Faculty Bibliography

History A 32-year-old woman presented to an ophthalmologist for bilateral blurry vision. She underwent MRI of the brain and orbits, which showed a focal abnormality within the pituitary gland. The patient was referred to an endocrinologist for further evaluation. Review of systems and physical examination by the endocrinologist revealed no symptoms or signs of endocrine dysfunction. Anterior pituitary hormone levels, including growth hormone, prolactin, thyroid stimulating hormone, follicular stimulating hormone, luteinizing hormone, and adrenocorticotropic hormone, were normal. Dynamic contrast-enhanced MRI of the sella and pituitary gland (Figs 1-3) and subsequent CT of the anterior skull base (Figs 4, 5) were performed.

BACKGROUND:Clinicians and machine classifiers reliably diagnose pilocytic astrocytoma (PA) on magnetic resonance imaging (MRI) but less accurately distinguish medulloblastoma (MB) from ependymoma (EP). One strategy is to first rule out the most identifiable diagnosis. OBJECTIVE:To hypothesize a sequential machine-learning classifier could improve diagnostic performance by mimicking a clinician's strategy of excluding PA before distinguishing MB from EP. METHODS:We extracted 1800 total Image Biomarker Standardization Initiative (IBSI)-based features from T2- and gadolinium-enhanced T1-weighted images in a multinational cohort of 274 MB, 156 PA, and 97 EP. We designed a 2-step sequential classifier - first ruling out PA, and next distinguishing MB from EP. For each step, we selected the best performing model from 6-candidate classifier using a reduced feature set, and measured performance on a holdout test set with the microaveraged F1 score. RESULTS:Optimal diagnostic performance was achieved using 2 decision steps, each with its own distinct imaging features and classifier method. A 3-way logistic regression classifier first distinguished PA from non-PA, with T2 uniformity and T1 contrast as the most relevant IBSI features (F1 score 0.8809). A 2-way neural net classifier next distinguished MB from EP, with T2 sphericity and T1 flatness as most relevant (F1 score 0.9189). The combined, sequential classifier was with F1 score 0.9179. CONCLUSION/CONCLUSIONS:An MRI-based sequential machine-learning classifiers offer high-performance prediction of pediatric posterior fossa tumors across a large, multinational cohort. Optimization of this model with demographic, clinical, imaging, and molecular predictors could provide significant advantages for family counseling and surgical planning.

CONCLUSION:A cutoff value of 6.0 mm for optic nerve sheath dilation may be used as a screening imaging marker to suspect elevated opening pressure with specificity of 88% in pediatric patients with new-onset idiopathic seizures.

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

BACKGROUND AND PURPOSE/OBJECTIVE:Atypical teratoid/rhabdoid tumors and medulloblastomas have similar imaging and histologic features but distinctly different outcomes. We hypothesized that they could be distinguished by MR imaging-based radiomic phenotypes. MATERIALS AND METHODS/METHODS:We retrospectively assembled T2-weighted and gadolinium-enhanced T1-weighted images of 48 posterior fossa atypical teratoid/rhabdoid tumors and 96 match-paired medulloblastomas from 7 institutions. Using a holdout test set, we measured the performance of 6 candidate classifier models using 6 imaging features derived by sparse regression of 900 T2WI and 900 T1WI Imaging Biomarker Standardization Initiative-based radiomics features. RESULTS:From the originally extracted 1800 total Imaging Biomarker Standardization Initiative-based features, sparse regression consistently reduced the feature set to 1 from T1WI and 5 from T2WI. Among classifier models, logistic regression performed with the highest AUC of 0.86, with sensitivity, specificity, accuracy, and F1 scores of 0.80, 0.82, 0.81, and 0.85, respectively. The top 3 important Imaging Biomarker Standardization Initiative features, by decreasing order of relative contribution, included voxel intensity at the 90th percentile, inverse difference moment normalized, and kurtosis-all from T2WI. CONCLUSIONS:Six quantitative signatures of image intensity, texture, and morphology distinguish atypical teratoid/rhabdoid tumors from medulloblastomas with high prediction performance across different machine learning strategies. Use of this technique for preoperative diagnosis of atypical teratoid/rhabdoid tumors could significantly inform therapeutic strategies and patient care discussions.

