Altered brain structure in preschool-aged children with tetralogy of Fallot.

BACKGROUND: Neurodevelopmental abnormalities are prevalent in children with tetralogy of Fallot. Our aim was to investigate the structural brain alterations of preschool-aged children with tetralogy of Fallot and its correlation with neurodevelopmental outcome. METHODS: T1-weighted structural images were obtained from 25 children with tetralogy of Fallot who had undergone cardiopulmonary bypass surgery and from 24 normal controls. Cortical morphological indices including gray matter volume, cortical thickness, sulcal depth, gyrification, and cortical surface complexity were compared between the two groups. Neurodevelopmental assessments of the children with tetralogy of Fallot were performed with the Wechsler Preschool and Primary Scale of Intelligence. RESULTS: Cortical morphological differences between groups were distributed throughout the right caudal middle frontal gyrus, right fusiform gyrus, right lateral occipital gyrus, right precuneus, and left inferior parietal lobule. Among children with tetralogy of Fallot, altered cortical structures were correlated with the visual spatial index, working memory index, and perioperative variables. CONCLUSION: Our results suggested that abnormal cortical structure in preschool-aged children with tetralogy of Fallot may be the persistent consequence of delayed cortical development in fetuses and cortical morphology can be used as an early potential biomarker to capture regional brain abnormalities that are relevant to neurodevelopmental outcomes. IMPACT: Altered cortical structures in preschool-aged children with ToF were correlated with both neurodevelopmental outcomes and clinical risk factors. Cortical morphology can be used as an effective tool to evaluate neuroanatomical changes and detect underlying neural mechanisms in ToF patients. Abnormal cortical structure may be the continuous consequence of delayed fetal brain development in children with ToF.

Aberrant White Matter Organization Correlated With Neurodevelopment Outcomes in Tetralogy of Fallot: An Atlas-Based Diffusion Tensor Imaging Study.

BACKGROUND: White matter injury (WMI) and impaired neurodevelopment are common in children with congenital heart disease. However, the effect of WMI on neurodevelopmental outcomes is still rarely reported. In this study, we aimed to investigate microstructural changes in white matter (WM) and its relationship with neurodevelopmental outcomes and further explore the underlying neurophysiological mechanisms of neurocognitive impairments in the tetralogy of Fallot (ToF). METHOD: Diffusion tensor imaging (DTI) data were acquired in preschool-aged children with ToF (n = 29) and normal controls (NC, n = 19), and neurodevelopmental assessments were performed with the Wechsler Preschool and Primary Scale of Intelligence in ToF. The differences in DTI metrics including fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity were evaluated between ToF and NC. Correlations between WM microstructural changes and neurodevelopmental outcomes were further analyzed. RESULTS: Significant WM differences were found in the uncinate fasciculus, cingulum hippocampus, superior longitudinal fasciculus, and corticospinal tract between children with ToF and NC. Impaired WM integrity was correlated with the verbal comprehension index and working memory index in ToF. CONCLUSIONS: This study demonstrated WM microstructure injury, and this injury is related to worse language and working memory performance in preschool-aged children with ToF. These findings suggested that DTI metrics may be a potential biomarker of neurocognitive impairments in ToF and can be used to predict future neurodevelopmental outcomes, which also provide new insights into the underlying neurophysiological mechanisms of neurocognitive impairments in ToF.

Brain Age Prediction of Children Using Routine Brain MR Images via Deep Learning.

Predicting brain age of children accurately and quantitatively can give help in brain development analysis and brain disease diagnosis. Traditional methods to estimate brain age based on 3D magnetic resonance (MR), T1 weighted imaging (T1WI), and diffusion tensor imaging (DTI) need complex preprocessing and extra scanning time, decreasing clinical practice, especially in children. This research aims at proposing an end-to-end AI system based on deep learning to predict the brain age based on routine brain MR imaging. We spent over 5 years enrolling 220 stacked 2D routine clinical brain MR T1-weighted images of healthy children aged 0 to 5 years old and randomly divided those images into training data including 176 subjects and test data including 44 subjects. Data augmentation technology, which includes scaling, image rotation, translation, and gamma correction, was employed to extend the training data. A 10-layer 3D convolutional neural network (CNN) was designed for predicting the brain age of children and it achieved reliable and accurate results on test data with a mean absolute deviation (MAE) of 67.6 days, a root mean squared error (RMSE) of 96.1 days, a mean relative error (MRE) of 8.2%, a correlation coefficient (R) of 0.985, and a coefficient of determination (R 2) of 0.971. Specially, the performance on predicting the age of children under 2 years old with a MAE of 28.9 days, a RMSE of 37.0 days, a MRE of 7.8%, a R of 0.983, and a R 2 of 0.967 is much better than that over 2 with a MAE of 110.0 days, a RMSE of 133.5 days, a MRE of 8.2%, a R of 0.883, and a R 2 of 0.780.