Divergent growth of the transient brain compartments in fetuses with nonsyndromic isolated clefts involving the primary and secondary palate.

Cleft lip/palate is a common orofacial malformation that often leads to speech/language difficulties as well as developmental delays in affected children, despite surgical repair. Our understanding of brain development in these children is limited. This study aimed to analyze prenatal brain development in fetuses with cleft lip/palate and controls. We examined in utero MRIs of 30 controls and 42 cleft lip/palate fetal cases and measured regional brain volumes. Cleft lip/palate was categorized into groups A (cleft lip or alveolus) and B (any combination of clefts involving the primary and secondary palates). Using a repeated-measures regression model with relative brain hemisphere volumes (%), and after adjusting for multiple comparisons, we did not identify significant differences in regional brain growth between group A and controls. Group B clefts had significantly slower weekly cerebellar growth compared with controls. We also observed divergent brain growth in transient brain structures (cortical plate, subplate, ganglionic eminence) within group B clefts, depending on severity (unilateral or bilateral) and defect location (hemisphere ipsilateral or contralateral to the defect). Further research is needed to explore the association between regional fetal brain growth and cleft lip/palate severity, with the potential to inform early neurodevelopmental biomarkers and personalized diagnostics.

Risk factors for health impairments in children after hospitalization for acute COVID-19 or MIS-C.

Objective: To identify risk factors for persistent impairments after pediatric hospitalization for acute coronavirus disease 2019 (COVID-19) or multisystem inflammatory syndrome in children (MIS-C) during the SARS-CoV-2 pandemic. Methods: Across 25 U.S. Overcoming COVID-19 Network hospitals, we conducted a prospective cohort study of patients <21-years-old hospitalized for acute COVID-19 or MIS-C (May 2020 to March 2022) surveyed 2- to 4-months post-admission. Multivariable regression was used to calculate adjusted risk ratios (aRR) and 95% confidence intervals (CI). Results: Of 232 children with acute COVID-19, 71 (30.6%) had persistent symptoms and 50 (21.6%) had activity impairments at follow-up; for MIS-C (n = 241), 56 (23.2%) had persistent symptoms and 58 (24.1%) had activity impairments. In adjusted analyses of patients with acute COVID-19, receipt of mechanical ventilation was associated with persistent symptoms [aRR 1.83 (95% CI: 1.07, 3.13)] whereas obesity [aRR 2.18 (95% CI: 1.05, 4.51)] and greater organ system involvement [aRR 1.35 (95% CI: 1.13, 1.61)] were associated with activity impairment. For patients with MIS-C, having a pre-existing respiratory condition was associated with persistent symptoms [aRR 3.04 (95% CI: 1.70, 5.41)] whereas obesity [aRR 1.86 (95% CI: 1.09, 3.15)] and greater organ system involvement [aRR 1.26 (1.00, 1.58)] were associated with activity impairments. Discussion: Among patients hospitalized, nearly one in three hospitalized with acute COVID-19 and one in four hospitalized with MIS-C had persistent impairments for ≥2 months post-hospitalization. Persistent impairments were associated with more severe illness and underlying health conditions, identifying populations to target for follow-up.

Atypical fetal brain development in fetuses with non-syndromic isolated musculoskeletal birth defects (niMSBDs).

Non-syndromic, isolated musculoskeletal birth defects (niMSBDs) are among the leading causes of pediatric hospitalization. However, little is known about brain development in niMSBDs. Our study aimed to characterize prenatal brain development in fetuses with niMSBDs and identify altered brain regions compared to controls. We retrospectively analyzed in vivo structural T2-weighted MRIs of 99 fetuses (48 controls and 51 niMSBDs cases). For each group (19-31 and >31 gestational weeks (GW)), we conducted repeated-measures regression analysis with relative regional volume (% brain hemisphere) as a dependent variable (adjusted for age, side, and interactions). Between 19 and 31GW, fetuses with niMSBDs had a significantly (P < 0.001) smaller relative volume of the intermediate zone (-22.9 ± 3.2%) and cerebellum (-16.1 ± 3.5%,) and a larger relative volume of proliferative zones (38.3 ± 7.2%), the ganglionic eminence (34.8 ± 7.3%), and the ventricles (35.8 ± 8.0%). Between 32 and 37 GW, compared to the controls, niMSBDs showed significantly smaller volumes of central regions (-9.1 ± 2.1%) and larger volumes of the cortical plate. Our results suggest there is altered brain development in fetuses with niMSBDs compared to controls (13.1 ± 4.2%). Further basic and translational neuroscience research is needed to better visualize these differences and to characterize the altered development in fetuses with specific niMSBDs.

