Artificial Intelligence and Acute Stroke Imaging

Summary: Artificial intelligence technology is a rapidly expanding field with many applications in acute stroke imaging, including ischemic and hemorrhage subtypes. Early identification of acute stroke is critical for initiating prompt intervention to reduce morbidity and mortality. AI can help with various aspects of the stroke treatment paradigm, including infarct or hemorrhage detection, segmentation, classification, large vessel occlusion detection, ASPECTS grading, and prognostication. Emerging AI techniques such as convolutional neural networks show promise in performing these imaging-based tasks efficiently and accurately. This review describes AI methods and available public and commercial platforms in stroke imaging, and summarizes the literature of current AI-driven applications for acute stroke triage, surveillance, and prediction.