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.

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.

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.

Down syndrome (DS) is the most common genetic cause of developmental disabilities. Advanced analysis of brain magnetic resonance imaging (MRI) has been used to find brain abnormalities and their relationship to neurocognitive impairments in children and adolescents with DS. Because genetic factors affect brain development in early fetal life, there is a growing interest in analyzing brains from living fetuses with DS. In this study, we investigated regional sulcal folding depth as well as global cortical gyrification from fetal brain MRIs. Nine fetuses with DS (29.1 ± 4.24 gestational weeks [mean ± standard deviation]) were compared with 17 typically developing [TD] fetuses (28.4 ± 3.44). Fetuses with DS showed lower whole-brain average sulcal depths and gyrification index than TD fetuses. Significant decreases in sulcal depth were found in bilateral Sylvian fissures and right central and parieto-occipital sulci. On the other hand, significantly increased sulcal depth was shown in the left superior temporal sulcus, which is related to atypical hemispheric asymmetry of cortical folding. Moreover, these group differences increased as gestation progressed. This study demonstrates that regional sulcal depth is a sensitive marker for detecting alterations of cortical development in DS during fetal life, which may be associated with later neurocognitive impairment.

Intergenerational effects are described as the genetic, epigenetic, as well as pre- and postnatal environmental influence parents have on their offspring's behavior, cognition, and brain. During fetal brain development, the primary cortical sulci emerge with a distinctive folding pattern that are under strong genetic influence and show little change of this pattern throughout postnatal brain development. We examined intergenerational transmission of cortical sulcal patterns by comparing primary sulcal patterns between children (N = 16, age 5.5 ± 0.81 years, 8 males) and their biological mothers (N = 15, age 39.72 ± 4.68 years) as well as between children and unrelated adult females. Our graph-based sulcal pattern comparison method detected stronger sulcal pattern similarity for child-mother pairs than child-unrelated pairs, where higher similarity between child-mother pairs was observed mostly for the right lobar regions. Our results also show that child-mother versus child-unrelated pairs differ for daughters and sons with a trend toward significance, particularly for the left hemisphere lobar regions. This is the first study to reveal significant intergenerational transmission of cortical sulcal patterns, and our results have important implications for the study of the heritability of complex behaviors, brain-based disorders, the identification of biomarkers, and targets for interventions.

Background Children operated on for a simple congenital heart defect (CHD) are at risk of neurodevelopmental abnormalities. Abnormal cortical development and folding have been observed in fetuses with CHD. We examined whether sulcal folding patterns in adults operated on for simple CHD in childhood differ from those of healthy controls, and whether such differences are associated with neuropsychological outcomes. Methods and Results Patients (mean age, 24.5 years) who underwent childhood surgery for isolated atrial septal defect (ASD; n=33) or ventricular septal defect (VSD; n=30) and healthy controls (n=37) were enrolled. Sulcal pattern similarity to healthy controls was determined using magnetic resonance imaging and looking at features of sulcal folds, their intersulcal relationships, and sulcal graph topology. The sulcal pattern similarity values were tested for associations with comprehensive neuropsychological scores. Patients with both ASD and VSD had decreased sulcal pattern similarity in the left hemisphere compared with controls. The differences were found in the left temporal lobe in the ASD group and in the whole left hemisphere in the VSD group (=0.033 and =0.039, respectively). The extent of abnormal left hemispheric sulcal pattern similarity was associated with worse neuropsychological scores (intelligence, executive function, and visuospatial abilities) in the VSD group, and special educational support in the ASD group. Conclusions Adults who underwent surgery for simple CHD in childhood display altered left hemisphere sulcal folding patterns, commensurate with neuropsychological scores for patients with VSD and special educational support for ASD. This may indicate that simple CHD affects early brain development. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT03871881.

Magnetic resonance imaging (MRI) is widely used during the fetal period when fetal abnormalities are identified, or diagnostic doubts remain after prenatal ultrasonography. In vivo fetal MRI can improve the diagnostic accuracy for fetal brain abnormalities, leading to better prenatal counseling and clinical management. MRI of the fetus in utero may be one of the most difficult imaging due to nonpredictable fetal motion, small brain size, and low tissue contrast. Especially, fetal motion disrupts the spatial encoding needed for 3D image acquisition. Therefore, fast structural fetal MRI has been performed using a single-shot fast spin echo T2-weighted sequence and inter-slice motion correction methods have been developed. In vivo diffusion-weighted and functional MRI are also used with the fetal motion correction for quantitative microstructural evaluation and examination of structural and functional connectivity development in the fetal brain. Recently, advanced fetal MRI analysis techniques have been proposed, which enable the quantitative assessment of brain volumetric growth; cortical surface areal growth and folding; global sulcal folding pattern; tissue microstructure; white matter structural connectivity; and functional connectivity and networks in healthy fetuses and fetuses with developmental brain disorders. Prior in vivo fetal MRI studies show great potential to not only help us better understand normal and abnormal brain development but also improve the management of high-risk pregnancies and the diagnosis and treatment of congenital anomalies. For future works, it is needed to improve the spatial resolution and contrast of fetal MRI, decrease its sensitivity to motion, reduce the total acquisition time, and develop more advanced image processing and analysis technologies.

Human cerebral cortex shows the dramatic areal expansion and folding during fetal life with the most prominent and dynamic genetic regulation. The position of early sulcal folds appears to be associated with cortical functional areas predetermined from genetic protomap, and specific patterns of sulcal folding have been hypothesized to relate to optimal organization and arrangement of the functional areas and their white matter connections. As primary sulcal folding pattern is prenatally determined and neurodevelopmental disabilities associated with abnormal pattern may have a prenatal origin, it is needed to develop and use in vivo fetal brain MRI analysis techniques to provide a predictive model of postnatal brain development and neurodevelopmental disability risk from early fetal life. Recent advances in fetal MRI analysis allow us to quantify and characterize normal and abnormal sulcal development and detect early-emerging subtle abnormalities in cortical sulcal pattern in several brain developmental disorders.

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 . 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 ( > 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.

Sulcal pits are thought to represent the first cortical folds of primary sulci during neurodevelopment. The uniform spatial distribution of sulcal pits across individuals is hypothesized to be predetermined by a human-specific protomap which is related to functional localization under genetic controls in early fetal life. Thus, it is important to characterize temporal and spatial patterns of sulcal pits in the fetal brain that would provide additional information of functional development of the human brain and crucial insights into abnormal cortical maturation. In this paper, we investigated temporal patterns of emergence and spatial distribution of sulcal pits using 48 typically developing fetal brains in the second half of gestation. We found that the position and spatial variance of sulcal pits in the fetal brain are similar to those in the adult brain, and they are also temporally uniform against dynamic brain growth during fetal life. Furthermore, timing of pit emergence shows a regionally diverse pattern that may be associated with the subdivisions of the protomap. Our findings suggest that sulcal pits in the fetal brain are useful anatomical landmarks containing detailed information of functional localization in early cortical development and maintaining their spatial distribution throughout the human lifetime.