. [PMID: 35305961 DOI: 10.1016/j.ajog.2022.03.030] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2022] [Revised: 03/12/2022] [Accepted: 03/14/2022] [Indexed: 12/11/2022]
Abstract
BACKGROUND Congenital heart disease is associated with an increased risk of smaller brain volumes and structural brain damage, and impaired growth of supratentorial brain structures in utero has been linked to poor neurodevelopmental outcomes. However, little is known on brainstem and cerebellar volumes in fetuses with congenital heart disease. Moreover, it is not clear whether impaired infratentorial growth, if present, is associated with only certain types of fetal cardiac defects or with supratentorial brain growth, and whether altered biometry is already present before the third trimester. OBJECTIVE This study aimed to investigate brainstem and cerebellar volumes in fetuses with congenital heart disease and to compare them to infratentorial brain volumes in fetuses with normal hearts. Secondarily, the study aimed to identify associations between infratentorial brain biometry and the type of cardiac defects, supratentorial brain volumes, and gestational age. STUDY DESIGN In this retrospective case-control study, 141 magnetic resonance imaging studies of 135 fetuses with congenital heart disease and 141 magnetic resonance imaging studies of 125 controls with normal hearts at 20 to 37 gestational weeks (median, 25 weeks) were evaluated. All cases and controls had normal birthweight and no evidence of structural brain disease or genetic syndrome. Six types of congenital heart disease were included: tetralogy of Fallot (n=32); double-outlet right ventricle (n=22); transposition of the great arteries (n=27); aortic obstruction (n=24); hypoplastic left heart syndrome (n=22); and hypoplastic right heart syndrome (n=14). First, brainstem and cerebellar volumes of each fetus were segmented and compared between cases and controls. In addition, transverse cerebellar diameters, vermian areas, and supratentorial brain and cerebrospinal fluid volumes were quantified and differences assessed between cases and controls. Volumetric differences were further analyzed according to types of cardiac defects and supratentorial brain volumes. Finally, volume ratios were created for each brain structure ([volume in fetus with congenital heart disease/respective volume in control fetus] × 100) and correlated to gestational age. RESULTS Brainstem (cases, 2.1 cm3 vs controls, 2.4 cm3; P<.001) and cerebellar (cases, 3.2 cm3 vs controls, 3.4 cm3; P<.001) volumes were smaller in fetuses with congenital heart disease than in controls, whereas transverse cerebellar diameters (P=.681) and vermian areas (P=.947) did not differ between groups. Brainstem and cerebellar volumes differed between types of cardiac defects. Overall, the volume ratio of cases to controls was 80.8% for the brainstem, 90.5% for the cerebellum, and 90.1% for the supratentorial brain. Fetuses with tetralogy of Fallot and transposition of the great arteries were most severely affected by total brain volume reduction. Gestational age had no effect on volume ratios. CONCLUSION The volume of the infratentorial brain, which contains structures considered crucial to brain function, is significantly smaller in fetuses with congenital heart disease than in controls from midgestation onward. These findings suggest that impaired growth of both supra- and infratentorial brain structures in fetuses with congenital heart disease occurs in the second trimester. Further research is needed to elucidate associations between fetal brain volumes and neurodevelopmental outcomes in congenital heart disease.
Collapse
|
6
|
Cerebellar and Prefrontal Structures Associated With Executive Functioning in Pediatric Patients With Congenital Heart Defects. Front Neurol 2022; 13:827780. [PMID: 35356449 PMCID: PMC8959311 DOI: 10.3389/fneur.2022.827780] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2021] [Accepted: 01/31/2022] [Indexed: 11/17/2022] Open
Abstract
Objective Children, adolescents, and young adults with congenital heart defects (CHD) often display executive dysfunction. We consider the prefrontal and cerebellar brain structures as mechanisms for executive dysfunction among those with CHD. Methods 55 participants with CHD (M age = 13.93) and 95 healthy controls (M age = 13.13) completed magnetic resonance imaging (MRI) of the brain, from which we extracted volumetric data on prefrontal and cerebellar regions. Participants also completed neuropsychological tests of executive functioning; their parents completed ratings of their executive functions. Results Compared to healthy controls, those with CHD had smaller cerebellums and lateral, medial, and orbital prefrontal regions, they performed more poorly on tests of working memory, inhibitory control, and mental flexibility, and their parents rated them as having poorer executive functions across several indices. Across both groups, there were significant correlations for cerebellar and/or prefrontal volumes with cognitive assessments of working memory, mental flexibility, and inhibitory control and with parent-completed ratings of task initiation, working memory, and planning/organization. Greater prefrontal volumes were associated with better working memory, among those with larger cerebellums (with group differences based on the measure and the prefrontal region). Greater prefrontal volumes were related to better emotional regulation only among participants with CHD with smaller cerebellar volumes, and with poorer inhibition and emotional regulation only among healthy controls with larger cerebellar volumes. Conclusion The cerebellum not only contributes to executive functioning among young individuals with CHD but may also modulate the relationships between prefrontal regions and executive functioning differently for pediatric patients with CHD vs. health controls.
