SUMMARY: Intracranial vessel wall MR imaging is an adjunct to conventional angiographic imaging with CTA, MRA, or DSA. The technique has multiple potential uses in the context of ischemic stroke and intracranial hemorrhage. There remain gaps in our understanding of intracranial vessel wall MR imaging findings and research is ongoing, but the technique is already used on a clinical basis at many centers. This article, on behalf of the Vessel Wall Imaging Study Group of the American Society of Neuroradiology, provides expert consensus recommendations for current clinical practice.

We present a case of focal cerebral arteriopathy and ischemic stroke in a pediatric patient with coronavirus disease 2019 who presented with seizure, right hemiparesis, and dysarthria with positive findings for severe acute respiratory syndrome coronavirus 2 from nasopharyngeal swab and cerebral spinal fluid.

BACKGROUND AND PURPOSE: Tumor segmentation is essential in surgical and treatment planning and response assessment and monitoring in pediatric brain tumors, the leading cause of cancer-related death among children. However, manual segmentation is time-consuming and has high interoperator variability, underscoring the need for more efficient methods. After training, we compared 2 deep-learning-based 3D segmentation models, DeepMedic and nnU-Net, with pediatric-specific multi-institutional brain tumor data based on multiparametric MR images. MATERIALS AND METHODS: Multiparametric preoperative MR imaging scans of 339 pediatric patients (n = 293 internal and n = 46 external cohorts) with a variety of tumor subtypes were preprocessed and manually segmented into 4 tumor subregions, ie, enhancing tumor, nonenhancing tumor, cystic components, and peritumoral edema. After training, performances of the 2 models on internal and external test sets were evaluated with reference to ground truth manual segmentations. Additionally, concordance was assessed by comparing the volume of the subregions as a percentage of the whole tumor between model predictions and ground truth segmentations using the Pearson or Spearman correlation coefficients and the Bland-Altman method. RESULTS: The mean Dice score for nnU-Net internal test set was 0.9 (SD, 0.07) (median, 0.94) for whole tumor; 0.77 (SD, 0.29) for enhancing tumor; 0.66 (SD, 0.32) for nonenhancing tumor; 0.71 (SD, 0.33) for cystic components, and 0.71 (SD, 0.40) for peritumoral edema, respectively. For DeepMedic, the mean Dice scores were 0.82 (SD, 0.16) for whole tumor; 0.66 (SD, 0.32) for enhancing tumor; 0.48 (SD, 0.27) for nonenhancing tumor; 0.48 (SD, 0.36) for cystic components, and 0.19 (SD, 0.33) for peritumoral edema, respectively. Dice scores were significantly higher for nnU-Net (P ≤ .01). Correlation coefficients for tumor subregion percentage volumes were higher (0.98 versus 0.91 for enhancing tumor, 0.97 versus 0.75 for nonenhancing tumor, 0.98 versus 0.80 for cystic components, 0.95 versus 0.33 for peritumoral edema in the internal test set). Bland-Altman plots were better for nnU-Net compared with DeepMedic. External validation of the trained nnU-Net model on the multi-institutional Brain Tumor Segmentation Challenge in Pediatrics (BraTS-PEDs) 2023 data set revealed high generalization capability in the segmentation of whole tumor, tumor core (a combination of enhancing tumor, nonenhancing tumor, and cystic components), and enhancing tumor with mean Dice scores of 0.87 (SD, 0.13) (median, 0.91), 0.83 (SD, 0.18) (median, 0.89), and 0.48 (SD, 0.38) (median, 0.58), respectively. CONCLUSIONS: The pediatric-specific data-trained nnU-Net model is superior to DeepMedic for whole tumor and subregion segmentation of pediatric brain tumors.

Schizencephaly is a rare malformation of the brain characterized by a gray matter-lined defect extending from the pial surface to the lateral ventricles. The purpose of this study was to correlate imaging findings of schizencephaly and associated anomalies on fetal and postnatal MR imaging and assess possible changes that may occur from the prenatal-to-postnatal state. A retrospective review of subjects with schizencephaly who had both pre- and postnatal MR imaging was performed. Subject age, cleft type, number, location, and features of the defects and associated anomalies were recorded. Normalized dimensions of the defect and ipsilateral ventricle were measured and correlated to changes in the clefts between pre- and postnatal imaging. Ten subjects with 18 clefts (8 bilateral) were included. Most defects (83%) were open on prenatal MR imaging, but 47% of those were found to have subsequently closed on postnatal imaging. Evidence of prior hemorrhage was seen in 83%. Prenatal MR imaging detected all cases of an absent septum pellucidum but detected a fraction of gross polymicrogyria and missed all cases of optic nerve hypoplasia. The normalized ipsilateral ventricular and inner and middle width dimensions of the defects were significantly decreased at postnatal imaging (P < .05). The widths of the defects, ventricular width, and presence of hemorrhage were not predictors of closure of prenatally diagnosed open defects (P > .05). In our series, nearly half of prenatally open schizencephaly defects had closed on postnatal imaging. Prenatal MR imaging was only able to demonstrate some of the associated anomalies.