Sheth SA, Lopez-Rivera V, Barman A, et al. - In this investigation, researchers developed and validated an automated machine learning-based method that assesses for large vessel occlusion (LVO) and ischemic core volume in patients using a widely available modality, computed tomography angiogram (CTA). They identified patients with acute ischemic stroke and stroke mimics with contemporaneous CTA and computed tomography perfusion (CTP) with RAPID (IschemaView) postprocessing as a part of the emergent stroke workup from the prospectively maintained stroke registry and electronic medical record. Participants in the study were 297 patients. Data reported that mean CTP-RAPID ischemic core volume was 23 ± 42 mL. The DeepSymNet algorithm learned to autonomously define the CTA intracerebral vasculature and identified LVO with AUC 0.88. In addition, the method was able to determine infarct core as defined by CTP-RAPID from the CTA source images with AUC 0.88 and 0.90. In patients presenting in early (0–6 hours) and late (6–24 hours) time windows (AUCs 0.90 and 0.91, ischemic core ≤ 50 mL), these findings were maintained. These results show that the information required to carry out the endovascular therapy neuroimaging evaluation with comparable accuracy to advanced imaging modalities may be present in CTA and the ability of machine learning to automate the analysis.