Collapse
|
7
|
Abstract
Following the improvements in the clinical management of patients with congenital heart disease (CHD) and their increased survival, neurodevelopmental outcome has become an emerging priority in pediatric cardiology. Large-scale efforts have been made to protect the brain during the postnatal, surgical, and postoperative period; however, the presence of brain immaturity and injury at birth suggests in utero and peripartum disturbances. Over the past decade, there has been considerable interest and investigations on fetal brain growth in the setting of CHD. Advancements in fetal brain imaging have identified abnormal brain development in fetuses with CHD from the macrostructural (brain volumes and cortical folding) down to the microstructural (biochemistry and water diffusivity) scale, with more severe forms of CHD showing worse disturbances and brain abnormalities starting as early as the first trimester. Anomalies in common genetic developmental pathways and diminished cerebral substrate delivery secondary to altered cardiovascular physiology are the forefront hypotheses, but other factors such as impaired placental function and maternal psychological stress have surfaced as important contributors to fetal brain immaturity in CHD. The characterization and timing of fetal brain disturbances and their associated mechanisms are important steps for determining preventative prenatal interventions, which may provide a stronger foundation for the developing brain during childhood.
Collapse
|
8
|
Editorial for "3D Volumetric MRI Detects Early Alterations of the Brain Growth in Fetuses with Congenital Heart Disease". J Magn Reson Imaging 2021; 54:273-274. [PMID: 33543806 DOI: 10.1002/jmri.27522] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2021] [Accepted: 01/07/2021] [Indexed: 11/10/2022] Open
|
9
|
Biometric assessments of the posterior fossa by fetal MRI: A systematic review. Prenat Diagn 2020; 41:258-270. [PMID: 33251640 DOI: 10.1002/pd.5874] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2020] [Revised: 10/07/2020] [Accepted: 11/19/2020] [Indexed: 12/12/2022]
Abstract
BACKGROUND Posterior fossa abnormalities (PFAs) are commonly identified within routine screening and are a frequent indication for fetal magnetic resonance imaging (MRI). Although biometric measurements of the posterior fossa (PF) are established on fetal ultrasound and MRI, qualitative visual assessments are predominantly used to differentiate PFAs. OBJECTIVES This systematic review aimed to assess 2-dimensional (2D) biometric measurements currently in use for assessing the PF on fetal MRI to delineate different PFAs. METHODS The protocol was registered (PROSPERO ID CRD42019142162). Eligible studies included T2-weighted MRI PF measurements in fetuses with and without PFAs, including measurements of the PF, or other brain areas relevant to PFAs. RESULTS 59 studies were included - 6859 fetuses had 62 2D PF and related measurements. These included linear, area and angular measurements, representing measures of PF size, cerebellum/vermis, brainstem, and supratentorial measurements. 11 measurements were used in 10 or more studies and at least 1200 fetuses. These dimensions were used to characterise normal for gestational age, diagnose a range of pathologies, and predict outcome. CONCLUSION A selection of validated 2D biometric measurements of the PF on fetal MRI may be useful for identification of PFA in different clinical settings. Consistent use of these measures, both clinically and for research, is recommended.