Factors Associated With Attendance for Cardiac Neurodevelopmental Evaluation.

BACKGROUND AND OBJECTIVES: Neurodevelopmental evaluation of toddlers with complex congenital heart disease is recommended but reported frequency is low. Data on barriers to attending neurodevelopmental follow-up are limited. This study aims to estimate the attendance rate for a toddler neurodevelopmental evaluation in a contemporary multicenter cohort and to assess patient and center level factors associated with attending this evaluation. METHODS: This is a retrospective cohort study of children born between September 2017 and September 2018 who underwent cardiopulmonary bypass in their first year of life at a center contributing data to the Cardiac Neurodevelopmental Outcome Collaborative and Pediatric Cardiac Critical Care Consortium clinical registries. The primary outcome was attendance for a neurodevelopmental evaluation between 11 and 30 months of age. Sociodemographic and medical characteristics and center factors specific to neurodevelopmental program design were considered as predictors for attendance. RESULTS: Among 2385 patients eligible from 16 cardiac centers, the attendance rate was 29.0% (692 of 2385), with a range of 7.8% to 54.3% across individual centers. In multivariable logistic regression models, hospital-initiated (versus family-initiated) scheduling for neurodevelopmental evaluation had the largest odds ratio in predicting attendance (odds ratio = 4.24, 95% confidence interval, 2.74-6.55). Other predictors of attendance included antenatal diagnosis, absence of Trisomy 21, higher Society of Thoracic Surgeons-European Association for Cardio-Thoracic Surgery mortality category, longer postoperative length of stay, private insurance, and residing a shorter distance from the hospital. CONCLUSIONS: Attendance rates reflect some improvement but remain low. Changes to program infrastructure and design and minimizing barriers affecting access to care are essential components for improving neurodevelopmental care and outcomes for children with congenital heart disease.

Neurological and Psychological Sequelae Associated With Multisystem Inflammatory Syndrome in Children.

Importance: Acute neurological involvement occurs in some patients with multisystem inflammatory syndrome in children (MIS-C), but few data report neurological and psychological sequelae, and no investigations include direct assessments of cognitive function 6 to 12 months after discharge. Objective: To characterize neurological, psychological, and quality of life sequelae after MIS-C. Design, Setting, and Participants: This cross-sectional cohort study was conducted in the US and Canada. Participants included children with MIS-C diagnosed from November 2020 through November 2021, 6 to 12 months after hospital discharge, and their sibling or community controls, when available. Data analysis was performed from August 2022 to May 2023. Exposure: Diagnosis of MIS-C. Main Outcomes and Measures: A central study site remotely administered a onetime neurological examination and in-depth neuropsychological assessment including measures of cognition, behavior, quality of life, and daily function. Generalized estimating equations, accounting for matching, assessed for group differences. Results: Sixty-four patients with MIS-C (mean [SD] age, 11.5 [3.9] years; 20 girls [31%]) and 44 control participants (mean [SD] age, 12.6 [3.7] years; 20 girls [45%]) were enrolled. The MIS-C group exhibited abnormalities on neurological examination more frequently than controls (15 of 61 children [25%] vs 3 of 43 children [7%]; odds ratio, 4.7; 95% CI, 1.3-16.7). Although the 2 groups performed similarly on most cognitive measures, the MIS-C group scored lower on the National Institutes of Health Cognition Toolbox List Sort Working Memory Test, a measure of executive functioning (mean [SD] scores, 96.1 [14.3] vs 103.1 [10.5]). Parents reported worse psychological outcomes in cases compared with controls, particularly higher scores for depression symptoms (mean [SD] scores, 52.6 [13.1] vs 47.8 [9.4]) and somatization (mean [SD] scores, 55.5 [15.5] vs 47.0 [7.6]). Self-reported (mean [SD] scores, 79.6 [13.1] vs 85.5 [12.3]) and parent-reported (mean [SD] scores, 80.3 [15.5] vs 88.6 [13.0]) quality of life scores were also lower in cases than controls. Conclusions and Relevance: In this cohort study, compared with contemporaneous sibling or community controls, patients with MIS-C had more abnormal neurologic examinations, worse working memory scores, more somatization and depression symptoms, and lower quality of life 6 to 12 months after hospital discharge. Although these findings need to be confirmed in larger studies, enhanced monitoring may be warranted for early identification and treatment of neurological and psychological symptoms.

