A Case Report on Radiation-Induced Cerebral Vasculopathy in a Long-Term Survivor of Childhood Medulloblastoma.

This case report discusses a patient diagnosed with radiation-induced cerebral vasculopathy who presented after cerebral irradiation of metastatic medulloblastoma to raise awareness of radiation-induced cerebral vasculopathy. Because radiation therapy has revolutionized treatment for children with brain cancers, radiation-induced vasculopathy is becoming ever more prominent, and its recognition is crucial to implementing early treatment strategies to improve patient outcomes. Currently, medical management is poorly defined, largely unexamined, and poorly studied. Because the clinical features of this disease are nonspecific, radiation-induced cerebral vasculopathy remains a diagnosis of exclusion and an essential addition to the differential diagnosis. Discussion regarding standardized treatment, screening, and guidelines is necessary to improve treatment and survival.

An international study presenting a federated learning AI platform for pediatric brain tumors.

While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

A devastating case of a Balamuthia mandrillaris pediatric brain infection.

Balamuthia mandrillaris is an amoeba that causes an uncommon but deadly encephalitis, referred to as granulomatous amoebic encephalitis (GAE). The highest incidence reported worldwide has occurred in America, and within the United States, it has been highest in the Southwest affecting predominantly children and young men of Hispanic ethnicity. Clinical presentation of GAE includes fever, headache, nausea, vomiting, lethargy, irritability, stiff neck, hallucinations, photophobia, and seizures. Our patient was a Hispanic male child living in Arizona. The patient presented at 3 years of age for severe encephalitis. Symptoms included difficulty with balance, gait, and sitting up and seizure-like activity. Initial CT showed an area of decreased density consistent with edema in the right frontal and left frontoparietal lobes. Rapid progression was seen on further imaging over the length of the patient's hospital stay revealing diffusion restriction, necrosis/blood products, edema, and hemorrhage. The patient expired three weeks after onset of symptoms and one week after admission to our institution. While there are multiple biochemical techniques that can test for B. mandrillaris, they are rarely employed for multiple reasons stemming from the rare occurrence of this infection. Because of the fatal nature of this infection, we propose (1) testing should be considered if a patient presents with progressing encephalitis on imaging and other pathogenic etiologies are ruled out and (2) the threshold to treat empirically should be low due to the fatal nature of the infection.

The Pediatric Neuroradiologist's Practical Guide to Capture and Evaluate Pre- and Postoperative Velopharyngeal Insufficiency.

Up to 30% of children with cleft palate will develop a severe speech disorder known as velopharyngeal insufficiency. Management of velopharyngeal insufficiency typically involves structural and functional assessment of the velum and pharynx by endoscopy and/or videofluoroscopy. These methods cannot provide direct evaluation of underlying velopharyngeal musculature. MR imaging offers an ideal imaging method, providing noninvasive, high-contrast, high-resolution imaging of soft-tissue anatomy. Furthermore, focused-speech MR imaging techniques can evaluate the function of the velum and pharynx during sustained speech production, providing critical physiologic information that supplements anatomic findings. The use of MR imaging for velopharyngeal evaluation is relatively novel, with limited literature describing its use in clinical radiology. Here we provide a practical approach to perform and interpret velopharyngeal MR imaging examinations. This article discusses the velopharyngeal MR imaging protocol, methods for interpreting velopharyngeal anatomy, and examples illustrating its clinical applications. This knowledge will provide radiologists with a new, noninvasive tool to offer to referring specialists.