Collapse
|
10
|
Growth trajectories of the human fetal brain in healthy and complicated pregnancies and associations with neurodevelopmental outcome in the early life course. Early Hum Dev 2020; 151:105224. [PMID: 33091852 DOI: 10.1016/j.earlhumdev.2020.105224] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/26/2020] [Revised: 09/03/2020] [Accepted: 10/03/2020] [Indexed: 01/21/2023]
Abstract
BACKGROUND There is a need for non-invasive prenatal markers of the brain to assess fetuses at risk for poor postnatal neurodevelopmental outcome. Periconceptional maternal conditions and pregnancy complications impact prenatal brain development. AIMS To investigate associations between growth trajectories of fetal brain structures and neurodevelopmental outcome in children in the early life course. STUDY DESIGN Periconceptional prospective observational cohort. SUBJECTS Singleton pregnancies were included in the Rotterdam periconception cohort. Two- and three-dimensional ultrasound scans at 22, 26 and 32 weeks gestational age were analysed. OUTCOME MEASURES Head circumference (HC), cerebellum, corpus callosum (CC), Sylvian fissure, insula and parieto-occipital fissure (POF) were measured. Neurodevelopment was evaluated using the Age-and-Stages-questionnaire-3 (ASQ-3) and the Child-Behaviour-Checklist (CBCL) at 2 years of age. Linear mixed models, used to estimate the prenatal brain growth trajectories, and linear regression models, used to evaluate the associations between prenatal brain structures and neurodevelopmental outcomes, were applied in the total study population, and in subgroups: fetal growth restriction (FGR), preterm birth (PTB), fetal congenital heart disease (CHD), and uncomplicated controls. RESULTS Consent for participation was received from parents on behalf of their child 138/203 (68%). ASQ-3 was completed in 128/203 children (63%) and CBCL in 93/203 children (46%). Significant smaller subject-specific growth trajectories (growth rate of CC, HC, left insula, left POF and right POF and the baseline size of CC, HC, left POF and right POF) were found in the FGR subgroup, compared to the other subgroups (all p-values <0.05). In the total group (n = 138), the growth rate of the left insula was associated with poorer ASQ-3 score (β = -869.51; p < 0.05). Healthy controls (n = 106) showed a comparable association (β = -1209.87; p < 0.01). FGR (n = 10) showed a larger baseline size of the right Sylvian fissure in association with poorer CBCL-score (β = 4.13; p < 0.01). In CHD (n = 12) the baseline size of the left Sylvian fissure and its growth rate were associated with respectively poorer and better CBCL-scores (β = 3.11; p < 0.01); (β = -171.99; p < 0.01). In PTB (n = 10) no associations were found. CONCLUSIONS This explorative study suggests associations between ultrasound measurements of fetal brain growth and neurodevelopmental outcome at 2 years of age. In future, this non-invasive technique may improve early identification of fetuses at risk for neurodevelopmental outcome and follow-up postnatal clinical care.
Collapse
|
11
|
Reduced structural connectivity in cortico-striatal-thalamic network in neonates with congenital heart disease. Neuroimage Clin 2020; 28:102423. [PMID: 32987301 PMCID: PMC7520425 DOI: 10.1016/j.nicl.2020.102423] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Revised: 08/17/2020] [Accepted: 09/07/2020] [Indexed: 12/15/2022]
Abstract
Impaired brain development has been observed in newborns with congenital heart disease (CHD). We performed graph theoretical analyses and network-based statistics (NBS) to assess global brain network topology and identify subnetworks of altered connectivity in infants with CHD prior to cardiac surgery. Fifty-eight infants with critical/serious CHD prior to surgery and 116 matched healthy controls as part of the developing Human Connectome Project (dHCP) underwent MRI on a 3T system and high angular resolution diffusion MRI (HARDI) was obtained. Multi-tissue constrained spherical deconvolution, anatomically constrained probabilistic tractography (ACT) and spherical-deconvolution informed filtering of tractograms (SIFT2) was used to construct weighted structural networks. Network topology was assessed and NBS was used to identify structural connectivity differences between CHD and control groups. Structural networks were partitioned into core and peripheral nodes, and edges classed as core, peripheral, or feeder. NBS identified one subnetwork with reduced structural connectivity in CHD infants involving basal ganglia, amygdala, hippocampus, cerebellum, vermis, and temporal and parieto-occipital lobe, primarily affecting core nodes and edges. However, we did not find significantly different global network characteristics in CHD neonates. This locally affected sub-network with reduced connectivity could explain, at least in part, the neurodevelopmental impairments associated with CHD.