Abnormal prenatal brain development in Chiari II malformation.

Introduction: The Chiari II is a relatively common birth defect that is associated with open spinal abnormalities and is characterized by caudal migration of the posterior fossa contents through the foramen magnum. The pathophysiology of Chiari II is not entirely known, and the neurobiological substrate beyond posterior fossa findings remains unexplored. We aimed to identify brain regions altered in Chiari II fetuses between 17 and 26 GW. Methods: We used in vivo structural T2-weighted MRIs of 31 fetuses (6 controls and 25 cases with Chiari II). Results: The results of our study indicated altered development of diencephalon and proliferative zones (ventricular and subventricular zones) in fetuses with a Chiari II malformation compared to controls. Specifically, fetuses with Chiari II showed significantly smaller volumes of the diencephalon and significantly larger volumes of lateral ventricles and proliferative zones. Discussion: We conclude that regional brain development should be taken into consideration when evaluating prenatal brain development in fetuses with Chiari II.

Learning to segment fetal brain tissue from noisy annotations.

Automatic fetal brain tissue segmentation can enhance the quantitative assessment of brain development at this critical stage. Deep learning methods represent the state of the art in medical image segmentation and have also achieved impressive results in brain segmentation. However, effective training of a deep learning model to perform this task requires a large number of training images to represent the rapid development of the transient fetal brain structures. On the other hand, manual multi-label segmentation of a large number of 3D images is prohibitive. To address this challenge, we segmented 272 training images, covering 19-39 gestational weeks, using an automatic multi-atlas segmentation strategy based on deformable registration and probabilistic atlas fusion, and manually corrected large errors in those segmentations. Since this process generated a large training dataset with noisy segmentations, we developed a novel label smoothing procedure and a loss function to train a deep learning model with smoothed noisy segmentations. Our proposed methods properly account for the uncertainty in tissue boundaries. We evaluated our method on 23 manually-segmented test images of a separate set of fetuses. Results show that our method achieves an average Dice similarity coefficient of 0.893 and 0.916 for the transient structures of younger and older fetuses, respectively. Our method generated results that were significantly more accurate than several state-of-the-art methods including nnU-Net that achieved the closest results to our method. Our trained model can serve as a valuable tool to enhance the accuracy and reproducibility of fetal brain analysis in MRI.

Abnormal development of transient fetal zones in mild isolated fetal ventriculomegaly.

Mild isolated fetal ventriculomegaly (iFVM) is the most common abnormality of the fetal central nervous system. It is characterized by enlargement of one or both of the lateral ventricles (defined as ventricular width greater than 10 mm, but less than 12 mm). Despite its high prevalence, the pathophysiology of iFVM during fetal brain development and the neurobiological substrate beyond ventricular enlargement remain unexplored. In this work, we aimed to establish the relationships between the structural development of transient fetal brain zones/compartments and increased cerebrospinal fluid volume. For this purpose, we used in vivo structural T2-weighted magnetic resonance imaging of 89 fetuses (48 controls and 41 cases with iFVM). Our results indicate abnormal development of transient zones/compartments belonging to both hemispheres (i.e. on the side with and also on the contralateral side without a dilated ventricle) in fetuses with iFVM. Specifically, compared to controls, we observed enlargement of proliferative zones and overgrowth of the cortical plate in iFVM with associated reduction of volumes of central structures, subplate, and fetal white matter. These results indicate that enlarged lateral ventricles might be linked to the development of transient fetal zones and that global brain development should be taken into consideration when evaluating iFVM.

