BACKGROUND AND PURPOSE: B-Raf proto-oncogene, serine/threonine kinase (BRAF) status has important implications for prognosis and therapy of pediatric low-grade gliomas. Currently, BRAF status classification relies on biopsy. Our aim was to train and validate a radiomics approach to predict BRAF fusion and BRAF V600E mutation. MATERIALS AND METHODS: In this bi-institutional retrospective study, FLAIR MR imaging datasets of 115 pediatric patients with low-grade gliomas from 2 children’s hospitals acquired between January 2009 and January 2016 were included and analyzed. Radiomics features were extracted from tumor segmentations, and the predictive model was tested using independent training and testing datasets, with all available tumor types. The model was selected on the basis of a grid search on the number of trees, opting for the best split for a random forest. We used the area under the receiver operating characteristic curve to evaluate model performance. RESULTS: The training cohort consisted of 94 pediatric patients with low-grade gliomas (mean age, 9.4 years; 45 boys), and the external validation cohort comprised 21 pediatric patients with low-grade gliomas (mean age, 8.37 years; 12 boys). A 4-fold cross-validation scheme predicted BRAF status with an area under the curve of 0.75 (SD, 0.12) (95% confidence interval, 0.62–0.89) on the internal validation cohort. By means of the optimal hyperparameters determined by 4-fold cross-validation, the area under the curve for the external validation was 0.85. Age and tumor location were significant predictors of BRAF status (P values = .04 and <.001, respectively). Sex was not a significant predictor (P value = .96). CONCLUSIONS: Radiomics-based prediction of BRAF status in pediatric low-grade gliomas appears feasible in this bi-institutional exploratory study.

Background: Digital subtraction angiography is the gold standard for detecting and characterising aneurysms. Here, we assess the feasibility of commercial-grade deep learning software for the detection of intracranial aneurysms on whole-brain anteroposterior and lateral 2D digital subtraction angiography images. Material and methods: Seven hundred and six digital subtraction angiography images were included from a cohort of 240 patients (157 female, mean age 59 years, range 20–92; 83 male, mean age 55 years, range 19–83). Three hundred and thirty-five (47%) single frame anteroposterior and lateral images of a digital subtraction angiography series of 187 aneurysms (41 ruptured, 146 unruptured; average size 7±5.3 mm, range 1–5 mm; total 372 depicted aneurysms) and 371 (53%) aneurysm-negative study images were retrospectively analysed regarding the presence of intracranial aneurysms. The 2D data was split into testing and training sets in a ratio of 4:1 with 3D rotational digital subtraction angiography as gold standard. Supervised deep learning was performed using commercial-grade machine learning software (Cognex, ViDi Suite 2.0). Monte Carlo cross validation was performed. Results: Intracranial aneurysms were detected with a sensitivity of 79%, a specificity of 79%, a precision of 0.75, a F1 score of 0.77, and a mean area-under-the-curve of 0.76 (range 0.68–0.86) after Monte Carlo cross-validation, run 45 times. Conclusion: The commercial-grade deep learning software allows for detection of intracranial aneurysms on whole-brain, 2D anteroposterior and lateral digital subtraction angiography images, with results being comparable to more specifically engineered deep learning techniques.

Purpose: Differentiation of radiation necrosis from tumor progression in brain metastases treated with stereotactic radiosurgery (SRS) is challenging. For this, we assessed the performance of the centrally restricted diffusion sign. Methods: Patients with brain metastases treated with SRS who underwent a subsequent intervention (biopsy/resection) for a ring-enhancing lesion on preoperative MRI between 2000 and 2020 were included. Excluded were lesions containing increased susceptibility limiting assessment of DWI. Two neuroradiologists classified the location of the diffusion restriction with respect to the post-contrast T1 images as centrally within the ring-enhancement (the centrally restricted diffusion sign), peripherally correlating to the rim of contrast enhancement, both locations, or none. Measures of diagnostic accuracy and 95% CI were calculated for the centrally restricted diffusion sign. Cohen's kappa was calculated to identify the interobserver agreement. Results: Fifty-nine patients (36 female; mean age 59, range 40 to 80) were included, 36 with tumor progression and 23 with radiation necrosis based on histopathology. Primary tumors included 34 lung, 12 breast, 5 melanoma, 3 colorectal, 2 esophagus, 1 head and neck, 1 endometrium, and 1 thyroid. The centrally restricted diffusion sign was seen in 19/23 radiation necrosis cases (sensitivity 83% (95% CI 63 to 93%), specificity 64% (95% CI 48 to 78%), PPV 59% (95% CI 42 to 74%), NPV 85% (95% CI 68 to 94%)) and 13/36 tumor progression cases (difference p < 0.001). Interobserver agreement was substantial, at 0.61 (95% CI 0.45 to 70.8). Conclusion: We found a low probability of radiation necrosis in the absence of the centrally restricted diffusion sign.

MRI is negative in a large percentage of autoimmune encephalitis cases or lacks findings specific to an antibody. Even rarer is literature correlating the evolution of imaging findings with treatment timepoints. We aim to characterize imaging findings in autoimmune encephalitis at presentation and on follow up correlated with treatment timepoints for this rare disease. A full-text radiological information system search was performed for “autoimmune encephalitis” between January 2012 and June 2022. Patients with laboratory-identified autoantibodies were included. MRI findings were assessed in correlation to treatment timepoints by two readers in consensus. For statistical analysis, cell-surface vs intracellular antibody groups were assessed for the presence of early limbic, early extralimbic, late limbic, and late extralimbic findings using the χ² test. Thirty-seven patients (female n = 18, median age 58.8 years; range 25.7 to 82.7 years) with 15 different autoantibodies were included in the study. Twenty-three (62%) patients were MRI-negative at time of presentation; 5 of these developed MRI findings on short-term follow up. Of the 19 patients with early MRI findings, 9 (47%) demonstrated improvement upon treatment initiation (7/9 cell-surface group). There was a significant difference (p = 0.046) between the MRI spectrum of cell-surface vs intracellular antibody syndromes as cell-surface antibody syndromes demonstrated more early classic findings of limbic encephalitis and intracellular antibody syndromes demonstrated more late extralimbic abnormalities. MRI can be used to help narrow the differential diagnosis in autoimmune encephalitis and can be used as a monitoring tool for certain subtypes of this rare disease.