Background/UNASSIGNED:Diffuse intrinsic pontine gliomas (DIPGs) are lethal pediatric brain tumors. Presently, MRI is the mainstay of disease diagnosis and surveillance. We identify clinically significant computational features from MRI and create a prognostic machine learning model. Methods/UNASSIGNED:We isolated tumor volumes of T1-post-contrast (T1) and T2-weighted (T2) MRIs from 177 treatment-naïve DIPG patients from an international cohort for model training and testing. The Quantitative Image Feature Pipeline and PyRadiomics was used for feature extraction. Ten-fold cross-validation of least absolute shrinkage and selection operator Cox regression selected optimal features to predict overall survival in the training dataset and tested in the independent testing dataset. We analyzed model performance using clinical variables (age at diagnosis and sex) only, radiomics only, and radiomics plus clinical variables. Results/UNASSIGNED:= .02). Conclusions/UNASSIGNED:In this international study, we demonstrate the use of radiomic signatures to create a machine learning model for DIPG prognostication. Standardized, quantitative approaches that objectively measure DIPG changes, including computational MRI evaluation, could offer new approaches to assessing tumor phenotype and serve a future role for optimizing clinical trial eligibility and tumor surveillance.

Pleomorphic xanthoastrocytoma (PXA) is a rare type of brain tumor that affects children and young adults. Molecular prognostic markers of PXAs remain poorly established. Similar to gangliogliomas, PXAs show prominent immune cell infiltrate, but its composition also remains unknown. In this study, we correlated DNA methylation and BRAF status with clinical outcome and explored the tumor microenvironment. We performed DNA methylation in 21 tumor samples from 18 subjects with a histological diagnosis of PXA. MethylCIBERSORT was used to deconvolute the PXA microenvironment by analyzing the associated immune cell-types. Median age at diagnosis was 16 years (range 7-32). At median follow-up of 30 months, 3-year and 5-year overall survival was 73% and 71%, respectively. Overall survival ranged from 1 to 139 months. Eleven out of 18 subjects (61%) showed disease progression. Progression-free survival ranged from 1 to 89 months. Trisomy 7 and CDKN2A/B (p16) homozygous deletion did not show any association with overall survival (p = 0.67 and p = 0.74, respectively). Decreased overall survival was observed for subjects with tumors lacking the BRAF V600E mutation (p = 0.02). PXAs had significantly increased CD8 T-cell epigenetic signatures compared with previously profiled gangliogliomas (p = 0.0019). The characterization of immune cell-types in PXAs may have implications for future development of immunotherapy.

Despite the severity of coronavirus disease 2019 (COVID-19) being more frequently related to acute respiratory distress syndrome and acute cardiac and renal injuries, thromboembolic events have been increasingly reported. We report a unique series of young patients with COVID-19 presenting with cerebral venous system thrombosis. Three patients younger than 41 years of age with confirmed Severe Acute Respiratory Syndrome coronavirus 2 (SARS-Cov-2) infection had neurologic findings related to cerebral venous thrombosis. They were admitted during the short period of 10 days between March and April 2020 and were managed in an academic institution in a large city. One patient had thrombosis in both the superficial and deep systems; another had involvement of the straight sinus, vein of Galen, and internal cerebral veins; and a third patient had thrombosis of the deep medullary veins. Two patients presented with hemorrhagic venous infarcts. The median time from COVID-19 symptoms to a thrombotic event was 7 days (range, 2-7 days). One patient was diagnosed with new-onset diabetic ketoacidosis, and another one used oral contraceptive pills. Two patients were managed with both hydroxychloroquine and azithromycin; one was treated with lopinavir-ritonavir. All patients had a fatal outcome. Severe and potentially fatal deep cerebral thrombosis may complicate the initial clinical presentation of COVID-19. We urge awareness of this atypical manifestation.

Coronavirus disease 2019 (COVID-19) is a serious public health crisis and can have neurologic manifestations. This is a retrospective observational case series performed March 1-31, 2020, at New York University Langone Medical Center campuses. Clinical and imaging data were extracted, reviewed, and analyzed. Two hundred forty-two patients with COVID-19 underwent CT or MRI of the brain within 2 weeks after the positive result of viral testing (mean age, 68.7 ± 16.5 years; 150 men/92 women [62.0%/38.0%]). The 3 most common indications for imaging were altered mental status (42.1%), syncope/fall (32.6%), and focal neurologic deficit (12.4%). The most common imaging findings were nonspecific white matter microangiopathy (134/55.4%), chronic infarct (47/19.4%), acute or subacute ischemic infarct (13/5.4%), and acute hemorrhage (11/4.5%). No patients imaged for altered mental status demonstrated acute ischemic infarct or acute hemorrhage. White matter microangiopathy was associated with higher 2-week mortality (P < .001). Our data suggest that in the absence of a focal neurologic deficit, brain imaging in patients with early COVID-19 with altered mental status may not be revealing.