- Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning
The authors developed and trained a novel deep learning model utilizing a diverse multi-institutional data set that was able to synthesize virtual contrast-enhanced T1-weighted images for primary brain tumors by using only noncontrast FLAIR, T2-weighted, and T1-weighted images.
- Prediction of Surgical Outcomes in Normal Pressure Hydrocephalus by MR Elastography
MR elastography allows noninvasive evaluation of mechanical properties of the brain altered by NPH. Different morphologic phenotypes of NPH are associated with unique mechanical signatures. Pattern analysis based on MRE is a promising method for improving diagnosis to distinguish NPH from other neurologic disorders that may have overlapping imaging and/or clinical presentations (such as Parkinson disease, Alzheimer disease, or progressive supranuclear palsy) and for predicting shunt outcomes.
- Clinical and Imaging Findings in Children with Myelin Oligodendrocyte Glycoprotein Antibody Associated Disease (MOGAD): From Presentation to Relapse
This study characterizes the CNS imaging manifestations of pediatric MOGAD. The authors also identify the clinical and imaging variables associated with relapse. There is an age-dependent imaging phenotype at presentation and first relapse, and older age at presentation is associated with shorter time to relapse.
- Newly Recognized Genetic Tumor Syndromes of the CNS in the 5th WHO Classification: Imaging Overview with Genetic Updates
In this review of the new 5th edition of the WHO classification, the authors focus on imaging and genetic characteristics of 8 new syndromes: Elongator protein complex-medulloblastoma syndrome, BRCA1-associated protein 1 tumor-predisposition syndrome, DICER1 syndrome, familial paraganglioma syndrome, melanoma-astrocytoma syndrome, Carney complex, Fanconi anemia, and familial retinoblastoma.