Background: Meningiomas are the most commonly occurring benign intracranial tumors. When presenting with peritumoral brain edema (PTBE), surgical treatment can lead to patient morbidity. This retrospective case series aims to describe the conservative medical management of moderate to large meningiomas with large PTBE. Methods: Patients with suspected meningiomas greater than 2.0cm and edema index greater than 2.0 were identified by screening 3345 MRI scans between 2012-2017. Imaging analysis included MR imaging features of suspected meningiomas and clinical data was gathered from the electronic patient record (patient age, sex, patient symptoms, follow-up duration, and follow-up symptoms). Results: We report on 31 patients who received conservative medical management. Presenting complaints included headache, seizure, weakness; many presented asymptomatically. The average follow-up time was 3.96 years. At the final follow-up appointment, 19 (61%) patients were asymptomatic. Among symptomatic patients, seizures were the most common complaint. There was no mortality reported in our cohort and the average tumor progression was 7.04cm3/year. Conclusions: In this retrospective report of meningioma patients with high edema index, we found that most patients remained asymptomatic or had stable symptoms after at least 1-yr follow up after medical treatment. This study provides insight around the surgical decision-making for meningiomas with large spread of edema.

This study evaluated automated machine learning (AutoML) in classifying the presence or absence of hemoperitoneum in ultrasonography (USG) images of Morrison’s pouch. In this multicenter, retrospective study, 864 trauma patients from trauma and emergency medical centers in South Korea were included. In all, 2200 USG images (1100 hemoperitoneum and 1100 normal) were collected. Of these, 1800 images were used for training and 200 were used for the internal validation of AutoML. External validation was performed using 100 hemoperitoneum images and 100 normal images collected separately from a trauma center that were not included in the training and internal validation sets. Google’s open-source AutoML was used to train the algorithm in classifying hemoperitoneum in USG images, followed by internal and external validation. In the internal validation, the sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve were 95%, 99%, and 0.97, respectively. In the external validation, the sensitivity, specificity, and AUROC were 94%, 99%, and 0.97, respectively. The performances of AutoML in the internal and external validation were not statistically different (p = 0.78). A publicly available, general-purpose AutoML can accurately classify the presence or absence of hemoperitoneum in USG images of the Morrison’s pouch of real-world trauma patients.