Sleep Patterns in Young Children with Congenital Heart Disease.

Sleep patterns of 419 toddlers with congenital heart disease were comparable with the normative population except for increased likelihood across the cohort of sleeping in parents' room and increased disrupted sleep in children aged 18-23 months. Disrupted sleep patterns were associated with lower maternal education and increased medical complexity.

Maternal Social Risk, Gestational Age at Delivery, and Cognitive Outcomes among Adolescents Born Extremely Preterm.

Background: Children born extremely preterm (EP) are at increased risk of cognitive deficits that persist into adulthood. Few large cohort studies have examined differential impairment of cognitive function in EP-born adolescents in relation to early life risk factors, including maternal social disadvantage, gestational age at delivery, and neonatal morbidities prevalent among EP neonates. Objectives: To assess cognitive abilities in relation to early life risk factors in an EP-born cohort at 15 years of age. Methods: 681 of 1198 surviving participants (57%) enrolled from 2002 to 2004 in the Extremely Low Gestational Age Newborn Study returned at age 15 years for an assessment of cognitive abilities with the Wechsler Abbreviated Scale of Intelligence-II and the NIH Toolbox Cognition Battery (NTCB) verbal cognition and fluid processing composites, the latter of which measured executive functions and processing speed. Three cognitive outcomes, WASI-II IQ, NTCB verbal cognition, and NTCB fluid processing, were analyzed for associations with maternal social disadvantage and gestational age. Mediation of maternal social disadvantage by gestational age and mediation of gestational age by neonatal morbidities were also examined. Results: Test scores were lower for NTCB fluid processing relative to IQ and NTCB verbal abilities. Social disadvantage and gestational age were associated with all three cognitive outcomes. Mediation analyses indicated partial mediation of gestational age associations with all three outcomes by neonatal morbidities but did not support mediation by gestational age of social risk associations with cognitive outcomes. Conclusions: Greater maternal social disadvantage and lower gestational age are associated with less favorable cognitive outcomes among EP-born adolescents at 15 years of age. Neonatal morbidities partially mediate associations between lower gestational age and cognitive outcomes. These findings highlight the need for improved medical and remedial interventions to mitigate risk of poor cognitive outcomes among EP-born adolescents.

Quantification of sulcal emergence timing and its variability in early fetal life: Hemispheric asymmetry and sex difference.

Human fetal brains show regionally different temporal patterns of sulcal emergence following a regular timeline, which may be associated with spatiotemporal patterns of gene expression among cortical regions. This study aims to quantify the timing of sulcal emergence and its temporal variability across typically developing fetuses by fitting a logistic curve to presence or absence of sulcus. We found that the sulcal emergence started from the central to the temporo-parieto-occipital lobes and frontal lobe, and the temporal variability of emergence in most of the sulci was similar between 1 and 2 weeks. Small variability (< 1 week) was found in the left central and postcentral sulci and larger variability (>2 weeks) was shown in the bilateral occipitotemporal and left superior temporal sulci. The temporal variability showed a positive correlation with the emergence timing that may be associated with differential contributions between genetic and environmental factors. Our statistical analysis revealed that the right superior temporal sulcus emerged earlier than the left. Female fetuses showed a trend of earlier sulcal emergence in the right superior temporal sulcus, lower temporal variability in the right intraparietal sulcus, and higher variability in the right precentral sulcus compared to male fetuses. Our quantitative and statistical approach quantified the temporal patterns of sulcal emergence in detail that can be a reference for assessing the normality of developing fetal gyrification.

Neurodevelopmental and Mental Health Outcomes in Patients With Fontan Circulation: A State-of-the-Art Review.

Children, adolescents and adults living with Fontan circulation face numerous neurological and developmental challenges. As the population with complex CHD increases thanks to outstanding improvement in medical and surgical care, the long-term developmental and mental health sequelae have become a public health priority in pediatric and congenital cardiology. Many patients with a Fontan circulation experience difficulty in areas of cognition related to attention and executive functioning, visual spatial reasoning and psychosocial development. They are also at high risk for mental health morbidities, particularly anxiety disorders and depression. Several hemodynamic risk factors, beginning during the fetal period, may influence outcomes and yield to abnormal brain growth and development. Brain injury such as white matter lesions, stroke or hemorrhage can occur before, during, or after surgery. Other sociodemographic and surgical risk factors such as multiple catheterizations and surgeries and prolonged hospital stay play a detrimental role in patients' neurodevelopmental prognosis. Prevention and intervention to optimize long-term outcomes are critical in the care of this vulnerable population with complex CHD.