Collapse
|
12
|
Association between Subcortical Morphology and Cerebral White Matter Energy Metabolism in Neonates with Congenital Heart Disease. Sci Rep 2018; 8:14057. [PMID: 30232359 PMCID: PMC6145929 DOI: 10.1038/s41598-018-32288-3] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2018] [Accepted: 09/05/2018] [Indexed: 12/11/2022] Open
Abstract
Complex congenital heart disease (CHD) is associated with neurodevelopmental impairment, the mechanism of which is unknown. Cerebral cortical dysmaturation in CHD is linked to white matter abnormalities, including developmental vulnerability of the subplate, in relation to oxygen delivery and metabolism deficits. In this study, we report associations between subcortical morphology and white matter metabolism in neonates with CHD using quantitative magnetic resonance imaging (MRI) and spectroscopy (MRS). Multi-modal brain imaging was performed in three groups of neonates close to term-equivalent age: (1) term CHD (n = 56); (2) preterm CHD (n = 37) and (3) preterm control group (n = 22). Thalamic volume and cerebellar transverse diameter were obtained in relation to cerebral metrics and white matter metabolism. Short echo single-voxel MRS of parietal and frontal white matter was used to quantitate metabolites related to brain maturation (n-acetyl aspartate [NAA], choline, myo-inositol), neurotransmitter (glutamate), and energy metabolism (glutamine, citrate, creatine and lactate). Multi-variate regression was performed to delineate associations between subcortical morphological measurements and white matter metabolism controlling for age and white matter injury. Reduced thalamic volume, most pronounced in the preterm control group, was associated with increased citrate levels in all three group in the parietal white matter. In contrast, reduced cerebellar volume, most pronounced in the preterm CHD group, was associated with reduced glutamine in parietal grey matter in both CHD groups. Single ventricle anatomy, aortic arch obstruction, and cyanotic lesion were predictive of the relationship between reduced subcortical morphometry and reduced GLX (particularly glutamine) in both CHD cohorts (frontal white matter and parietal grey matter). Subcortical morphological associations with brain metabolism were also distinct within each of the three groups, suggesting these relationships in the CHD groups were not directly related to prematurity or white matter injury alone. Taken together, these findings suggest that subplate vulnerability in CHD is likely relevant to understanding the mechanism of both cortical and subcortical dysmaturation in CHD infants. Future work is needed to link this potential pattern of encephalopathy of CHD (including the constellation of grey matter, white matter and brain metabolism deficits) to not only abnormal fetal substrate delivery and oxygen conformance, but also regional deficits in cerebral energy metabolism.
Collapse
|
13
|
Abstract
Predicting neurodevelopmental outcomes in high-risk neonates remains challenging despite advances in neonatal care. Early and accurate characterization of infants at risk for neurodevelopmental delays is necessary to best identify those who may benefit from existing early interventions and novel therapies that become available. Although neuroimaging is a promising biomarker in the prediction of neurodevelopmental outcomes in high-risk infants, it requires additional resources and expertise. Despite many advances in neonatal neuroimaging, there remain limitations in relating early neuroimaging findings with long-term outcomes; further studies are necessary to determine the optimal protocols to best identify high-risk patients and improve neurodevelopmental outcome prediction.
Collapse
|
14
|
A computational framework for the detection of subcortical brain dysmaturation in neonatal MRI using 3D Convolutional Neural Networks. Neuroimage 2018; 178:183-197. [PMID: 29793060 PMCID: PMC6503677 DOI: 10.1016/j.neuroimage.2018.05.049] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2018] [Revised: 05/04/2018] [Accepted: 05/19/2018] [Indexed: 12/16/2022] Open
Abstract
Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging.
Collapse
|
15
|
Volumetric Brain MRI Study in Fetuses with Congenital Heart Disease. AJNR Am J Neuroradiol 2018; 39:1164-1169. [PMID: 29674414 DOI: 10.3174/ajnr.a5628] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2017] [Accepted: 02/14/2018] [Indexed: 11/07/2022]
Abstract
BACKGROUND AND PURPOSE It is well-established that a high prevalence of infants with congenital heart defects surviving to childhood have neurodevelopmental abnormalities. The etiology is not clear. In this study, we aimed to find prenatal neuroanatomic changes in fetuses with congenital heart disease to better understand the pathophysiology behind these sequelae. MATERIALS AND METHODS A retrospective study of 46 fetal brain MR imaging scans was performed at a tertiary medical center during a 4-year period. Clinical data were collected from electronic medical charts. Volumes of the supratentorial brain, right hemisphere, left hemisphere, and cerebellum were measured using a semiautomated method and were compared with the normal growth percentiles. RESULTS We found that cerebellar volume and the cerebellar-supratentorial volume ratio were significantly lower among fetuses with congenital heart disease. Supratentorial and hemisphere volumes showed no difference between groups. This difference was not observed in fetuses with septation defects. CONCLUSIONS Fetuses with congenital heart disease have smaller cerebellar volumes than healthy fetuses. Additional research is needed to assess this finding as a radiologic marker for long-term outcome.
Collapse
|