Commercial AI Model Diagnostic Accuracy for Intracranial Large- and Medium-Vessel Occlusion at Emergency CT Angiography

2026/04/15 by Henrik Andersson, Björn Hansen, Johan Wassélius · 1 voice
Medicine · #Acute Ischemic Stroke Management #Intracerebral and Subarachnoid Hemorrhage Research #Traumatic Brain Injury and Neurovascular Disturbances

paper · doi:10.1148/ryai.250749

openalex publication_date 2026/04/15 · openalex created_date 2026/04/16 · openalex updated_date 2026/07/16

Abstract

The commercial artificial intelligence model identified 42 examinations with occlusions not described in the original radiology reports (18.8% of all examinations with occlusions), with few false alerts, in a regional multicenter emergency head and neck CT angiogram sample.

Discussions

• Evaluating a commercial artificial intelligence model for diagnosing intracranial large- and medium-vessel occlusion on CT angiography in a multicenter emergency setting https://doi.org/10.1148/ryai.2 [bsky, 6 points, 1 comments]

Related

• Development and Validation of a Sham-AI Model for Intracranial Aneurysm Detection at CT Angiography
• Minimizing Human-Induced Variability in Quantitative Angiography for Robust and Explainable AI-Based Occlusion Prediction
• End-to-End Autonomous Quantification of Brain Aneurysm and Parent Artery Morphology at CT Angiography
• Examining Deployment and Refinement of the VIOLA-AI Intracranial Hemorrhage Model Using an Interactive NeoMedSys Platform
• Clinical Implementation of AI for Pulmonary Embolism Detection in over 30 000 CT Pulmonary Angiography Examinations