Fetal Brain Volume Predicts Neurodevelopment in Congenital Heart Disease.

BACKGROUND: Neurodevelopmental impairment is common in children with congenital heart disease (CHD), but postnatal variables explain only 30% of the variance in outcomes. To explore whether the antecedents for neurodevelopmental disabilities might begin in utero, we analyzed whether fetal brain volume predicted subsequent neurodevelopmental outcome in children with CHD. METHODS: Fetuses with isolated CHD and sociodemographically comparable healthy control fetuses underwent fetal brain magnetic resonance imaging and 2-year neurodevelopmental evaluation with the Bayley Scales of Infant and Toddler Development, Third Edition (Bayley-III) and the Adaptive Behavior Assessment System, Third Edition (ABAS-3). Hierarchical regression evaluated potential predictors of Bayley-III and ABAS-3 outcomes in the CHD group, including fetal total brain volume adjusted for gestational age and sex, sociodemographic characteristics, birth measures, and medical history. RESULTS: The CHD group (n=52) had lower Bayley-III cognitive, language, and motor scores than the control group (n=26), but fetal brain volumes were similar. Within the CHD group, larger fetal total brain volume correlated with higher Bayley-III cognitive, language, and motor scores and ABAS-3 adaptive functioning scores (r=0.32-0.47; all P<0.05), but this was not noted in the control group. Fetal brain volume predicted 10% to 21% of the variance in neurodevelopmental outcome measures in univariate analyses. Multivariable models that also included social class and postnatal factors explained 18% to 45% of the variance in outcome, depending on developmental domain. Moreover, in final multivariable models, fetal brain volume was the most consistent predictor of neurodevelopmental outcome across domains. CONCLUSIONS: Small fetal brain volume is a strong independent predictor of 2-year neurodevelopmental outcomes and may be an important imaging biomarker of future neurodevelopmental risk in CHD. Future studies are needed to support this hypothesis. Our findings support inclusion of fetal brain volume in risk stratification models and as a possible outcome in fetal neuroprotective intervention studies.

Neurological features in infants with congenital heart disease.

AIM: To report neurological examination findings at 5 to 12 months of age in infants with congenital heart disease (CHD) and to identify predictors of abnormal neurological examination. METHOD: This retrospective observational study included infants who required cardiac surgery at less than 3 months of age and underwent a standard neurological examination from a neurologist in the cardiac neurodevelopmental outpatient clinic between age 5 months and 12 months. Predictors for abnormal neurological examination (concerns on structured developmental history, demographic factors, medical history, and newborn neurodevelopmental assessment) were considered for multivariate regression. RESULTS: The sample included 127 infants (mean age 7mo 2wks), who underwent first cardiac surgery at 7 days (4-49 interquartile range [IQR]) of age and were seen for a neurological examination in the cardiac neurodevelopmental clinic. Neurological abnormalities were common; 88% of infants had an abnormal neurological examination in at least one domain assessed. The most common abnormalities were abnormal axial (48%) and extremity (44%) tone, mostly hypotonia. Abnormal neurological examination was associated with concerns on the concurrent structured developmental history, genetic condition, extracardiac anomaly, longer length of stay, more than one cardiac surgery, ongoing early intervention services, and abnormalities on newborn neurodevelopmental assessment. INTERPRETATION: Neurological examination abnormalities are common in infants with CHD after infant heart surgery, supporting the need for early and ongoing therapeutic developmental services and adherence to American Heart Association recommendations for developmental follow-up for children with CHD. What this paper adds Neurological examination abnormalities are common in infants who undergo open-heart surgery. Medical complications in infancy increase risk for neurological abnormalities. Family-reported concerns on structured developmental history may predict abnormal neurological examination at 5 to 12 months of age. Abnormal newborn neurodevelopmental assessment may predict abnormal neurological examination at 5 to 12 months of age.

