With postnatal MR imaging as reference, retrospective consensus review of fetal MR images by pediatric neuroradiologists had sensitivity of 85% for polymicrogyria, 100% for schizencephaly, and 67% ... PurposeTo determine the diagnostic accuracy of fetal magnetic resonance (MR) imaging for malformations of cortical development by using postnatal MR imaging as reference standard.Materials and Meth...

The hippocampal formation plays an important role in learning and memory; however, data on its development in utero in humans are limited. This study was performed to evaluate hippocampal development in healthy fetuses using 3D reconstructed MRI. A cohort of 20 healthy pregnant women underwent prenatal MRI at a median GA of 24.9 wk (range, 21.3–31.9 wk); six of the women also had a second fetal MRI performed at a 6-wk interval. Routine 2D ultrafast T2-weighted images were used to reconstruct a 3D volume image, which was then used to manually segment the right and left hippocampi. Total hippocampal volume was calculated for each subject and compared against GA. There was a linear increase in total hippocampal volume with increasing GA (p < 0.001). For subjects scanned twice, there was an increase in hippocampal size on the second fetal MRI (p = 0.0004). This represents the first volumetric study of fetal hippocampal development in vivo. This normative volumetric data will be helpful for future comparison studies of suspected developmental abnormalities of hippocampal structure and function.

A deep learning model that evaluates myelination patterns can predict the gestationally corrected age of neonates and infants on the basis of T1- and T2-weighted MRI scans of the brain. Background Assessment of appropriate brain myelination on T1- and T2-weighted MRI scans is based on gestationally corrected age (GCA) and requires subjective visual inspection of the brain with kno...

BACKGROUND AND PURPOSE: Short-term results demonstrate that prenatal repair of a myelomeningocele is associated with a reduction in hydrocephalus and an increased likelihood of the reversal of Chiari II malformations compared with postnatal repair. The purpose of this study was to identify the long-term imaging findings at school age among subjects who underwent pre- versus postnatal repair of a myelomeningocele. MATERIALS AND METHODS: A subset of subjects enrolled in the Management of Myelomeningocele Study who underwent either prenatal (n = 66) or postnatal (n = 63) repair of a lumbosacral myelomeningocele and had follow-up brain MR imaging at school age were included. The prevalence of posterior fossa features of Chiari II malformation and supratentorial abnormalities and the change in these findings from fetal to school-age MR imaging were compared between the 2 groups. RESULTS: Prenatal repair of a myelomeningocele was associated with higher rates of normal location of fourth ventricle and lower rates of hindbrain herniation, cerebellar herniation, tectal beaking, brainstem distortion, and kinking at school age compared with postnatal repair (all P < .01). Supratentorial abnormalities, including corpus callosal abnormalities, gyral abnormalities, heterotopia, and hemorrhage, were not significantly different between the 2 groups (all P > .05). The rates of resolution of brainstem kinking, tectal beaking, cerebellar and hindbrain herniation, and normalization of fourth ventricle size from fetal to school age MR imaging were higher among the prenatal compared with postnatal surgery group (all, P < .02). CONCLUSIONS: Prenatal repair of a myelomeningocele is associated with persistent improvement in posterior fossa imaging findings of Chiari II malformation at school age compared with postnatal repair.

BACKGROUND AND PURPOSE: Fetal brain MR imaging interpretations are subjective and require subspecialty expertise. We aimed to develop a deep learning algorithm for automatically measuring intracranial and brain volumes of fetal brain MRIs across gestational ages. MATERIALS AND METHODS: This retrospective study included 246 patients with singleton pregnancies at 19–38 weeks gestation. A 3D U-Net was trained to segment the intracranial contents of 2D fetal brain MRIs in the axial, coronal, and sagittal planes. An additional 3D U-Net was trained to segment the brain from the output of the first model. Models were tested on MRIs of 10 patients (28 planes) via Dice coefficients and volume comparison with manual reference segmentations. Trained U-Nets were applied to 200 additional MRIs to develop normative reference intracranial and brain volumes across gestational ages and then to 9 pathologic fetal brains. RESULTS: Fetal intracranial and brain compartments were automatically segmented in a mean of 6.8 (SD, 1.2) seconds with median Dices score of 0.95 and 0.90, respectively (interquartile ranges, 0.91–0.96/0.89–0.91) on the test set. Correlation with manual volume measurements was high (Pearson r = 0.996, P < .001). Normative samples of intracranial and brain volumes across gestational ages were developed. Eight of 9 pathologic fetal intracranial volumes were automatically predicted to be >2 SDs from this age-specific reference mean. There were no effects of fetal sex, maternal diabetes, or maternal age on intracranial or brain volumes across gestational ages. CONCLUSIONS: Deep learning techniques can quickly and accurately quantify intracranial and brain volumes on clinical fetal brain MRIs and identify abnormal volumes on the basis of a normative reference standard.