Optimal Method for Fetal Brain Age Prediction Using Multiplanar Slices From Structural Magnetic Resonance Imaging.

The accurate prediction of fetal brain age using magnetic resonance imaging (MRI) may contribute to the identification of brain abnormalities and the risk of adverse developmental outcomes. This study aimed to propose a method for predicting fetal brain age using MRIs from 220 healthy fetuses between 15.9 and 38.7 weeks of gestational age (GA). We built a 2D single-channel convolutional neural network (CNN) with multiplanar MRI slices in different orthogonal planes without correction for interslice motion. In each fetus, multiple age predictions from different slices were generated, and the brain age was obtained using the mode that determined the most frequent value among the multiple predictions from the 2D single-channel CNN. We obtained a mean absolute error (MAE) of 0.125 weeks (0.875 days) between the GA and brain age across the fetuses. The use of multiplanar slices achieved significantly lower prediction error and its variance than the use of a single slice and a single MRI stack. Our 2D single-channel CNN with multiplanar slices yielded a significantly lower stack-wise MAE (0.304 weeks) than the 2D multi-channel (MAE = 0.979, p < 0.001) and 3D (MAE = 1.114, p < 0.001) CNNs. The saliency maps from our method indicated that the anatomical information describing the cortex and ventricles was the primary contributor to brain age prediction. With the application of the proposed method to external MRIs from 21 healthy fetuses, we obtained an MAE of 0.508 weeks. Based on the external MRIs, we found that the stack-wise MAE of the 2D single-channel CNN (0.743 weeks) was significantly lower than those of the 2D multi-channel (1.466 weeks, p < 0.001) and 3D (1.241 weeks, p < 0.001) CNNs. These results demonstrate that our method with multiplanar slices accurately predicts fetal brain age without the need for increased dimensionality or complex MRI preprocessing steps.

Abnormal Right-Hemispheric Sulcal Patterns Correlate with Executive Function in Adolescents with Tetralogy of Fallot.

Neurodevelopmental disabilities are the most common noncardiac conditions in patients with congenital heart disease (CHD). Executive function skills have been frequently observed to be decreased among children and adults with CHD compared with peers, but a neuroanatomical basis for the association is yet to be identified. In this study, we quantified sulcal pattern features from brain magnetic resonance imaging data obtained during adolescence among 41 participants with tetralogy of Fallot (ToF) and 49 control participants using a graph-based pattern analysis technique. Among patients with ToF, right-hemispheric sulcal pattern similarity to the control group was decreased (0.7514 vs. 0.7553, P = 0.01) and positively correlated with neuropsychological testing values including executive function (r = 0.48, P < 0.001). Together these findings suggest that sulcal pattern analysis may be a useful marker of neurodevelopmental risk in patients with CHD. Further studies may elucidate the mechanisms leading to different alterations in sulcal patterning.

Association between Quantitative MR Markers of Cortical Evolving Organization and Gene Expression during Human Prenatal Brain Development.

The relationship between structural changes of the cerebral cortex revealed by Magnetic Resonance Imaging (MRI) and gene expression in the human fetal brain has not been explored. In this study, we aimed to test the hypothesis that relative regional thickness (a measure of cortical evolving organization) of fetal cortical compartments (cortical plate [CP] and subplate [SP]) is associated with expression levels of genes with known cortical phenotype. Mean regional SP/CP thickness ratios across age measured on in utero MRI of 25 healthy fetuses (20-33 gestational weeks [GWs]) were correlated with publicly available regional gene expression levels (23-24 GW fetuses). Larger SP/CP thickness ratios (more pronounced cortical evolving organization) was found in perisylvian regions. Furthermore, we found a significant association between SP/CP thickness ratio and expression levels of the FLNA gene (mutated in periventricular heterotopia, congenital heart disease, and vascular malformations). Further work is needed to identify early MRI biomarkers of gene expression that lead to abnormal cortical development.

Regional Brain Growth Trajectories in Fetuses with Congenital Heart Disease.

OBJECTIVE: Congenital heart disease (CHD) is associated with abnormal brain development in utero. We applied innovative fetal magnetic resonance imaging (MRI) techniques to determine whether reduced fetal cerebral substrate delivery impacts the brain globally, or in a region-specific pattern. Our novel design included two control groups, one with and the other without a family history of CHD, to explore the contribution of shared genes and/or fetal environment to brain development. METHODS: From 2014 to 2018, we enrolled 179 pregnant women into 4 groups: "HLHS/TGA" fetuses with hypoplastic left heart syndrome (HLHS) or transposition of the great arteries (TGA), diagnoses with lowest fetal cerebral substrate delivery; "CHD-other," with other CHD diagnoses; "CHD-related," healthy with a CHD family history; and "optimal control," healthy without a family history. Two MRIs were obtained between 18 and 40 weeks gestation. Random effect regression models assessed group differences in brain volumes and relationships to hemodynamic variables. RESULTS: HLHS/TGA (n = 24), CHD-other (50), and CHD-related (34) groups each had generally smaller brain volumes than the optimal controls (71). Compared with CHD-related, the HLHS/TGA group had smaller subplate (-13.3% [standard error = 4.3%], p < 0.01) and intermediate (-13.7% [4.3%], p < 0.01) zones, with a similar trend in ventricular zone (-7.1% [1.9%], p = 0.07). These volumetric reductions were associated with lower cerebral substrate delivery. INTERPRETATION: Fetuses with CHD, especially those with lowest cerebral substrate delivery, show a region-specific pattern of small brain volumes and impaired brain growth before 32 weeks gestation. The brains of fetuses with CHD were more similar to those of CHD-related than optimal controls, suggesting genetic or environmental factors also contribute. ANN NEUROL 2021;89:143-157.

A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI.

Fetal cortical plate segmentation is essential in quantitative analysis of fetal brain maturation and cortical folding. Manual segmentation of the cortical plate, or manual refinement of automatic segmentations is tedious and time-consuming. Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation. To reduce the burden of manual refinement of segmentations, we have developed a new and powerful deep learning segmentation method. Our method exploits new deep attentive modules with mixed kernel convolutions within a fully convolutional neural network architecture that utilizes deep supervision and residual connections. We evaluated our method quantitatively based on several performance measures and expert evaluations. Results show that our method outperforms several state-of-the-art deep models for segmentation, as well as a state-of-the-art multi-atlas segmentation technique. We achieved average Dice similarity coefficient of 0.87, average Hausdorff distance of 0.96 mm, and average symmetric surface difference of 0.28 mm on reconstructed fetal brain MRI scans of fetuses scanned in the gestational age range of 16 to 39 weeks (28.6± 5.3). With a computation time of less than 1 minute per fetal brain, our method can facilitate and accelerate large-scale studies on normal and altered fetal brain cortical maturation and folding.

Fetal Cortical Plate Segmentation Using Fully Convolutional Networks With Multiple Plane Aggregation.

Fetal magnetic resonance imaging (MRI) has the potential to advance our understanding of human brain development by providing quantitative information of cortical plate (CP) development in vivo. However, for a reliable quantitative analysis of cortical volume and sulcal folding, accurate and automated segmentation of the CP is crucial. In this study, we propose a fully convolutional neural network for the automatic segmentation of the CP. We developed a novel hybrid loss function to improve the segmentation accuracy and adopted multi-view (axial, coronal, and sagittal) aggregation with a test-time augmentation method to reduce errors using three-dimensional (3D) information and multiple predictions. We evaluated our proposed method using the ten-fold cross-validation of 52 fetal brain MR images (22.9-31.4 weeks of gestation). The proposed method obtained Dice coefficients of 0.907 ± 0.027 and 0.906 ± 0.031 as well as a mean surface distance error of 0.182 ± 0.058 mm and 0.185 ± 0.069 mm for the left and right, respectively. In addition, the left and right CP volumes, surface area, and global mean curvature generated by automatic segmentation showed a high correlation with the values generated by manual segmentation (R 2 > 0.941). We also demonstrated that the proposed hybrid loss function and the combination of multi-view aggregation and test-time augmentation significantly improved the CP segmentation accuracy. Our proposed segmentation method will be useful for the automatic and reliable quantification of the cortical structure in the fetal brain.